CVPR2020論文サマリ

EfficientDet: Scalable and Efficient Object Detection
by: 中嶋航大
ObjectDetection
PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
by: 綱島 秀樹
GAN Makeup
StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching
by: Teppei Kurita
GAN Domain Adaptation Stereo Depth
Wavelet Integrated CNNs for Noise-Robust Image Classification
by: Teppei Kurita
Wavelet Object Recognition
Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View Matching
by: Teppei Kurita
Cross-View Geo-Localization Aerial Localization
SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
by: Teppei Kurita
Autonomous Vehicles GAN Simulator Data Driven CG
On the Uncertainty of Self-Supervised Monocular Depth Estimation
by: Teppei Kurita
Self Supervised Uncertainty Monocular Depth
FroDO: From Detections to 3D Objects
by: Teppei Kurita
Multi-View 3D Object Reconstruction
Binarizing MobileNet via Evolution-Based Searching
by: Teppei Kurita
MobileNet Binary Neural Networks Group Convolution
Large-Scale Object Detection in the Wild From Imbalanced Multi-Labels
by: Teppei Kurita
Object Detection Multi-Label Softmax
Background Matting: The World Is Your Green Screen
by: Teppei Kurita
Matting Self-Supervised GAN
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
by: 綱島 秀樹
GAN 3D Prior Disentanglement Image Manipulation
Context Prior for Scene Segmentation
by: Teppei Kurita
Semantic Segmentation Prior
Robust 3D Self-Portraits in Seconds
by: Teppei Kurita
3D Reconstruction 3D Self-Portrait Volumetric Bundle Adjustment
SEAN: Image Synthesis With Semantic Region-Adaptive Normalization
by: 綱島 秀樹
GAN Normalization Style Injection Conditional Generation
Self-Supervised Viewpoint Learning From Image Collections
by: 榎本和馬
Self-Supervised Viewpoint
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
by: Rei Tamaru
adversarial person re-identification
Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial example robustness data augmentation adversarial training
Blurry Video Frame Interpolation
by: 中嶋航大
Deblurring frame interpolation
REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
by: Yue Qiu
Vision and Language Embodied AI Dataset
Domain Adaptive Image-to-Image Translation
by: 綱島 秀樹
GAN I2I DAI2I Domain Adaptation Attribute Transfer
Attentive Normalization for Conditional Image Generation
by: 中嶋航大
GAN Normalization
SketchyCOCO: Image Generation From Freehand Scene Sketches
by: 綱島 秀樹
GAN Sketch2Img Domain Transfer Edge2Img Dataset
X3D: Expanding Architectures for Efficient Video Recognition
by: Kensho Hara
Action Recognition 3D CNN
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training
by: Seitaro Shinagawa
vision-and-language pre-training masked language model navigation
Learning Better Lossless Compression Using Lossy Compression
by: Shoma Iwai
Image Compression Lossless Compression
Boosting Semantic Human Matting With Coarse Annotations
by: Masaki Taniguchi
human matting coarse annotated data
Dual Super-Resolution Learning for Semantic Segmentation
by: Takuji Tahara
Semantic Segmentation Single Image Super-Resolution
Image Search With Text Feedback by Visiolinguistic Attention Learning
by: Seitaro Shinagawa
vision-and-language image search fashion
Evolving Losses for Unsupervised Video Representation Learning
by: Kensho Hara
Self-supervised Learning Action Recognition
Weakly-Supervised Action Localization by Generative Attention Modeling
by: Komiki Maruyama
Weakly Supervised Learning Temporal Action Localization
SAPIEN: A SimulAted Part-Based Interactive ENvironment
by: Yue Qiu
Embodied AI Dataset
Guided Variational Autoencoder for Disentanglement Learning
by: hiroki tsujimoto
disentanglement VAE adversarial
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
by: Teppei Kurita
Deblur Prior Video
Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image
by: Teppei Kurita
Inverse Rendering Depth Surface Normal Intrinsic Decomposition Light Estimation SVBRDF Dataset
Gold Seeker: Information Gain From Policy Distributions for Goal-Oriented Vision-and-Langauge Reasoning
by: Seitaro Shinagawa
vision-and-language goal-oriented reinforcement learning reasoning bayesian
Instance-Aware Image Colorization
by: Teppei Kurita
Colorization Object Detection
HyperSTAR: Task-Aware Hyperparameters for Deep Networks
by: Teppei Kurita
Hyperparameter Meta Learning
Vision-Language Navigation With Self-Supervised Auxiliary Reasoning Tasks
by: Yue Qiu
Vision and Language Vision-Language Navigation
Fashion Editing With Adversarial Parsing Learning
by: Seitaro Shinagawa
fashion editing GAN in-paining
Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization
by: 飯田啄巳
Mislabel Noisy label robust learning
Actor-Transformers for Group Activity Recognition
by: Shunsuke Kogure
Action Recognition
SQuINTing at VQA Models: Introspecting VQA Models With Sub-Questions
by: Yue Qiu
Vision and Language Visual Question Answering Dataset
LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
by: Ryota Suzuki
LiDAR simulation self-driving
Intuitive, Interactive Beard and Hair Synthesis With Generative Models
by: Shoma Iwai
Image manipulation
Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve
by: Shoji Sonoyama
camera calibration bundle adjustment
Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination
by: Teppei Kurita
Inverse Rendering Stereo Multi-Plane Image Lighting Estimation
3D Packing for Self-Supervised Monocular Depth Estimation
by: Shoji Sonoyama
self-supervised learning monocular depth estimation SLAM
Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular Camera
by: 綱島 秀樹
NVS Novel View Synthesis Depth Prediction Video
Image Based Virtual Try-On Network From Unpaired Data
by: fnakamura
Virtual Try-on 仮想試着 着せ替え
MMTM: Multimodal Transfer Module for CNN Fusion
by: Yusuke Machii
Malti-modal gesture recognition audiovisual speech enhancement human action recognition
Prior Guided GAN Based Semantic Inpainting
by: Ho Ching Chiu
Image Inpainting GAN
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
by: Shoji Sonoyama
multi view stereo stereo matching cost volume depth estimation
Neural Network Pruning With Residual-Connections and Limited-Data
by: Tomoro Tokusumi
pruning 枝刈り 小規模データセット
Benchmarking Adversarial Robustness on Image Classification
by: Tomoki Tanimura
Robustness Adversarial Robustness Adversarial Training Image Classification Adversarial Attack Adversarial Defense
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image
by: yusuke saito
3D Object Detection Object Pose Prediction Object Reconstruction
Ego-Topo: Environment Affordances From Egocentric Video
by: Katsuyuki Nakamura
Egocentric vision Graph convolution
Improving Confidence Estimates for Unfamiliar Examples
by: Anonymous
familiar unfamiliar
Transformation GAN for Unsupervised Image Synthesis and Representation Learning
by: Hiroaki Aizawa
GAN self-supervised learning unsupervised representation learning
Generative Hybrid Representations for Activity Forecasting With No-Regret Learning
by: Shun.ishizaka
activity forecasting trajectory forecasting egocentric
What Makes Training Multi-Modal Classification Networks Hard?
by: pshiko
multi-modal classification video
A Neural Rendering Framework for Free-Viewpoint Relighting
by: Teppei Kurita
Inverse Rendering Relighting Multi-View
Focus on Defocus: Bridging the Synthetic to Real Domain Gap for Depth Estimation
by: Teppei Kurita
Focal Stack Depth Estimation Defocus
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks
by: Obi
normalization activation function
Oops! Predicting Unintentional Action in Video
by: Shun.ishizaka
unintentional dataset self-supervised learning
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
by: Hiroki Yamamoto
Dataset Driving
Don't Hit Me! Glass Detection in Real-World Scenes
by: Hiroki Yamamoto
Segmentation Glass Dataset
Hardware-in-the-Loop End-to-End Optimization of Camera Image Processing Pipelines
by: MatsuokaHikaru
Camera Image Processing Pipelines Object detection
Learning to Autofocus
by: Teppei Kurita
Focal Stack Depth Estimation Auto Focus
Quasi-Newton Solver for Robust Non-Rigid Registration
by: MatsuokaHikaru
Robust Non-Rigid Registration Quasi-Newton
Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings
by: Shunsuke Nakatsuka
Anomaly Detection Teacher-Student Learning
Bringing Old Photos Back to Life
by: Teppei Kurita
Image Restoration VAE GAN
Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations
by: Tomoki Tanimura
Adversarial Examples Certified Robustness Adversarial Robustness Semantic Adversarial Attack
Camouflaged Object Detection
by: Teppei Kurita
Object Detection Camouflaged Object Detection Dataset
Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations
by: Hiroaki Aizawa
3D scene understanding
Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
by: Hiroaki Aizawa
3D Reconstruction
A Multigrid Method for Efficiently Training Video Models
by: Kensho Hara
Action Recognition Video Recognition Efficient
What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images
by: Shintaro Yamamoto
Scene Text Recognition Adversarial Attack
What It Thinks Is Important Is Important: Robustness Transfers Through Input Gradients
by: Rei Tamaru
Adversarial Example Transfer Learning
12-in-1: Multi-Task Vision and Language Representation Learning
by: Shintaro Yamamoto
Vision-and-Language Multi-Task Learning
Learning Temporal Co-Attention Models for Unsupervised Video Action Localization
by: Komiki Maruyama
Unsupervised Learning Temporal Action Localization
BSP-Net: Generating Compact Meshes via Binary Space Partitioning
by: Yue Qiu
3D Vision;Mesh
DeepCap: Monocular Human Performance Capture Using Weak Supervision
by: Yue Qiu
3D Surface Reconstruction Pose Estimation 3D Vision
CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
by: 綱島 秀樹
GAN Anonymization
Syn2Real Transfer Learning for Image Deraining Using Gaussian Processes
by: Hao
syn2real image deraining
Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer
by: Keita Goto
person re-identification cross modal
TITAN: Future Forecast Using Action Priors
by: Ryo Fujii
Trajectory prediction egocentric View Action recognition
Explorable Super Resolution
by: Hao
SR、超解像度、編集
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
by: Yue Qiu
Saliency Map Estimation;RGB-D;CVAE;
Transferring Cross-Domain Knowledge for Video Sign Language Recognition
by: Yue Qiu
Word-level Sign Language Recognition;Sign News;Video;
Cross-Batch Memory for Embedding Learning
by: Yue Qiu
Deep Metric Learning;Hard Negative Instances
Visual Chirality
by: Hirokatsu Kataoka
Visual Chirality Data Augmentation
Squeeze-and-Attention Networks for Semantic Segmentation
by: Anonymous
Attention semantic segmentation
A Spatial RNN Codec for End-to-End Image Compression
by: Shoma Iwai
Image Compression
METAL: Minimum Effort Temporal Activity Localization in Untrimmed Videos
by: Komiki Maruyama
Few-shot Learning Weakly Supervised Learning Temporal Action Localization
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
by: Pavel Savkin
high resolution 3d reconstruction human shape implicit function monocular image
Efficient Neural Vision Systems Based on Convolutional Image Acquisition
by: Ryota Suzuki
optical system point spread function cnn
PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
by: Hiroaki Aizawa
3D Shape Generation Seq2Seq
Learning to Shadow Hand-Drawn Sketches
by: yasud
GAN hand-drawn shadow lighting
Geometry-Aware Satellite-to-Ground Image Synthesis for Urban Areas
by: Hiroaki Aizawa
cross-view synthesis
Total Deep Variation for Linear Inverse Problems
by: MatsuokaHikaru
image restoration Total Deep Variation Diverse inverse problems maximum a posterior estimator
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image
by: Hiroaki Aizawa
Part Decomposition 3D Reconstruction
DaST: Data-Free Substitute Training for Adversarial Attacks
by: 飯田啄巳
gan adversarial learning data-free online system substitute model black box
Hierarchical Human Parsing With Typed Part-Relation Reasoning
by: Seitaro Shinagawa
human parsing segmentation graph neural networks message-passing reasoning
Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data
by: 岡本大和
Transfer Learning
Footprints and Free Space From a Single Color Image
by: Shoji Sonoyama
segmentation depth estimation
Learning Memory-Guided Normality for Anomaly Detection
by: Shunsuke Nakatsuka
Anomaly Detection
Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
by: Teppei Kurita
3D Reconstruction Transparent Surface Normal
SpeedNet: Learning the Speediness in Videos
by: Teppei Kurita
Action Recognition Speediness Video
Self-Supervised Learning of Pretext-Invariant Representations
by: hiroki tsujimoto
representation learning Self-Supervised
RetinaTrack: Online Single Stage Joint Detection and Tracking
by: Michiya Abe
mot retinanet waymo
Revisiting Knowledge Distillation via Label Smoothing Regularization
by: Hiroki Yamamoto
Knowledge Distillation Transfer Learning
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs
by: Shun.ishizaka
scene graph dataset action recognition relationships compositional
3D Photography Using Context-Aware Layered Depth Inpainting
by: Teppei Kurita
3D Reconstruction Depth Occlusion
TextureFusion: High-Quality Texture Acquisition for Real-Time RGB-D Scanning
by: yusuke saito
RGB-D Scanning Texture Acquisition
Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization
by: Teppei Kurita
Light Field Computational Photography 4D Super Resolution
Learning Event-Based Motion Deblurring
by: Teppei Kurita
Dynamic Vision Sensor Event Based Camera Deblur
Panoptic-Based Image Synthesis
by: Teppei Kurita
Panoptic Map Image Synthesis
Adaptive Subspaces for Few-Shot Learning
by: Shuhei M Yoshida
few-shot learning subspace method
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
by: So Uchida
super-resolution data augmentation
A Self-supervised Approach for Adversarial Robustness
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial examples robustness self-supervised learning
End-to-End Illuminant Estimation Based on Deep Metric Learning
by: Teppei Kurita
Illuminant Estimation Triplet Loss Color Histogram Color Consistency ICDF
15 Keypoints Is All You Need
by: Shuhei M Yoshida
pose tracking PoseTrack Challenge tracking
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
by: Ryo Takahashi
Probabilistic Structural Latent Representation for Unsupervised Embedding
by: 綱島 秀樹
Unsupervised Embedding Retrieval Fine-grained Classification
Controllable Person Image Synthesis With Attribute-Decomposed GAN
by: 綱島 秀樹
GAN PIS Disentanglement Pose Transfer Virtual Try-on
From Image Collections to Point Clouds With Self-Supervised Shape and Pose Networks
by: HIroaki Aizawa
3D Reconstruction Point Cloud Differentiable Renderer
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
by: Rei Tamaru
Adversarial Example Model-Inversion GAN
Unpaired Image Super-Resolution Using Pseudo-Supervision
by: Ho Ching Chiu
Super Resolution Cycle Consistency GAN
SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings
by: Hiroaki Aizawa
Spatial Reasoning
BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion
by: Shoji Sonoyama
depth estimation 360 camera single image depth estimation
Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild
by: Hiroaki Aizawa
3D Reconstruction
Webly Supervised Knowledge Embedding Model for Visual Reasoning
by: Shintaro Yamamoto
Visual Reasoning Knowledge Base
Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial examples robustness
The GAN That Warped: Semantic Attribute Editing With Unpaired Data
by: 中嶋航大
Towards Backward-Compatible Representation Learning
by: Tomoki Tanimura
Representation Learning Life Long Learning Continuous Learning Image Retrieval Feature Extraction
Conditional Channel Gated Networks for Task-Aware Continual Learning
by: 岡本大和
Continual Learning
Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA
by: Shintaro Yamamoto
VQA TextVQA Transformer
End-to-End Adversarial-Attention Network for Multi-Modal Clustering
by: Yusuke Machii
Multi-Modal Adversarial clustering attention
Articulation-Aware Canonical Surface Mapping
by: Hiroaki Aizawa
Canonical Surface Mapping Articulation
WCP: Worst-Case Perturbations for Semi-Supervised Deep Learning
by: 岡本大和
Semi-supervised Learning worst-case perturbations model-based robustness sample-based robustness additive perturbations dropconnect perturbations
S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
by: Shuhei M Yoshida
self-supervised learning sequential data representation disentanglement
Iterative Context-Aware Graph Inference for Visual Dialog
by: Yue Qiu
Visual Dialog Graph CNN
Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules
by: Shoma Iwai
Image Compression
TA-Student VQA: Multi-Agents Training by Self-Questioning
by: Shintaro Yamamoto
VQA Reinforcement Learning
Skeleton-Based Action Recognition With Shift Graph Convolutional Network
by: Wataru Kudo
Action Recognition Graph Convolutional Network
Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
by: Kensho Hara
Physics Video Force Prediction
HybridPose: 6D Object Pose Estimation Under Hybrid Representations
by: Pavel Savkin
6D pose estimation edge symmetry keypoint SVD
Two Causal Principles for Improving Visual Dialog
by: Yue Qiu
Visual Dialog
UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space Translation
by: Ho Ching Chiu
Image Inpainting Unsupervised Learning Multiple-solution inpainting
Single-Shot Monocular RGB-D Imaging Using Uneven Double Refraction
by: Shoji Sonoyama
single shot depth estimation depth estimation double refraction
Intelligent Home 3D: Automatic 3D-House Design From Linguistic Descriptions Only
by: Ryota Suzuki
GAN GCN GAN GCN layout generation texture generation text-to-3d
Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions
by: Shoma Iwai
GAN Deep Fake
D2Det: Towards High Quality Object Detection and Instance Segmentation
by: Munetaka Minoguchi
object detection instance segmentation 2 stage detector
High-Resolution Daytime Translation Without Domain Labels
by: kiyo
Image-to-Image Translation
Few-Shot Open-Set Recognition Using Meta-Learning
by: 岡本大和
open-set few-shot meta-learning
Efficient Adversarial Training With Transferable Adversarial Examples
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial training adversarial example robustness
BachGAN: High-Resolution Image Synthesis From Salient Object Layout
by: Shoma Iwai
GAN Layout
Telling Left From Right: Learning Spatial Correspondence of Sight and Sound
by: Masuyama Yoshiki
self-supervised learning audio-visual multi modal object detection sound source separation
Adversarial Examples Improve Image Recognition
by: Rei Tamaru
Adversarial Example Image Recognition Batch Normalization
One Man's Trash Is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial examples robustness
Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object Localization
by: 堀田大地
WSOL
Orderless Recurrent Models for Multi-Label Classification
by: 堀田大地
multi-label clasiffication
Semantically Multi-Modal Image Synthesis
by: 綱島 秀樹
GAN Conditional Image Synthesis SMIS
Counterfactual Samples Synthesizing for Robust Visual Question Answering
by: Shintaro Yamamoto
VQA
Auxiliary Training: Towards Accurate and Robust Models
by: 福原吉博 (Yoshihiro Fukuhara)
robustness distillation trade-off
Disentangled Image Generation Through Structured Noise Injection
by: Ho Ching Chiu
GAN Image Generation Disentanglement
Generating and Exploiting Probabilistic Monocular Depth Estimates
by: Shoji Sonoyama
depth estimation single depth estimation C-VAE MAP estimation
Listen to Look: Action Recognition by Previewing Audio
by: Shun.ishizaka
action recognition audio-visual learning multi-modal video understanding
BBN: Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition
by: Hiroki Yamamoto
Class Imbalance Long tail Classification
SynSin: End-to-End View Synthesis From a Single Image
by: Anonymous
Image and video synthesis Neural Generative Models Novel view synthesis
PhraseCut: Language-Based Image Segmentation in the Wild
by: Shun.ishizaka
VQA dataset vision and language segmentation
Learning Multiview 3D Point Cloud Registration
by: yusuke saito
multiview 3D point cloud registration RGB-D
STAViS: Spatio-Temporal AudioVisual Saliency Network
by: Masuyama Yoshiki
audio-visual multi modal saliency map
Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias
by: pshiko
Few-Shot Class-Incremental Learning
by: Shuhei M Yoshida
few-shot learning class-incremental learning
Progressive Mirror Detection
by: Teppei Kurita
Mirror Mirror Detection Object Detection Edge Detection
Counterfactual Vision and Language Learning
by: Yue Qiu
Vision and Language Counterfactual Causal Reasoning Visual Question Ansering
Learn2Perturb: An End-to-End Feature Perturbation Learning to Improve Adversarial Robustness
by: Tomoki Tanimura
Adversarial Robustness Adversarial Defense Adversarial Training Noise Injection
Visual Commonsense R-CNN
by: Yue Qiu
Recognition Object Detection Vision and Language
Cascade EF-GAN: Progressive Facial Expression Editing With Local Focuses
by: Ho Ching Chiu
Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
by: Shintaro Yamamoto
Referring Expression Multi-Task Learning
Nested Scale-Editing for Conditional Image Synthesis
by: 綱島 秀樹
GAN Conditional Image Synthesis I2I Disentanglement
Differentiable Adaptive Computation Time for Visual Reasoning
by: Seitaro Shinagawa
differentiable visual reasoning adaptive computation time VQA
Active Speakers in Context
by: Yue Qiu
Active Speakers Detection Video Recognition
Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning
by: Kensho Hara
Human Attention Saliency Inverse Reinforcement Learning
UnrealText: Synthesizing Realistic Scene Text Images From the Unreal World
by: Yue Qiu
3D Dataset Scene Text Generation
Robustness Guarantees for Deep Neural Networks on Videos
by: Rei Tamaru
Adversarial Learning Optical Flow Video RNN
VQA With No Questions-Answers Training
by: Shintaro Yamamoto
VQA
MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
by: 綱島 秀樹
GAN Image Manipulation Mask2Img Face Style Injection
Show, Edit and Tell: A Framework for Editing Image Captions
by: Yue Qiu
Image Captioning Vision and Language
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
by: Mariko Nakano
Action Recognition Graph Convolutional Network
Deep Distance Transform for Tubular Structure Segmentation in CT Scans
by: 中村 優太
Radiology Segmentation CT scan Tubular structure Multi-task learning Geometry-aware
Neural Topological SLAM for Visual Navigation
by: Yue Qiu
Visual Navigation SLAM Embodied AI
Embodied Language Grounding With 3D Visual Feature Representations
by: Yue Qiu
3D Visual Feature Representations Vision and Language
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation From a Blackbox Model
by: Hiroki Ohashi
distillation active learning mix-up
Physically Realizable Adversarial Examples for LiDAR Object Detection
by: Rei Tamaru
Adversarial Example 3D Point Cloud
Vision-Dialog Navigation by Exploring Cross-Modal Memory
by: Yue Qiu
Visual Dialog Vision-Language Navigation
A Context-Aware Loss Function for Action Spotting in Soccer Videos
by: Komiki Maruyama
Weakly Supervised Learning Temporal Action Localization Video Summarization
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
by: Ryota Suzuki
sim2real embodied platform robot
Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for Mammogram Mass Detection
by: 藤中彩乃
# Crossmodal Learning # Graph Convolutional Network # Cross-view Correspondence Reasoning
An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers' Outputs
by: MatsuokaHikaru
Internal Covariate Shif Batch Normalization Earth Mover distance
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
by: Pavel Savkin
SLAM visual odometry VO monocular unsupervised depth DSO
Graph Structured Network for Image-Text Matching
by: Shintaro Yamamoto
Image-Text Matching Graph Matching
SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation
by: Komiki Maruyama
Weakly Supervised Learning Temporal Action Segmentation
Relative Interior Rule in Block-Coordinate Descent
by: MatsuokaHikaru
Max-Sum Potts model maximum a posteriori message-passing
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
by: Ryota Suzuki
3D detection pseudo-LiDAR end-to-end
Dataless Model Selection With the Deep Frame Potential
by: 中村真裕
neural network deep neural network
Unsupervised Person Re-Identification via Multi-Label Classification
by: Masanori YANO
Unsupervised Learning Person Re-Identification Transfer Learning
FocalMix: Semi-Supervised Learning for 3D Medical Image Detection
by: 中村 優太
3D Object detection Focal Loss Feature Pyramid Networks CT scan Lang Nodule Semi-supervised learning
SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation
by: Shoji Sonoyama
single depth estimation semantic segmentation instance segmentation
MPM: Joint Representation of Motion and Position Map for Cell Tracking
by: Issei Tomotsuka
cell microscopy object detection
Cross-Domain Correspondence Learning for Exemplar-Based Image Translation
by: 綱島 秀樹
GAN Domain Transfer Exemplar-guided
Music Gesture for Visual Sound Separation
by: Masuyama Yoshiki
audio-visual multi modal sound source separation
Learning a Neural Solver for Multiple Object Tracking
by: 遠藤大河
motion and tracking MOT MPN
Rotation Equivariant Graph Convolutional Network for Spherical Image Classification
by: 古川 遼
spherical image equivariance graph convolutional network
Training Quantized Neural Networks With a Full-Precision Auxiliary Module
by: Tomoro Tokusumi
Quantization Object Detection
Semantic Image Manipulation Using Scene Graphs
by: Seitaro Shinagawa
image manipulation image editing scene graph image generation GAN
Multi-Dimensional Pruning: A Unified Framework for Model Compression
by: Hiroki Ohashi
pruning model compression
Speech2Action: Cross-Modal Supervision for Action Recognition
by: Shun.ishizaka
action recognition cross-modal weakly supervised learning BERT
AdversarialNAS: Adversarial Neural Architecture Search for GANs
by: 綱島 秀樹
GAN NAS
Unsupervised Learning for Intrinsic Image Decomposition From a Single Image
by: Teppei Kurita
Intrinsic Decomposition Physics Constraint Albedo Shading
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
by: Anonymous
semantic segmentation pooling
Momentum Contrast for Unsupervised Visual Representation Learning
by: pshiko
contrastive-learning self-supervised unsupervised representation-leraning
Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
by: 堀田大地
GAN 3D
AdderNet: Do We Really Need Multiplications in Deep Learning?
by: Hiroki Ohashi
efficient training efficient inference
CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries
by: 藤中彩乃
CPR-GCN Conditional Partial-Residual Graph Convolutional Network 3D Hybrid Model Coronary Artery
Few-Shot Video Classification via Temporal Alignment
by: Hiroki Ohashi
few-shot learning video classification DTW
Learning Dynamic Routing for Semantic Segmentation
by: hiroki tsujimoto
semantic segmentation
Instance Segmentation of Biological Images Using Harmonic Embeddings
by: 藤中彩乃
Instance Segmentation Harmonic Embedding U-Net proposal-free approach
Computing the Testing Error Without a Testing Set
by: Anonymous
DNN without a Testing Set
Rethinking Classification and Localization for Object Detection
by: pshiko
object-detection R-CNN
Adversarial Latent Autoencoders
by: Shunsuke Nakatsuka
GANs Generative Models Autoencoder Representation Learning
Novel Object Viewpoint Estimation Through Reconstruction Alignment
by: Hiroaki Aizawa
Viewpoint Estimation
Unsupervised Learning From Video With Deep Neural Embeddings
by: hiroki tsujimoto
unsupervised learning action recognition
Unsupervised Person Re-Identification via Softened Similarity Learning
by: Masanori YANO
Unsupervised Learning Person Re-Identification Similarity Dissimilarity
Neural Voxel Renderer: Learning an Accurate and Controllable Rendering Tool
by: Hiroaki Aizawa
Differentiable Renderer Voxel
When NAS Meets Robustness: In Search of Robust Architectures Against Adversarial Attacks
by: Tomoki Tanimura
Adversarial Robustness Neural Architecture Search Adversarial Defense Adversarial Examples
Dynamic Fluid Surface Reconstruction Using Deep Neural Network
by: 榎本
3D reconstruction
Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning
by: 綱島 秀樹
GAN Conditional Image Syntheiss Semi-supervised Learning
MineGAN: Effective Knowledge Transfer From GANs to Target Domains With Few Images
by: Hiroaki Aizawa
GAN Knowledge Transfer
Recognizing Objects From Any View With Object and Viewer-Centered Representations
by: Hiroaki Aizawa
Object Recognition
Satellite Image Time Series Classification With Pixel-Set Encoders and Temporal Self-Attention
by: Hirokatsu Kataoka
satellite image pixel-set encoders self-attention
Wish You Were Here: Context-Aware Human Generation
by: Rei Tamaru
Pose Transfer Pose Generation GAN Semantic Maps
DMCP: Differentiable Markov Channel Pruning for Neural Networks
by: Tomoro Tokusumi
Channel Pruning Markov Process
Self-Supervised Scene De-Occlusion
by: Hiroaki Aizawa
Scene De-Occlusion Amodal Perception
View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis
by: yusuke saito
view-based graph-based 3D Shape Analysis RGB-D
Single-View View Synthesis With Multiplane Images
by: Hiroaki Aizawa
View Synthesis Multiplane Image
Dynamic Traffic Modeling From Overhead Imagery
by: Katsuyuki Nakamura
Application
UNAS: Differentiable Architecture Search Meets Reinforcement Learning
by: Obi
nas neural architecture search objective function
Single Image Reflection Removal Through Cascaded Refinement
by: Teppei Kurita
Reflection Removal Cascaded Refinement LSTM
Referring Image Segmentation via Cross-Modal Progressive Comprehension
by: Seitaro Shinagawa
semantic segmentation vision-and-language
What You See is What You Get: Exploiting Visibility for 3D Object Detection
by: Higaki Yoshinari
3D object detection LiDAR BEV
Adversarial Texture Optimization From RGB-D Scans
by: 榎本
reconstruction
Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging
by: Higaki Yoshinari
Compressive Imaging ADMM
Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning
by: Tomoki Tanimura
Adversarial Robustness Self-supervised Ensemble Adversarial Examples
Deep Generative Model for Robust Imbalance Classification
by: Shunsuke Nakatsuka
Imbalanced Data Classification Generative Models
Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform
by: Higaki Yoshinari
NLOS albedo normal
ViewAL: Active Learning With Viewpoint Entropy for Semantic Segmentation
by: 榎本
ActiveLearning SemanticSegmentation
Adversarial Feature Hallucination Networks for Few-Shot Learning
by: Shuhei M Yoshida
few-shot learning data augmentation GANs
RevealNet: Seeing Behind Objects in RGB-D Scans
by: Hiroaki Aizawa
3D instance segmentation 3D scan completion Semantic instance completion
Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images
by: 藤中彩乃
Multiple instance learning Domain adversarial normalization Multi-scale learning 弱教師あり学習
Learning to Manipulate Individual Objects in an Image
by: 綱島 秀樹
Image Manipulation Object-aware Representation Learning Disentanglement VAE
Compositional Convolutional Neural Networks: A Deep Architecture With Innate Robustness to Partial Occlusion
by: Hiroaki Aizawa
VIBE: Video Inference for Human Body Pose and Shape Estimation
by: 榎本
3D GAN estimation
PatchVAE: Learning Local Latent Codes for Recognition
by: Rei Tamaru
Unsupervised Learning Disentangled Learning Image Recognition VAE Representation Learning
DAVD-Net: Deep Audio-Aided Video Decompression of Talking Heads
by: Yue Qiu
Video Decompression Videos of Talking Heads Audio and Vision
SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification
by: 藤中彩乃
Selective objective switch SOS 冗長性 Paradoxical loss
Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
by: kiyo
Image Inpainting
A Disentangling Invertible Interpretation Network for Explaining Latent Representations
by: Hiroaki Aizawa
Interpretability Disentanglement
Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-Resolvers
by: So Uchida
Super-Resolution Filter Correction
Local Context Normalization: Revisiting Local Normalization
by: HayataEbisawa
Normalization
Boosting Few-Shot Learning With Adaptive Margin Loss
by: Shuhei M Yoshida
few-shot learning metric learning meta learning additive margin loss
Structure-Guided Ranking Loss for Single Image Depth Prediction
by: Shoji Sonoyama
single depth estimation ranking loss instance segmentation
MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps
by: HayataEbisawa
3D object detection motion prediction
Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging
by: Higaki Yoshinari
HDR DOE PSF Glare
Organ at Risk Segmentation for Head and Neck Cancer Using Stratified Learning and Neural Architecture Search
by: 榎本
medical segmentation
Orthogonal Convolutional Neural Networks
by: Anonymous
Deep Residual Flow for Out of Distribution Detection
by: Shunsuke Nakatsuka
Out of Distribution Detection Flow Based Model Generative Models
CNN-Generated Images Are Surprisingly Easy to Spot… for Now
by: Ho Ching Chiu
Image Forensic Fake Detection GAN
Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation
by: pshiko
video instance segmentation segmentation instance segmentation
Interpreting the Latent Space of GANs for Semantic Face Editing
by: Hiroaki Aizawa
Image Manipulation
RoutedFusion: Learning Real-Time Depth Map Fusion
by: yusuke saito
Depth Fusion RGB-D Multi-view3D reconstruction
GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
by: 遠藤大河
Motion and Tracking Optical Flow Geometric Matching
Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge
by: Masuyama Yoshiki
cross-modal multi-modal knowledge distillation meta learning
Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations
by: 山縣英介
disentangled adversarial
A Characteristic Function Approach to Deep Implicit Generative Modeling
by: 古川 遼
implicit generative models GANs characteristic function
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
by: 山縣英介
semantic human action
KFNet: Learning Temporal Camera Relocalization Using Kalman Filtering
by: yusuke saito
camera relocalization temporal camera relocalization kalman filter
Training Noise-Robust Deep Neural Networks via Meta-Learning
by: 山縣英介
label noise meta learning loss correction
PointRend: Image Segmentation As Rendering
by: pshiko
semantic segmentation instnace segmentation
Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation
by: Hiroki Ohashi
action segmentation domain adaptation self-supervised learning transductive learning
Generating Accurate Pseudo-Labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations
by: Obi
semi-supervised learning pseudo-label activation function
Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis
by: Teppei Kurita
Dataset Agriculture Semantic Segmentation NIR
Dynamic Refinement Network for Oriented and Densely Packed Object Detection
by: Hirokatsu Kataoka
Object Detection Densely Annotated Objects
Unsupervised Model Personalization While Preserving Privacy and Scalability: An Open Problem
by: Hirokatsu Kataoka
Privacy Preserving
Incremental Few-Shot Object Detection
by: Hiroki Ohashi
object detection few-shot learning incremental learning
Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization
by: Hirokatsu Kataoka
Object Detection Contextual Reasoning Faster R-CNN Cascade R-CNN
Multimodal Categorization of Crisis Events in Social Media
by: Hirokatsu Kataoka
Multimodal Categorization Crisis Event Detection SNS
Learning From Synthetic Animals
by: Hao
synthetic animals keypoints
Where, What, Whether: Multi-Modal Learning Meets Pedestrian Detection
by: Hirokatsu Kataoka
Pedestrian Detection Multimodal
Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models
by: Rei Tamaru
Attention GAN Sparcity
Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic Correspondence
by: yasud
Style Transfer 画風変換 GAN Colorization
Learning Physics-Guided Face Relighting Under Directional Light
by: Rei Tamaru
Image Transfer Relighting GAN
Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions
by: Shuhei M Yoshida
few-shot learning metric learning transformer set-to-set function
Leveraging 2D Data to Learn Textured 3D Mesh Generation
by: Hiroaki Aizawa
3D Shape Generation Mesh
NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
by: Munetaka Minoguchi
single shot detection feature pyramid
Deep Grouping Model for Unified Perceptual Parsing
by: Anonymous
semantic segmentation grouping process graph convolution
Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
by: 中嶋航大
Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
by: Yue Qiu
Visual Question Answering Causal Reasoning Dataset
FDA: Fourier Domain Adaptation for Semantic Segmentation
by: 中嶋航大
C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
by: 中村 優太
Neural Architecture Search evolutionary algorithm medical image segmentation
Which Is Plagiarism: Fashion Image Retrieval Based on Regional Representation for Design Protection
by: Hirokatsu Kataoka
Plagiarized Fashion Landmark Detection Image Retrieval
Hierarchical Conditional Relation Networks for Video Question Answering
by: Yue Qiu
Video Question Answering Conditional Relation Networks
Breaking the Cycle - Colleagues Are All You Need
by: fnakamura
Image-to-Image Translation Council-GAN without cycle-consistency
FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding
by: Hirokatsu Kataoka
Fine-grained Action Recognition FineGym
The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation
by: 綱島 秀樹
Pose Estimation Data Bias
Violin: A Large-Scale Dataset for Video-and-Language Inference
by: Shintaro Yamamoto
Vision-and-Language Dataset
MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
by: Hiroaki Aizawa
Image Synthesis Disentanglement
Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
by: Yue Qiu
Visual Navigation Meta Learning Unsupervised Reinforcement Learning
Cops-Ref: A New Dataset and Task on Compositional Referring Expression Comprehension
by: Yue Qiu
Refering Expression Vision and Language Dataset
AugFPN: Improving Multi-Scale Feature Learning for Object Detection
by: Munetaka Minoguchi
object detection feature pyramid network
3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset
by: yamada ryosuke
dataset 3d
DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers
by: Shuhei M Yoshida
few-shot learning earth mover's distance
Cascaded Refinement Network for Point Cloud Completion
by: Naoya Chiba
Point Cloud Completion Point Cloud Upsampling
Vec2Face: Unveil Human Faces From Their Blackbox Features in Face Recognition
by: 野中琢登
GAN
NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks
by: Tomoro Tokusumi
Pruning NAS
On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks
by: Naoya Chiba
Adversarial Attacks Point Cloud Isometry Robustness
Few-Shot Pill Recognition
by: Masanori YANO
Few-Shot Learning Recognition Image Classification Segmentation Dataset
Mapillary Street-Level Sequences: A Dataset for Lifelong Place Recognition
by: Anonymous
MSLS Place Recognition
Image Processing Using Multi-Code GAN Prior
by: Hao
GAN inversion prior image processing
Deep Optics for Single-Shot High-Dynamic-Range Imaging
by: Higaki Yoshinari
HDR DOE PSF
Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images
by: 綱島 秀樹
GAN Neural Renderer 3D Generation Unsupervised Self-Supervised Face Verification Face Identification Data Augmentation
Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs
by: 飯田啄巳
backdoor attack poisoning universal attack defense
ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
by: Shoji Sonoyama
human pose estimation active vision drone
Temporal Pyramid Network for Action Recognition
by: Anonymous
Action Recognition
Visual-Textual Capsule Routing for Text-Based Video Segmentation
by: 日坂　幸次
Vision and Language
SuperGlue: Learning Feature Matching With Graph Neural Networks
by: Shoji Sonoyama
feature matching local feature graph neural network SfM SLAM
Meta-Transfer Learning for Zero-Shot Super-Resolution
by: So Uchida
Super-Resolution Internal Learning Meta Learning
Deep Image Spatial Transformation for Person Image Generation
by: Hiroaki Aizawa
Pose-guided person image generation
DUNIT: Detection-Based Unsupervised Image-to-Image Translation
by: kiyo
Image-to-Image Translation
Tracking by Instance Detection: A Meta-Learning Approach
by: 遠藤大河
物体追跡 物体検出
Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection
by: pshiko
object detection anchor-based anchor-free
CookGAN: Causality Based Text-to-Image Synthesis
by: Hirokatsu Kataoka
GAN Image Synthesis Cooking
You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions
by: Katsuyuki Nakamura
egocentric vision pose estimation
ClusterFit: Improving Generalization of Visual Representations
by: Hirokatsu Kataoka
Self-supervised Learning ClusterFit
CycleISP: Real Image Restoration via Improved Data Synthesis
by: Teppei Kurita
Noise Reduction RAW sRGB ISP Attention
Modality Shifting Attention Network for Multi-Modal Video Question Answering
by: Shintaro Yamamoto
Video Question Answering
Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector
by: Hiroki Ohashi
object detection few-shot learning new dataset
Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks
by: 岡本大和
Robust Learning; Bayesian Deep Learning; Semi-supervised Learning
Graph-Structured Referring Expression Reasoning in the Wild
by: 日坂　幸次
Vision and Language
Unbiased Scene Graph Generation From Biased Training
by: 綱島 秀樹
Causal Inference Counterfactual SGG Scene Graph Generation
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
by: Shoma Iwai
IQA Image quality assessment
Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions
by: Yue Qiu
3D Vision 3D Scene Graph PointNet Graph NN
PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving
by: HayataEbisawa
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
by: Yue Qiu
Vision and Language Egocentric Vision Dataset
Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
by: Yue Qiu
Scene Text Detection Graph NN Relational Reasoning
RiFeGAN: Rich Feature Generation for Text-to-Image Synthesis From Prior Knowledge
by: 中村 優太
Text-to-image generation Text-to-Image Synthesis multi-captions generative adversarial networks
In Defense of Grid Features for Visual Question Answering
by: Shintaro Yamamoto
Vision-and-Language Attention
IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
by: Anonymous
3D Medicine disease
Transferring Dense Pose to Proximal Animal Classes
by: Hiroaki Aizawa
Transfer Learning
Visual Grounding in Video for Unsupervised Word Translation
by: Masuyama Yoshiki
multi-modal machine translation
Multi-Modality Cross Attention Network for Image and Sentence Matching
by: Shintaro Yamamoto
Image-Text Matching Transformer
Fantastic Answers and Where to Find Them: Immersive Question-Directed Visual Attention
by: Yue Qiu
Visual Attention Visual Question Answering Vision and Language
End-to-End Learning of Visual Representations From Uncurated Instructional Videos
by: Seito Kasai
Action Recognition Self-supervised Learning Multimodal
Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness
by: Shoji Sonoyama
multi view stereo adaptive thin volume depth estimation
Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds
by: Naoya Chiba
Point Cloud Segmentation Weakly Supervised 3D Semantic Segmentation
DualSDF: Semantic Shape Manipulation Using a Two-Level Representation
by: 綱島 秀樹
3D Generation 3D Manipulation
Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention
by: Shuhei M Yoshida
zero-shot learning attention mechanism
Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
by: Naoya Chiba
Point Cloud Object Detection LiDAR
Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax
by: Masanori YANO
Object Detection Instance Segmentation Imbalanced Data
Dynamic Graph Message Passing Networks
by: Takuji Tahara
Graph Semantic Segmentation Instance Segmentation Object Detection
MaskFlownet: Asymmetric Feature Matching With Learnable Occlusion Mask
by: 遠藤大河
機械学習 Optical Flow AsymOFMM
On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering
by: Seitaro Shinagawa
vision-and-language VQA scene text detection
Multi-View Neural Human Rendering
by: yusuke saito
dynamic 3D reconstruction multi-view
AOWS: Adaptive and Optimal Network Width Search With Latency Constraints
by: Obi
NAS neural architecture search slimmable network width search
Recurrent Feature Reasoning for Image Inpainting
by: Seitaro Shinagawa
in-painting image generation partial convolution reasoning contextual attention
Learning Texture Transformer Network for Image Super-Resolution
by: So Uchida
Super-Resolution Reference-based Super-Resolution Transformer Attention
How Useful Is Self-Supervised Pretraining for Visual Tasks?
by: Hiroki Ohashi
self-supervised learning
Deblurring by Realistic Blurring
by: Teppei Kurita
Blur Deblur GAN SinGAN
Video Modeling With Correlation Networks
by: Kensho Hara
Action Recognition Motion Representation
ColorFool: Semantic Adversarial Colorization
by: Tomoki Tanimura
Adversarial Attack Semantic Segmentation Black Box Attack Adversarial Examples Color Space
Towards Photo-Realistic Virtual Try-On by Adaptively Generating-Preserving Image Content
by: 綱島 秀樹
Virtual Try-on
Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning
by: Hiroki Ohashi
self-supervised learning video data action recognition video retrieval
How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework
by: 榎本
Self-Supervised Learning of Interpretable Keypoints From Unlabelled Videos
by: Hiroaki Aizawa
Self-supervised Learning
Fine-Grained Image-to-Image Transformation Towards Visual Recognition
by: Shoma Iwai
Image Transformation
3D Part Guided Image Editing for Fine-Grained Object Understanding
by: Yue Qiu
3D Editing Semantic segmentation
Hierarchical Graph Attention Network for Visual Relationship Detection
by: Yue Qiu
Visual Relationship Detection Graph NN
Low-Rank Compression of Neural Nets: Learning the Rank of Each Layer
by: Kiro Otsu
Neural network compression low-rank optimization
Weakly Supervised Visual Semantic Parsing
by: Yue Qiu
Weakly Supervised Learning Visual Semantic Parsing
Attention-Guided Hierarchical Structure Aggregation for Image Matting
by: Masaki Taniguchi
alpha matting attention
Online Knowledge Distillation via Collaborative Learning
by: Yue Qiu
Knowledge Distillation
End-to-End Camera Calibration for Broadcast Videos
by: Hirokatsu Kataoka
Camera Calibration Sports Scene Basketball
ActionBytes: Learning From Trimmed Videos to Localize Actions
by: Hirokatsu Kataoka
Action Localization Action Recognition
Distilling Cross-Task Knowledge via Relationship Matching
by: 岡本大和
Knowledge Distillation Model Reuse Knowledge Transfer Cross-Task Learning Embedding Learning
Category-Level Articulated Object Pose Estimation
by: Hirokatsu Kataoka
Point Cloud Depth Image 3D Object Recognition
Cross-Domain Detection via Graph-Induced Prototype Alignment
by: 岡本大和
Cross-domain Detection Relation Graph Prototype-based Domain Adaptation Balanced Training
Mask Encoding for Single Shot Instance Segmentation
by: pshiko
instance segmentation single stage COCO
DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing
by: Naoya Chiba
Implicit Function DeepSDF Rendering
Deep Parametric Shape Predictions Using Distance Fields
by: Naoya Chiba
Distance Field Chamfer Distance Font
Rethinking Zero-Shot Video Classification: End-to-End Training for Realistic Applications
by: Shuhei M Yoshida
SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
by: Naoya Chiba
Differentiable Rendering Signed Distance Fields Single-view 3D Reconstruction
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
by: pacifinapacific
MOT Tracking 3DCNN
Robust Learning Through Cross-Task Consistency
by: Shun.ishizaka
consistency multi-task 3D robust surface normals depth
Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation
by: Katsuyuki Nakamura
egocentric vision hand segmentation domain adaptation self-supervision
Single-Stage 6D Object Pose Estimation
by: Shoji Sonoyama
pose estimation single image
Improving Convolutional Networks With Self-Calibrated Convolutions
by: Yusuke Kyokawa
recognition architecture cnn
ManiGAN: Text-Guided Image Manipulation
by: 綱島 秀樹
GAN Image Manipulation Text-guided Image Manipulation
Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
by: 鏡川悠介
domain adaptation style transfer semantic segmentation
Joint 3D Instance Segmentation and Object Detection for Autonomous Driving
by: Higaki Yoshinari
LiDAR 3D instance segmentation bounding box
StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images
by: Ho Ching Chiu
GAN Image Synthesis Cycle Consistency Rig-like control
Local Implicit Grid Representations for 3D Scenes
by: Naoya Chiba
Local Implicit Grid 3D Reconstruction Implicit Surface
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective
by: pshiko
class imbalanced data log tailed data recognition domain adaptation
TEA: Temporal Excitation and Aggregation for Action Recognition
by: Anonymous
Action Recognition
Self-Supervised Learning of Video-Induced Visual Invariances
by: Hiroki Ohashi
self-supervised learning video transfer learning
Straight to the Point: Fast-Forwarding Videos via Reinforcement Learning Using Textual Data
by: Shintaro Yamamoto
Fast-forwarding Reinforcement Learning
Real-Time Panoptic Segmentation From Dense Detections
by: Masaki Taniguchi
panoptic segmentation single-shot real-time
Exploiting Joint Robustness to Adversarial Perturbations
by: Tomoki Tanimura
Adversarial Robustness Ensemble Learning Adversarial Examples Adversarial Defense
Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
by: Shintaro Yamamoto
VQA GNN
A Physics-Based Noise Formation Model for Extreme Low-Light Raw Denoising
by: Teppei Kurita
CMOS Image Sensor Noise Model Noise Reduction NR
Cross-Domain Document Object Detection: Benchmark Suite and Method
by: Shintaro Yamamoto
Document Analysis Domain Adaptation Object Detection
Better Captioning With Sequence-Level Exploration
by: 中村 優太
Image captioning Video captioning Reinforcement learning
Deep Snake for Real-Time Instance Segmentation
by: Masaki Taniguchi
instance segmentation snake algorithm graph convolutional network
Global Texture Enhancement for Fake Face Detection in the Wild
by: Shoma Iwai
Deepfake detection fake face detection
Reciprocal Learning Networks for Human Trajectory Prediction
by: Ryo Fujii
Trajectory prediction GAN adversarial attack
Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
by: Hiroaki Aizawa
Few-shot Classification Fine-grained Classification
Deep Fair Clustering for Visual Learning
by: Ryo Takahashi
fairness 公平性 クラスタリング
DeepFaceFlow: In-the-Wild Dense 3D Facial Motion Estimation
by: 遠藤大河
Motion and Tracking Facial Recognition Optical Flow
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
by: Ho Ching Chiu
Super Resolution GAN Self-supervised
SSRNet: Scalable 3D Surface Reconstruction Network
by: Naoya Chiba
3D Surface Reconstruction Implicit Surface 3D Reconstruction
Image2StyleGAN++: How to Edit the Embedded Images?
by: Anonymous
GAN StyleGAN Inpainting Style transfer Reconstruction
Deep Global Registration
by: Shoji Sonoyama
registration point cloud pose estimation
State-Relabeling Adversarial Active Learning
by: 岡本大和
active learning adversarial learning uncertainty relabel
Context Aware Graph Convolution for Skeleton-Based Action Recognition
by: Mariko Nakano
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
by: pshiko
network architecture search recognition localization coco
Mixture Dense Regression for Object Detection and Human Pose Estimation
by: Anonymous
LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation
by: Naoya Chiba
Object Pose Estimation 3D shape learning View Synthesis
ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes
by: Naoya Chiba
3D Object Detection RGB-D Deep Hough Voting
End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds
by: Naoya Chiba
Point Cloud Registration Multi-View CNN View Pooling
Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects
by: Shun.ishizaka
hand pose estimation hand-object interaction GAN 3D mesh model
Learning to Super Resolve Intensity Images From Events
by: Teppei Kurita
Event Camera DVS Dynamic Vision Sensor Super Resolution RNN
SwapText: Image Based Texts Transfer in Scenes
by: Yue Qiu
Text Transfer GAN
Set-Constrained Viterbi for Set-Supervised Action Segmentation
by: Kensho Hara
Action Segmentation HMM Viterbi Weakly-supervised
More Grounded Image Captioning by Distilling Image-Text Matching Model
by: Yue Qiu
Image Captioning Knowledge Distillation
Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion
by: Ryota Suzuki
optical flow 3D optical flow local affine transformation
OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
by: Ryota Suzuki
octree pointcloud compression
Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
by: Shoma Iwai
GAN Semantic Image Synthesis Semantic Cross-View Image Translation
Normalized and Geometry-Aware Self-Attention Network for Image Captioning
by: Yue Qiu
Image Captioning
Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task
by: Ryota Suzuki
reinforcement learning keypoint matching
Meshed-Memory Transformer for Image Captioning
by: Yue Qiu
Image Captioning Transformer
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
by: Ryota Suzuki
HDR camera pipeline
Transform and Tell: Entity-Aware News Image Captioning
by: Yue Qiu
News Image Captioning Image Captioning Transformer
Detecting Attended Visual Targets in Video
by: Hiroki Ohashi
gaze attention target visual target video gaze estimation
Context-Aware and Scale-Insensitive Temporal Repetition Counting
by: Komiki Maruyama
Action Repetition Action Counting
Distilling Knowledge From Graph Convolutional Networks
by: Komiki Maruyama
Graph Convolutional Network Knowledge Distillation
End-to-End Optimization of Scene Layout
by: 綱島 秀樹
Scene Graph Layout Generation Conditional Layout Generation
Uncertainty-Aware Score Distribution Learning for Action Quality Assessment
by: Komiki Maruyama
Action Quality Assessment
G-TAD: Sub-Graph Localization for Temporal Action Detection
by: Komiki Maruyama
Temporal Action Localization Graph Convolutional network
nuScenes: A Multimodal Dataset for Autonomous Driving
by: Michiya Abe
dataset autonomous driving lidar rader 3d bounding box nuScenes
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild
by: Komiki Maruyama
Periodicity Detection Repetition Counting
Maintaining Discrimination and Fairness in Class Incremental Learning
by: yamada ryosuke
incremental learning fairness class imbalance
Optimizing Rank-Based Metrics With Blackbox Differentiation
by: MatsuokaHikaru
Learning to Rank LR mAP Blackbox Differentiation
Spatiotemporal Fusion in 3D CNNs: A Probabilistic View
by: 若宮天雅
Video Recognition
PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling
by: Naoya Chiba
Point Cloud Processing Adaptive Sapling Object Detection Semantic Segmentation
Say As You Wish: Fine-Grained Control of Image Caption Generation With Abstract Scene Graphs
by: 日坂　幸次
Vision and Language
Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion
by: Teppei Kurita
Face Restoration Landmark MSL AdaIN
Learning to Structure an Image With Few Colors
by: Masanori YANO
Recognition Image Classification Color Quantization Regularization
Sign Language Transformers: Joint End-to-End Sign Language Recognition and Translation
by: 日坂　幸次
Vision and Language
CvxNet: Learnable Convex Decomposition
by: 寺田英雄
convex autoencoder cvxnet end-to-end 3d-reconstruction
What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation
by: 藤中彩乃
半教師あり学習 転移学習 Unsupervised domain adaptation Semantic segmentation Crossmodal learning
ActBERT: Learning Global-Local Video-Text Representations
by: Shintaro Yamamoto
Vision-and-Language Pre-training
Exploit Clues From Views: Self-Supervised and Regularized Learning for Multiview Object Recognition
by: yamada ryosuke
multi-view self-supervised learning
A U-Net Based Discriminator for Generative Adversarial Networks
by: kiyo
GAN
Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition
by: yamada ryosuke
fashion two-stream
Unsupervised Representation Learning for Gaze Estimation
by: hiroki tsujimoto
gaze estimation unsupervised learning representation learning few-shot learning disentanglement
Information-Driven Direct RGB-D Odometry
by: yusuke saito
visual odometry visual slam information-based rgb-d
DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction With Deep T1 Prior
by: 中村 優太
MRI reconstruction
Advancing High Fidelity Identity Swapping for Forgery Detection
by: Ho Ching Chiu
Face Swap GAN Attention Denormalization Self-supervision
Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning
by: yamada ryosuke
fairness face recognition reinforcement learning
GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-Wise Transformations
by: Naoya Chiba
Graph Convolutional Neural Networks Transformation Equivariant Representations Unsupervised Learning
BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Networks
by: yamada ryosuke
multi-view dataset
HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
by: Higaki Yoshinari
Object detection LiDAR BEV Multi-scale
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
by: Higaki Yoshinari
3D point cloud object detection context
Fashion Outfit Complementary Item Retrieval
by: yamada ryosuke
fashion
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
by: Naoya Chiba
3D Object Detection Point Cloud PointVoxel-RCNN
Fast Soft Color Segmentation
by: Masanori YANO
Segmentation Self-Supervised Learning
Inter-Task Association Critic for Cross-Resolution Person Re-Identification
by: Anonymous
Person Re-Identification resolution
Something-Else: Compositional Action Recognition With Spatial-Temporal Interaction Networks
by: Katsuyuki Nakamura
action recognition compositionality dataset
Learning Selective Self-Mutual Attention for RGB-D Saliency Detection
by: yusuke saito
silency detection RGB-D Self-Mutual Attention Non-local network
Polishing Decision-Based Adversarial Noise With a Customized Sampling
by: 山縣英介
AE boundary attack
Flow Contrastive Estimation of Energy-Based Models
by: 古川 遼
enegy-based model flow-based model contrastive estimation joint training
Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial examples robustness adversarial detection
Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion
by: 岡本大和
model inversiond ata-free distillation transfer pruning compression incremental learning continual learning efficient image synthesis explainable ai
Unsupervised Adaptation Learning for Hyperspectral Imagery Super-Resolution
by: Teppei Kurita
HIS MIS Hyper Spectral Multi Spectral Super Resolution
Deformable Siamese Attention Networks for Visual Object Tracking
by: Anonymous
Object Tracking Siamese Deformable Siamese Attention
Predicting Lymph Node Metastasis Using Histopathological Images Based on Multiple Instance Learning With Deep Graph Convolution
by: 中村 優太
Histopathological Images Multi-instance learning Lymph Node Metastasis Cancer Graph Convolutional Network VAE-GAN weakly-supervised learning
ADINet: Attribute Driven Incremental Network for Retinal Image Classification
by: 藤中彩乃
ADINet Attribute driven incremental network 画像分類 Dynamical training Incremental learning framework
Unified Dynamic Convolutional Network for Super-Resolution With Variational Degradations
by: Ho Ching Chiu
Super Resolution Dynamic Convolution Multiple Degradation
Structure Boundary Preserving Segmentation for Medical Image With Ambiguous Boundary
by: 中村 優太
Edge Detection Semantic Segmentation Skin Lesion Ultrasound
Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-Weighting
by: 藤中彩乃
教師なし学習 Unsupervised domain adaptation (UDA) Instance segmentation Cyc-consistency panoptic domain adaptive mask R-CNN (CyC-PDAM) task re-weighting
GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction
by: 中村 優太
Parallel Imaging MRI U-Net GRAPPA
GroupFace: Learning Latent Groups and Constructing Group-Based Representations for Face Recognition
by: yamada ryosuke
face recognition
Scale-Equalizing Pyramid Convolution for Object Detection
by: Higaki Yoshinari
Object Detection feature pyramid 3D convolution
Generating 3D People in Scenes Without People
by: Katsuyuki Nakamura
Optical Flow in Dense Foggy Scenes Using Semi-Supervised Learning
by: Higaki Yoshinari
Optical Flow fog
Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences
by: Seitaro Shinagawa
video grounding vision-and-language localization
Structure-Preserving Super Resolution With Gradient Guidance
by: Ho Ching Chiu
Super Resolution Gradient Guidance
Enhancing Generic Segmentation With Learned Region Representations
by: hiroki tsujimoto
representation learning semantic segmentation generic segmentation edge detection
ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network
by: Masanori YANO
Object Detection Dataset
Joint Texture and Geometry Optimization for RGB-D Reconstruction
by: yusuke saito
3D reconstruction rgb-d joint texture optimization geometry optimization high-boost normal
C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds
by: Naoya Chiba
Generative Flow Model Point Cloud Generation Image Manipulation
3DRegNet: A Deep Neural Network for 3D Point Registration
by: Naoya Chiba
3D Registration Point Cloud Registration
Point Cloud Completion by Skip-Attention Network With Hierarchical Folding
by: Naoya Chiba
Point Cloud Completion Hierarchical Folding Point Cloud Auto Encoder
Enhancing Cross-Task Black-Box Transferability of Adversarial Examples With Dispersion Reduction
by: 山縣英介
AEs transferability feature map
Siam R-CNN: Visual Tracking by Re-Detection
by: 遠藤大河
Visual Object Tracking Object Tracking Faster R-CNN
Rethinking Performance Estimation in Neural Architecture Search
by: Obi
NAS neural architecture search performance estimation
Learning to Generate 3D Training Data Through Hybrid Gradient
by: 山縣英介
synthetic image blackbox optimization
Improved Few-Shot Visual Classification
by: Shuhei M Yoshida
few-shot learning deep metric learning Mahalanobis distance
Seeing the World in a Bag of Chips
by: Teppei Kurita
Surface Light Fields RGBD Illumination Estimation
Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution
by: Ho Ching Chiu
Super Resolution Self-supervision
Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning
by: Seito Kasai
Cross-modal Retrieval Vision & Language
Learning Oracle Attention for High-Fidelity Face Completion
by: Shoma Iwai
face image synthesis iamge inpainting
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
by: Naoya Chiba
Point Cloud 3D Instance Segmentation
FPConv: Learning Local Flattening for Point Convolution
by: Naoya Chiba
Point Cloud Convolution 2D Projection
Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations
by: 福原吉博 (Yoshihiro Fukuhara)
universal adversarial examples adversarial examples
A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image
by: 藤中彩乃
4D spatiotemporal volumetric interpolation network (SVIN) 時空間モデル 動画補間 教師なし学習
Unity Style Transfer for Person Re-Identification
by: Yukitaka Tsuchiya
re-ID GAN
DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization
by: 綱島 秀樹
Copy-move Forgery Detection
PointAugment: An Auto-Augmentation Framework for Point Cloud Classification
by: Naoya Chiba
Point Cloud Classification Data Augmentation Adversarial Training
Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networks
by: 藤中彩乃
位置合わせ Unsupervised symmetric image registration CNN 逆変換
Extreme Relative Pose Network Under Hybrid Representations
by: Shoji Sonoyama
RGB-D pose estimation
Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts
by: Anonymous
semantic segmentation semantic boundary detection
RPM-Net: Robust Point Matching Using Learned Features
by: Naoya Chiba
Point Cloud Registration Point Cloud Matching
Semantic Pyramid for Image Generation
by: fnakamura
image generation GAN generative adversarial networks
Grid-GCN for Fast and Scalable Point Cloud Learning
by: Naoya Chiba
Graph Convolutional Network Point Cloud Classification Point Cloud Segmentation
Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping
by: fnakamura
image-to-image translation image generation GAN generative adversarial networks
P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
by: Naoya Chiba
Point Cloud Tracking 3D Object Tracking Point-to-Box
A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning
by: 岡本大和
multi-label learning zero-shot learning few-shot learning attention
Fast MSER
by: Masanori YANO
Object Detection Feature
Learning Interactions and Relationships Between Movie Characters
by: 若宮天雅
Video Recognition
Proxy Anchor Loss for Deep Metric Learning
by: hiroki tsujimoto
metric learning
Gate-Shift Networks for Video Action Recognition
by: Anonymous
Understanding Human Hands in Contact at Internet Scale
by: Katsuyuki Nakamura
Human-object interaction Hand detection Dataset
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
by: yusuke saito
3D reconstruction multi view Cost Volume Pyramid Depth Inference
Toward a Universal Model for Shape From Texture
by: 山縣英介
shape texture 3pgame
GAN Compression: Efficient Architectures for Interactive Conditional GANs
by: iida
Compression cGAN GAN
Deep White-Balance Editing
by: Teppei Kurita
White Balance AWB
From Paris to Berlin: Discovering Fashion Style Influences Around the World
by: Hirokatsu Kataoka
Fashion Trend SNS
Towards Global Explanations of Convolutional Neural Networks With Concept Attribution
by: Hirokatsu Kataoka
Explainability Interpretability
Learning Unseen Concepts via Hierarchical Decomposition and Composition
by: Yue Qiu
Zero-shot Learning
Self-Supervised Deep Visual Odometry With Online Adaptation
by: Shoji Sonoyama
visual odometry self supervised learning meta learning online adaptation
Discriminative Multi-Modality Speech Recognition
by: Yue Qiu
Audio Speech Recognition Multi-modality Speech Recognition
Learning From Web Data With Self-Organizing Memory Module
by: Yue Qiu
Web Data Learning from Web Data
Noise Robust Generative Adversarial Networks
by: fnakamura
image generation generative adverarial networks GANs
SAM: The Sensitivity of Attribution Methods to Hyperparameters
by: Ryo Takahashi
Learning Visual Emotion Representations From Web Data
by: Yue Qiu
Web data Emotion Recognition Zero-shot Learning
DeepFLASH: An Efficient Network for Learning-Based Medical Image Registration
by: 藤中彩乃
DeepFLASH 位置合わせ Learning-based image registration 帯域制限 高速化
Part-Aware Context Network for Human Parsing
by: Hirokatsu Kataoka
Human Pose Estimation
Visual-Semantic Matching by Exploring High-Order Attention and Distraction
by: Yue Qiu
Visual-Semantic Matching Image Retrieval Text Retrieval Scene Graph
RL-CycleGAN: Reinforcement Learning Aware Simulation-to-Real
by: fnakamura
reinforcement leanring sim2real image-to-image translation CycleGAN
RankMI: A Mutual Information Maximizing Ranking Loss
by: Shuhei M Yoshida
image retrieval mutual information deep metric learning
Self-Trained Deep Ordinal Regression for End-to-End Video Anomaly Detection
by: 岡本大和
anomaly detection deep ordinal regression human-in-the-loop machine learning anomaly explanation self-training unsupervised representation learning abnormal activity detection video learning
A Programmatic and Semantic Approach to Explaining and Debugging Neural Network Based Object Detectors
by: 岡本大和
population-level explanation testing perception neural network blackbox scenario object detection machine learning autonomous driving
Future Video Synthesis With Object Motion Prediction
by: Yukitaka Tsuchiya
Video Synthesis Spatial Transformer GAN Inpainting
On Positive-Unlabeled Classification in GAN
by: 綱島 秀樹
GAN Unconditional Generation
Regularization on Spatio-Temporally Smoothed Feature for Action Recognition
by: 若宮天雅
Action Recognition
Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics
by: 岡本大和
self-supervised representation learning inpainting unsupervised feature learning self-supervision transformations image statistics
SampleNet: Differentiable Point Cloud Sampling
by: Naoya Chiba
Point Cloud Sampling Point Cloud Classification 3D Registration Point Cloud Reconstruction
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis
by: a2kiti
Pose Estimation single image
Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient Situations
by: Asato Matsumoto
semi-supervised learning domain adaptation open domain recognition
Neural Point Cloud Rendering via Multi-Plane Projection
by: Naoya Chiba
Point Cloud Rendering Multi Plane Rendering
Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild
by: a2kiti
pose estimation
Boosting the Transferability of Adversarial Samples via Attention
by: 山縣英介
AEs transfer blackbox
Learning to Have an Ear for Face Super-Resolution
by: Teppei Kurita
Super Resolution Multi Modal Audio Style GAN
Explaining Knowledge Distillation by Quantifying the Knowledge
by: Shuhei M Yoshida
knowledge distillation visual concepts
Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles
by: Tomoki Tanimura
Adversarial Examples Adversarial Attack Camouflage Real World Style Transfer
Distortion Agnostic Deep Watermarking
by: Tomoki Tanimura
Watermarking Robustness Adversarial Training Noise Encoding
Deep 3D Portrait From a Single Image
by: Yukitaka Tsuchiya
3D face manipulation GAN
Universal Weighting Metric Learning for Cross-Modal Matching
by: Keita Goto
cross modal triplet loss
FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation
by: 中村 優太
meta learning motion estimation MRI cardiac MRI optical flow
Weakly Supervised Discriminative Feature Learning With State Information for Person Identification
by: Masanori YANO
Weakly Supervised Learning Unsupervised Learning Person Re-Identification Recognition
Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence
by: yamada ryosuke
MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model
by: Yue Qiu
Cross-Modal Retrieval Vision and Language
Context-Aware Attention Network for Image-Text Retrieval
by: Yue Qiu
Image-Text Retrieval
4D Visualization of Dynamic Events From Unconstrained Multi-View Videos
by: Yukitaka Tsuchiya
4D visualization video manipulation
IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval
by: Yue Qiu
Image-Text Retrieval Vision and Language
Gated Channel Transformation for Visual Recognition
by: Anonymous
visual recognition
Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
by: Hiroaki Aizawa
Implicit Function
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting
by: Yukitaka Tsuchiya
Motion Retargeting Disentanglement Pose GAN
Active Vision for Early Recognition of Human Actions
by: Mariko Nakano
Action Recognition
Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
by: Shoma Iwai
image-to-image GAN style transfer
Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
by: Anonymous
semantic segmentation graph convolution graph reasoning
Dynamic Neural Relational Inference
by: Takehiko Ohkawa
Neural Contours: Learning to Draw Lines From 3D Shapes
by: yasud
draw line 3D
Can We Learn Heuristics for Graphical Model Inference Using Reinforcement Learning?
by: Takehiko Ohkawa
Semantic Segmentation Reinforcement Learning
SaccadeNet: A Fast and Accurate Object Detector
by: Ryosuke Araki
ObjectDetection
Depth Sensing Beyond LiDAR Range
by: Shoji Sonoyama
depth estimation
Cross-Modal Cross-Domain Moment Alignment Network for Person Search
by: 若宮天雅
person search
iTAML: An Incremental Task-Agnostic Meta-learning Approach
by: Shuhei M Yoshida
incremental learning class-incremental learning meta learning
Search to Distill: Pearls Are Everywhere but Not the Eyes
by: Takehiko Ohkawa
Knowledge Distillation Neural Architecture Search
CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection
by: Ryosuke Araki
ObjectDetection
FReeNet: Multi-Identity Face Reenactment
by: yamada ryosuke
face reenactment
Look-Into-Object: Self-Supervised Structure Modeling for Object Recognition
by: Hiroaki Aizawa
A Semi-Supervised Assessor of Neural Architectures
by: 山縣英介
NAS semi-supervised auto-encoder
Domain Balancing: Face Recognition on Long-Tailed Domains
by: yamada ryosuke
face recognition fairness
Retina-Like Visual Image Reconstruction via Spiking Neural Model
by: Teppei Kurita
Spike Camera Retina
ScopeFlow: Dynamic Scene Scoping for Optical Flow
by: Hiroki Ohashi
optical flow learning process augmentation
Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective
by: Tomoki Tanimura
Representation Learning Imbalance Dataset Augmentation Person ReIdentification Face Recognition
A Hierarchical Graph Network for 3D Object Detection on Point Clouds
by: 寺田英雄
point cloud 3d object detection hgnet graph network graph convolution pyramidal model
Local-Global Video-Text Interactions for Temporal Grounding
by: Shintaro Yamamoto
Temporal Grounding Vision and Language
Exploring Unlabeled Faces for Novel Attribute Discovery
by: Shoma Iwai
Towards Visually Explaining Variational Autoencoders
by: 古澤嘉久
ExplainableAI 生成モデル 異常検知
A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension
by: Yue Qiu
Referring Expression Vision and Language
On Vocabulary Reliance in Scene Text Recognition
by: Yue Qiu
Scene Text Recognition
ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection
by: Yue Qiu
Scene Text Recognition
STEFANN: Scene Text Editor Using Font Adaptive Neural Network
by: Yue Qiu
Scene Text Editing
Semantic Drift Compensation for Class-Incremental Learning
by: 綱島 秀樹
Incremental Learning Class-IL Semantic Drift
Optical Flow in the Dark
by: Komiki Maruyama
Optical Flow Optical Flow Estimation
Video Panoptic Segmentation
by: Komiki Maruyama
Video Panoptic Segmentation Panoptic Segmentation
On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location
by: 榎本
CNN
FeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation
by: 榎本
optical-flow interpolation
Training a Steerable CNN for Guidewire Detection
by: 榎本
medical detection
Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks
by: 榎本
segmentation semi-supervised
Learning to Simulate Dynamic Environments With GameGAN
by: Shunsuke Nakatsuka
GANs Generative Models Reinforcement Learning
Benchmarking the Robustness of Semantic Segmentation Models
by: Hayata Ebisawa
segmantation robustness autonomous
Making Better Mistakes: Leveraging Class Hierarchies With Deep Networks
by: Shuhei M Yoshida
multi-class classification class hierarchy
RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild
by: Masanori YANO
Localization Object Detection
BSP-Net: Generating Compact Meshes via Binary Space Partitioning
by: Shoji Sonoyama
3d reconstruction segmentation single view 3d reconstruction
Height and Uprightness Invariance for 3D Prediction From a Single View
by: Hiroaki Aizawa
Local Deep Implicit Functions for 3D Shape
by: yusuke saito
Deep Implicit Functions 3D shape representation
GhostNet: More Features From Cheap Operations
by: Teppei Kurita
Convolution Ghost Net Redundancy Feature Map
Hierarchically Robust Representation Learning
by: Shuhei M Yoshida
robust optimization representation learning
Learning in the Frequency Domain
by: Tomoki Tanimura
Frequency DCT Image Classification Instance Segmentation Feature Selection
Learning User Representations for Open Vocabulary Image Hashtag Prediction
by: Shintaro Yamamoto
Image Recognition
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
by: Yue Qiu
Scene Text Recognition Encoder-Decoder Framework
Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
by: Yue Qiu
Scene Text Generation Data Augmentation Scene Text Recognition
SCATTER: Selective Context Attentional Scene Text Recognizer
by: Shintaro Yamamoto
Scene Text Recognition
Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning
by: Yue Qiu
Shredded Text Reconstruction Metric Learning
Modeling the Background for Incremental Learning in Semantic Segmentation
by: 綱島 秀樹
Semantic Segmentation Incremental Learning
Interactive Image Segmentation With First Click Attention
by: Shintaro Yamamoto
Segmentation
OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
by: Yue Qiu
Text Recognition Full Page Text Recognition
Towards Transferable Targeted Attack
by: Keita Goto
adversarial attack triplet loss
Multi-Modal Domain Adaptation for Fine-Grained Action Recognition
by: Yasuhiko Tajiri
action recognition
PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
by: Naoya Chiba
LiDAR Point Cloud Point Cloud Segmentation
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
by: Naoya Chiba
Point Cloud Semantic Segmentation Point Cloud Sampling
CARP: Compression Through Adaptive Recursive Partitioning for Multi-Dimensional Images
by: Ryota Suzuki
image compression video compression pixel partitioning Bayesian model
Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
by: Shunsuke Nakatsuka
Weakly Supervised CAM Semantic Segmentation
The Edge of Depth: Explicit Constraints Between Segmentation and Depth
by: Ryota Suzuki
depth estimation self-supervised semantic segmentation
Deformation-Aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
by: hiroki tsujimoto
pose estimation GAN style transfer
Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
by: Ryota Suzuki
lip reading personal dataset
Old Is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm
by: Shunsuke Nakatsuka
Anomaly Detection Generative Models
Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without Correspondences
by: Naoya Chiba
Point Cloud Registration PointNetLK Feature Learning
Screencast Tutorial Video Understanding
by: 若宮天雅
video recognition video caption
PointGMM: A Neural GMM Network for Point Clouds
by: Naoya Chiba
hierarchical Gaussian Mixture Model (hGMM) Point Cloud Registration Point Cloud Generation
Symmetry and Group in Attribute-Object Compositions
by: Anonymous
Combining Detection and Tracking for Human Pose Estimation in Videos
by: Masanori YANO
3D CNN Pose Estimation Tracking Object Detection
Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives
by: Anonymous
Optimization
DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
by: Asato Matsumoto
knowledge transferability representation task similarity
Learning Video Stabilization Using Optical Flow
by: 遠藤大河
Optical Flow Motion and Tracking
Frequency Domain Compact 3D Convolutional Neural Networks
by: Teppei Kurita
DCT Frequency Domain 3D Convolution
Learning to Cartoonize Using White-Box Cartoon Representations
by: Yukitaka Tsuchiya
GAN Cartoon white-box
Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
by: Tomoki Tanimura
Metric Learning Embedding Space Data Augmentation Embedding Expansion
Single Image Reflection Removal With Physically-Based Training Images
by: Anonymous
Reflection removal Physically-Based training dataset
Exploring Self-Attention for Image Recognition
by: 日坂　幸次
Spatio-Temporal Graph for Video Captioning With Knowledge Distillation
by: Katsuyuki Nakamura
video captioning object interaction knowledge distillation
A Local-to-Global Approach to Multi-Modal Movie Scene Segmentation
by: 日坂　幸次
ARShadowGAN: Shadow Generative Adversarial Network for Augmented Reality in Single Light Scenes
by: Yukitaka Tsuchiya
AR Shadow GAN
Detailed 2D-3D Joint Representation for Human-Object Interaction
by: 日坂　幸次
Human-Object Interaction
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
by: fnakamura
3D hand pose estimation 3D mesh reconstruction
Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather
by: 福沢栄治
自動運転、悪天候、データセット、マルチセンサーの融合
Semi-Supervised Learning for Few-Shot Image-to-Image Translation
by: kiyo
Image-to-Image Translation semi-supervised learning
Detection in Crowded Scenes: One Proposal, Multiple Predictions
by: 福沢栄治
人物検出、混雑したシーン
LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks
by: 日坂　幸次
LG-GAN
Solving Mixed-Modal Jigsaw Puzzle for Fine-Grained Sketch-Based Image Retrieval
by: 日坂　幸次
FG-SBIR
Rethinking Computer-Aided Tuberculosis Diagnosis
by: Anonymous
CTD TB TBX11K Faster R-CNN
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
by: 日坂　幸次
DispR-CNN
Gum-Net: Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging
by: Issei Tomotsuka
Cyro-EM tomography alignment
Learning Geocentric Object Pose in Oblique Monocular Images
by: Katsuyuki Nakamura
geocentric pose depth estimation rectification
G3AN: Disentangling Appearance and Motion for Video Generation
by: Rei Tamaru
Generative Adversarial Learning Disentangled Representations
Hyperbolic Image Embeddings
by: 古川 遼
hyperbolic space image embedding few-shot classification person re-identification
HRank: Filter Pruning Using High-Rank Feature Map
by: Asato Matsumoto
pruning feature map rank
Learning Generative Models of Shape Handles
by: Hiroaki Aizawa
Hyperbolic Visual Embedding Learning for Zero-Shot Recognition
by: Shuhei M Yoshida
zero-shot learning Poincare embedding
Fast Sparse ConvNets
by: Masanori YANO
Sparsity Kernel
Learning to Segment 3D Point Clouds in 2D Image Space
by: Naoya Chiba
Point Cloud Semantic Segmentation Kamada-Kawai Algorithm
Can Deep Learning Recognize Subtle Human Activities?
by: Katsuyuki Nakamura
deep learning activity recognition human performance
X-Linear Attention Networks for Image Captioning
by: Seitaro Shinagawa
image-captioning bilinear pooling attention
Filter Grafting for Deep Neural Networks
by: 遠藤大河
Deep Neural Networks DNN Filter Grafting
UniPose: Unified Human Pose Estimation in Single Images and Videos
by: a2kiti
Pose Estimation Atrous Convolution
Putting Visual Object Recognition in Context
by: Seitaro Shinagawa
image-recognition
Bodies at Rest: 3D Human Pose and Shape Estimation From a Pressure Image Using Synthetic Data
by: a2kiti
pose estimation pressure image
EmotiCon: Context-Aware Multimodal Emotion Recognition Using Frege's Principle
by: Seitaro Shinagawa
emotion recognition multi-modal
Context-Aware Group Captioning via Self-Attention and Contrastive Features
by: Seitaro Shinagawa
group-captioning image-captioning multi-source
High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
by: 古澤嘉久
adversarial-training explainableAI
MemNAS: Memory-Efficient Neural Architecture Search With Grow-Trim Learning
by: 山縣英介
NAS memory
Equalization Loss for Long-Tailed Object Recognition
by: Hiroki Ohashi
loss function instance segmentation object detection image classification
Detail-recovery Image Deraining via Context Aggregation Networks
by: Seitaro Shinagawa
deraining image-inpainting
Defending Against Universal Attacks Through Selective Feature Regeneration
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial examples robustness universal perturbation
Universal Physical Camouflage Attacks on Object Detectors
by: 山縣英介
AEs physical
Instance Shadow Detection
by: Teppei Kurita
Shadow Detection Cast Shadow Object Detection Instance Segmentation Light Estimation
FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation
by: Higaki Yoshinari
video denoising multiscale
Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation
by: 藤中彩乃
非可逆画像変換 CycleGAN 仮想大腸内視鏡検査 深度推定
MAGSAC++, a Fast, Reliable and Accurate Robust Estimator
by: Higaki Yoshinari
robust estimator RANSAC fundamental matrix homography
Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging
by: Higaki Yoshinari
event camera super resolution denoising
Dense Regression Network for Video Grounding
by: Yue Qiu
Video Grounding
MAST: A Memory-Augmented Self-Supervised Tracker
by: pacifinapacific
Tracking self supervised
Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition
by: Ryota Suzuki
latent space auxiliary task facial expression recognition
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
by: Keita Goto
person re-identification cross modal infrared image
Syntax-Aware Action Targeting for Video Captioning
by: Yue Qiu
Video Captioning
Siamese Box Adaptive Network for Visual Tracking
by: pacifinapacific
VOT Tracking
Learning When and Where to Zoom With Deep Reinforcement Learning
by: Narifumi Otoeb
PatchDrop
Object Relational Graph With Teacher-Recommended Learning for Video Captioning
by: Yue Qiu
Video Captioning External Language Model
Large Scale Video Representation Learning via Relational Graph Clustering
by: Seito Kasai
representation learning retrieval search recommendation clustering
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
by: Yue Qiu
RGB-D Scene Completion Self-Supervised 3D Vision
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
by: 福沢　栄治
単眼カメラ、三次元物体検出、KITTI
Pose-Guided Visible Part Matching for Occluded Person ReID
by: 福沢　栄治
隠れた人、同一人物判定、姿勢
There and Back Again: Revisiting Backpropagation Saliency Methods
by: 古澤嘉久
ExplainableAI Grad-CAM Saliency-Method
Robust Superpixel-Guided Attentional Adversarial Attack
by: Keita Goto
adversarial attack class activation mapping
When to Use Convolutional Neural Networks for Inverse Problems
by: 山縣英介
CSC CNN
Adaptive Hierarchical Down-Sampling for Point Cloud Classification
by: Naoya Chiba
Point Cloud Downsampling Point Cloud Classification
SCOUT: Self-Aware Discriminant Counterfactual Explanations
by: Seitaro Shinagawa
explanation counterfactual visual explanation
AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization
by: 福沢　栄治
UAV、自動追跡、視覚追跡
Towards Universal Representation Learning for Deep Face Recognition
by: 山縣英介
face recognition universal model
From Depth What Can You See? Depth Completion via Auxiliary Image Reconstruction
by: 福沢栄治
深度補完、補助画像再構成、KITTI
Bidirectional Graph Reasoning Network for Panoptic Segmentation
by: Anonymous
semantic segmentation instance segmentation panoptic segmentation
Face X-Ray for More General Face Forgery Detection
by: 榎本
deepfake
Just Go With the Flow: Self-Supervised Scene Flow Estimation
by: 福沢　栄治
シーンフロー推定、教師無し学習、自己監視損失
Boundary-Aware 3D Building Reconstruction From a Single Overhead Image
by: 寺田英雄
multi-task multi-feature 3d building modeling fpn mask r-cnn bpsh
Noisier2Noise: Learning to Denoise From Unpaired Noisy Data
by: 福沢栄治
画像ノイズ、除去、ニューラルネットワーク
Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View With a Reachability Prior
by: Katsuyuki Nakamura
Reachability prior
What's Hidden in a Randomly Weighted Neural Network?
by: Shuhei M Yoshida
random neural networks lottery ticket hypothesis
Self-Training With Noisy Student Improves ImageNet Classification
by: Anonymous
self-training semi-supervised learning ImageNet
Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous Driving
by: 福沢栄治
データ集約、自動運転、ポリシー学習
Predicting Semantic Map Representations From Images Using Pyramid Occupancy Networks
by: 福沢栄治
自律運転、セマンティックマップ、単眼カメラ
Noise-Aware Fully Webly Supervised Object Detection
by: 福沢栄治
物体検出、Web画像、ノイズ画像
Sub-Frame Appearance and 6D Pose Estimation of Fast Moving Objects
by: 遠藤大河
Motion and Tracking
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets
by: Masanori YANO
Recognition Image Classification Kernel
Deep Unfolding Network for Image Super-Resolution
by: So Uchida
Supre-Resolution
Deep Degradation Prior for Low-Quality Image Classification
by: Anonymous
Image Classification
Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
by: Naoya Chiba
Object Detection LiDAR Point Cloud
TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style
by: hirotaka hiraki
clothing 3d deformation pose shape garment style
Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer
by: Anonymous
Domain Adaptation Semantic Segmentation
4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video Cameras
by: yusuke saito
Multi-view Multi-person Realtime Motion Capture 4D Association Graph
AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces
by: Anonymous
face analysis face detection fine-grained animal dataset
Cascaded Human-Object Interaction Recognition
by: Seitaro Shinagawa
image recognition human-object interaction recognition
Attention-Based Context Aware Reasoning for Situation Recognition
by: Seitaro Shinagawa
situation recognition
Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
by: kiyo
Multi-modal Image Registration Generative Adversarial Models Unsupervised Learning
OASIS: A Large-Scale Dataset for Single Image 3D in the Wild
by: Anonymous
single-view 3D dataset annotation crowdsourcing depth estimation
A Morphable Face Albedo Model
by: hirotaka hiraki
photometric albedo 3d morphable model
Interpretable and Accurate Fine-grained Recognition via Region Grouping
by: Hirokatsu Kataoka
Fine-grained Recognition Interpretability Explainability
Reflection Scene Separation From a Single Image
by: Teppei Kurita
Reflection Enhancement Reflection Removal Reflection Separation
Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global Context
by: Yue Qiu
Video visual relation detection Sliding Window Graph CN
PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimation
by: Anonymous
Pose Estimation 6D
Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels
by: Naoya Chiba
Point Cloud Segmentation Weakly Supervised Learning
Learning Representations by Predicting Bags of Visual Words
by: Tomoki Tanimura
Self-Supservised Learning Bag of Visual Words Classification Detection
Scalability in Perception for Autonomous Driving: Waymo Open Dataset
by: Anonymous
autonomous driving dataset LiDAR multi-modal
NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing
by: Masanori YANO
Object Detection
Bi-Directional Relationship Inferring Network for Referring Image Segmentation
by: Anonymous
referring segmentation language attention
Domain Adaptation for Image Dehazing
by: Hao
image dehazing domain adaptation
DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
by: Hao
face forgery detection dataset
Going Deeper With Lean Point Networks
by: Hirokatsu Kataoka
Point Cloud Segmentation
Cars Can't Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention Networks
by: Hirokatsu Kataoka
Semantic Segmentation
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
by: Hao
DeepFake dataset
Anisotropic Convolutional Networks for 3D Semantic Scene Completion
by: Yue Qiu
Semantic Scene Completion 3D CNNs 3D Vision
Time Flies: Animating a Still Image With Time-Lapse Video As Reference
by: Hao
time lapse style transfer
High-Dimensional Convolutional Networks for Geometric Pattern Recognition
by: 中村真裕
convnets
StarGAN v2: Diverse Image Synthesis for Multiple Domains
by: Hao
image-image transfer
Designing Network Design Spaces
by: Hirokatsu Kataoka
EfficientNet AutoML NAS
ViBE: Dressing for Diverse Body Shapes
by: Hao
body dressing fashion
Select, Supplement and Focus for RGB-D Saliency Detection
by: Yue Qiu
RGB-D Saliency Detection
MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation
by: Anonymous
dataset MSeg multi-domain semantic segmentation
Diverse Image Generation via Self-Conditioned GANs
by: Hao
GAN mode collapse Self-Conditioned
Discovering Human Interactions With Novel Objects via Zero-Shot Learning
by: 福沢栄治
ゼロショット、人間との相互作用、物体認識
Train in Germany, Test in the USA: Making 3D Object Detectors Generalize
by: 福沢栄治
三次元物体認識、自動運転、データセット
PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection
by: Wataru Kudo
Action recognition
DoveNet: Deep Image Harmonization via Domain Verification
by: Yukitaka Tsuchiya
image harmonization U-Net dataset
Learning Multi-View Camera Relocalization With Graph Neural Networks
by: 福沢栄治
グラフニューラルネットワーク、カメラの絶対ポーズの推定、自動運転
Learning Situational Driving
by: 裏優斗
Autonomous Driving imitation learning
STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction
by: 福沢栄治
歩行者追跡、時空間交互ネットワーク、３次元点群
Memory Enhanced Global-Local Aggregation for Video Object Detection
by: Hiroki Ohashi
video object detection object detection video
Generalized Product Quantization Network for Semi-Supervised Image Retrieval
by: Anonymous
GPQ semi supervised image retrieval
Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-Identification
by: Hirokatsu Kataoka
Person Re-ID
Adaptive Loss-Aware Quantization for Multi-Bit Networks
by: Kiro Otsu
Network Compression Quantization multi-bit networks
Deep Polarization Cues for Transparent Object Segmentation
by: Masaki Taniguchi
transparent instance segmentation polarization
How Much Time Do You Have? Modeling Multi-Duration Saliency
by: 榎本
Scene Analysis
Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction
by: Shun.ishizaka
pose 3D skeleton human motion prediction multi-scale graph
Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
by: Naoya Chiba
Point Cloud Segmentation Point Cloud Convolution
Searching for Actions on the Hyperbole
by: Shun.ishizaka
video retrieval hierarchical action
Scene Recomposition by Learning-Based ICP
by: Shoji Sonoyama
reinforced learning scene recomposition pose estimation semantic segmentation
Don't Even Look Once: Synthesizing Features for Zero-Shot Detection
by: 福沢栄治
ゼロショット検出、物体検出、目に見えないオブジェクト
Open Compound Domain Adaptation
by: 岡本大和
domain adaptation compound domains open world curriculum learning visual memory
Deep Iterative Surface Normal Estimation
by: Ryosuke Araki
Surface Normal Estimation
Real-World Person Re-Identification via Degradation Invariance Learning
by: Masanori YANO
Person Re-Identification Self-Supervised Learning Disentangled Representation GAN
Bi3D: Stereo Depth Estimation via Binary Classifications
by: Shoji Sonoyama
depth estimation segmentation stereo depth estimation
MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
by: Anonymous
3D Object Detection
PnPNet: End-to-End Perception and Prediction With Tracking in the Loop
by: Anonymous
Autonomous driving object detection tracking motion prediction lidar nuScenes
Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity Volume
by: Shoji Sonoyama
monocular depth estimation depth estimation self attention self supervised learning
On the Detection of Digital Face Manipulation
by: Yukitaka Tsuchiya
deep fake detection dataset attention map
Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning
by: Ryosuke Araki
Classification Gaussian Mixture Model Weakly Supervised Fine-grained Image Recognition
Modeling Biological Immunity to Adversarial Examples
by: kiyo
Adversarial Examples Sparse Coding
Prime Sample Attention in Object Detection
by: Anonymous
object detection prime sampling
Towards Accurate Scene Text Recognition With Semantic Reasoning Networks
by: Seitaro Shinagawa
scene text recognition reasoning
Composed Query Image Retrieval Using Locally Bounded Features
by: Anonymous
composed query image retrieval
Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision
by: Asato Matsumoto
active learning pseudo label fisher kernel Kullback–Leibler
Solving Jigsaw Puzzles With Eroded Boundaries
by: Teppei Kurita
Inpainiting GAN Jigsaw Pazzles
Interactive Object Segmentation With Inside-Outside Guidance
by: Anonymous
Interactive Object Segmentation
Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training
by: Hiroki Ohashi
deblur optical flow deformable convolution dilated convolution
FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions
by: Tomoki Tanimura
Privacy Privacy Preserving Fourier Transform
MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation
by: Ryota Suzuki
pose estimation multiple camera fusion meta learning
KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human Annotations
by: Ryota Suzuki
3D keypoint dataset keypoints aggregation
Continual Learning With Extended Kronecker-Factored Approximate Curvature
by: Asato Matsumoto
K-FAC Continual Learning natural gradient learning
Label Decoupling Framework for Salient Object Detection
by: Anonymous
salient object detection distance transformation
Towards Robust Image Classification Using Sequential Attention Models
by: Tomoki Tanimura
Adversarial Examples Adversarial Robustness Adversarial Defense Sequential Process Attention Robustness LSTM
Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval
by: yasud
sketch RL 強化学習 Siamese network
PaStaNet: Toward Human Activity Knowledge Engine
by: Kensho Hara
image-based activity recognition human-object interaction
Deep Semantic Clustering by Partition Confidence Maximisation
by: Asato Matsumoto
deep clustering unsupervised
Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors
by: Pavel Savkin
SDF NOCS Differentiable rendering LiDAR annotation curriculum learning
Learning the Redundancy-Free Features for Generalized Zero-Shot Object Recognition
by: Anonymous
Zero-Shot Object Recognition
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
by: Masaki Taniguchi
instance segmentation real-time attention
Data Uncertainty Learning in Face Recognition
by: yamada ryosuke
face recognition
Video Object Grounding Using Semantic Roles in Language Description
by: Shintaro Yamamoto
Video Object Grounding Vision-and-Language
ZSTAD: Zero-Shot Temporal Activity Detection
by: Hiroki Ohashi
zero-shot learning activity detection label embedding word2vec
Style Normalization and Restitution for Generalizable Person Re-Identification
by: Masa
Person Re-Identification Domain Adaption Domain Generalization
Learning Instance Occlusion for Panoptic Segmentation
by: Hirokatsu Kataoka
Panoptic Segmentation Instance Segmentation Semantic Segmentation
RDCFace: Radial Distortion Correction for Face Recognition
by: yamada ryosuke
face recognition
Google Landmarks Dataset v2 - A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
by: Shunsuke Kogure
Dataset Evaluation
Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End
by: Ryota Suzuki
Action Modifiers: Learning From Adverbs in Instructional Videos
by: Wataru Kudo
Weakly Supervised Embedding
BEDSR-Net: A Deep Shadow Removal Network From a Single Document Image
by: Shintaro Yamamoto
Document Recognition
ReDA:Reinforced Differentiable Attribute for 3D Face Reconstruction
by: Daiki Kimura
3D Face Reconstruction
MISC: Multi-Condition Injection and Spatially-Adaptive Compositing for Conditional Person Image Synthesis
by: Yukitaka Tsuchiya
image synthesis gan
Learning From Noisy Anchors for One-Stage Object Detection
by: Hirokatsu Kataoka
Object Detection MSCOCO Noisy Anchor
M2m: Imbalanced Classification via Major-to-Minor Translation
by: Shintaro Yamamoto
Classification Class-Imbalance
Attention Scaling for Crowd Counting
by: Hirokatsu Kataoka
Crowd Counting Density Attention
Intra- and Inter-Action Understanding via Temporal Action Parsing
by: Kensho Hara
Action Understanding Video Dataset Action Parsing
Two-Shot Spatially-Varying BRDF and Shape Estimation
by: yamada ryosuke
BRDF shape estimation
Learning to Dress 3D People in Generative Clothing
by: 中村真裕
3d people
Hypergraph Attention Networks for Multimodal Learning
by: Shintaro Yamamoto
VQA Vision-and-Language
Self-Supervised Monocular Scene Flow Estimation
by: Hirokatsu Kataoka
Scene Flow Depth Image
Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification
by: Hirokatsu Kataoka
Vehicle Re-identification
Correspondence-Free Material Reconstruction using Sparse Surface Constraints
by: Ryota Suzuki
physical material parameter deformable object sparse observation
Analyzing and Improving the Image Quality of StyleGAN
by: 綱島 秀樹
GAN Regularization Latent Space Mapping
Learning to Discriminate Information for Online Action Detection
by: Kensho Hara
Online Action Detection Temporal Action Detection RNN
WaveletStereo: Learning Wavelet Coefficients of Disparity Map in Stereo Matching
by: 若宮天雅
stereo matching
Three-Dimensional Reconstruction of Human Interactions
by: Hirokatsu Kataoka
Monocular 3D Reconstruction Human Interaction
Moving in the Right Direction: A Regularization for Deep Metric Learning
by: Shintaro Yamamoto
Metric Learning
Copy and Paste GAN: Face Hallucination From Shaded Thumbnails
by: Hirokatsu Kataoka
GAN Face Generation
Data-Efficient Semi-Supervised Learning by Reliable Edge Mining
by: Asato Matsumoto
Semi-Supervised Learning graph
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
by: Hiroaki Aizawa
CenterMask: Real-Time Anchor-Free Instance Segmentation
by: Masanori YANO
Instance Segmentation
Deep Homography Estimation for Dynamic Scenes
by: Yukitaka Tsuchiya
homography
CenterMask: Single Shot Instance Segmentation With Point Representation
by: Masanori YANO
Instance Segmentation
RGBD-Dog: Predicting Canine Pose from RGBD Sensors
by: yamada ryosuke
3DSSD: Point-Based 3D Single Stage Object Detector
by: Hirokatsu Kataoka
Point Cloud Object Detection
Variational Context-Deformable ConvNets for Indoor Scene Parsing
by: Seitaro Shinagawa
scene parsing image segmentation depth convolution
VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions
by: Shintaro Yamamoto
Human Object Interaction Graph Convolution
Learning a Unified Sample Weighting Network for Object Detection
by: Ryota Suzuki
object detection sample weighting
Image Demoireing with Learnable Bandpass Filters
by: Teppei Kurita
Demoire Moire Bandpass Filter
Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS
by: Hirokatsu Kataoka
Neural Architecture Search Weight Sharing
Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data
by: Shintaro Yamamoto
Medical Image GAN Privacy
Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision
by: Hiroaki Aizawa
Interactive Multi-Label CNN Learning With Partial Labels
by: Asato Matsumoto
multi-label partial label smoothing
SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
by: Shunsuke Kogure
object detection tracking
Circle Loss: A Unified Perspective of Pair Similarity Optimization
by: Masa
metric learning face recognition fine-grained image retrieval person re-id
An Adaptive Neural Network for Unsupervised Mosaic Consistency Analysis in Image Forensics
by: Ryota Suzuki
mosaic consistency analysis image forensics
Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images
by: yamada ryosuke
multi-view
Progressive Relation Learning for Group Activity Recognition
by: Mariko Nakano
Group Activity Recognition Action Recognition
Meta-Learning of Neural Architectures for Few-Shot Learning
by: Asato Matsumoto
NSA meta-learning few-shot
Assessing Eye Aesthetics for Automatic Multi-Reference Eye In-Painting
by: Ryota Suzuki
inpainting aesthetics
Single-Stage Semantic Segmentation From Image Labels
by: Yuchi Ishikawa
weakly-supervised semantic segmentation
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
by: 野中琢登
Style Transfer Distillation
Disparity-Aware Domain Adaptation in Stereo Image Restoration
by: Anonymous
Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision
by: Anonymous
Unsupervised Domain Adaptation Semantic Segmentation Self-Supervision
Sideways: Depth-Parallel Training of Video Models
by: Kensho Hara
Video Efficient
DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
by: Anonymous
3D Mesh Semantic Segmentation
Clean-Label Backdoor Attacks on Video Recognition Models
by: Kensho Hara
Backdoor Attack Video Recognition Action Recognition
Active 3D Motion Visualization Based on Spatiotemporal Light-Ray Integration
by: Ryota Suzuki
projector light field
Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data
by: fnakamura
3D hand pose estimation 3D mesh reconstruction
Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching
by: Yuchi Ishikawa
optical flow stereo matching self-supervised learning
Multiple Anchor Learning for Visual Object Detection
by: Ryosuke Araki
Object Detection
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
by: Masa
Occluded Person Re-ID
Video Super-Resolution With Temporal Group Attention
by: Yuchi Ishikawa
video super-resolution
PuppeteerGAN: Arbitrary Portrait Animation With Semantic-Aware Appearance Transformation
by: Anonymous
GAN Semantic Segmentation Image to Image
Towards Efficient Model Compression via Learned Global Ranking
by: Shuhei M Yoshida
pruning
Sketch-BERT: Learning Sketch Bidirectional Encoder Representation From Transformers by Self-Supervised Learning of Sketch Gestalt
by: yasud
sketch retrival generation recognition
Towards Unified INT8 Training for Convolutional Neural Network
by: Shuhei M Yoshida
quantization quantized training
Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction
by: Wataru Kudo
SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking
by: MatsuokaHikaru
Multi-Object Tracking ground truth Gaussian mixture model
PointPainting: Sequential Fusion for 3D Object Detection
by: Naoya Chiba
LiDAR Point Cloud 3D Semantic Segmentation
Deep Implicit Volume Compression
by: yusuke saito
3D reconstruction 3D voxel grids truncated signed distance fields compressing
Learning to Forget for Meta-Learning
by: Shuhei M Yoshida
meta learning MAML
Learning a Dynamic Map of Visual Appearance
by: Katsuyuki Nakamura
visual attribute dataset
Domain-Aware Visual Bias Eliminating for Generalized Zero-Shot Learning
by: Asato Matsumoto
zero-shot learning semantic-aligned visual representation
Spherical Space Domain Adaptation With Robust Pseudo-Label Loss
by: Ryo Takahashi
ドメイン適応
Learning to Detect Important People in Unlabelled Images for Semi-Supervised Important People Detection
by: Rei Tamaru
Important People Detection pseudo-label estimation Object Detection
Understanding Road Layout From Videos as a Whole
by: ReiTamaru
3D Reconstruction
Generalized Zero-Shot Learning via Over-Complete Distribution
by: Asato Matsumoto
zero-shot learning CVAE
Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction
by: 日坂　幸次
Human Trajectory Prediction
One-Shot Adversarial Attacks on Visual Tracking With Dual Attention
by: 日坂　幸次
dversarial attack
Correspondence Networks With Adaptive Neighbourhood Consensus
by: 日坂　幸次
visual correspondence
Neural Architecture Search for Lightweight Non-Local Networks
by: 日坂　幸次
Meshlet Priors for 3D Mesh Reconstruction
by: Naoya Chiba
Meshlet Priors Mesh Reconstruction
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
by: 日坂　幸次
FGVC
PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation
by: Ryosuke Araki
Object Pose Estimation
Learning Saliency Propagation for Semi-Supervised Instance Segmentation
by: 日坂　幸次
Instance segmentatio
Memory Aggregation Networks for Efficient Interactive Video Object Segmentation
by: 日坂　幸次
iVOS Segmentation
Cloth in the Wind: A Case Study of Physical Measurement Through Simulation
by: 日坂　幸次
physical Measurement
Single-Step Adversarial Training With Dropout Scheduling
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial training adversarial robustness adversarial examples
From Two Rolling Shutters to One Global Shutter
by: Teppei Kurita
Rolling Shutter Global Shutter CMOS RANSAC
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
by: Masaki Taniguchi
semantic segmentation cascade network high resolution image
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification
by: Masa
Person Re-Identification Dataset
Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction
by: Rei Tamaru
PDE Video Prediction Video Forcasting
Heterogeneous Knowledge Distillation Using Information Flow Modeling
by: Shuhei M Yoshida
knowledge distillation
AvatarMe: Realistically Renderable 3D Facial Reconstruction "In-the-Wild"
by: Naoya Chiba
3D Facial Reconstruction Face Rendering BRDF Estimation
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
by: Ryosuke Araki
3D Object Detection Semi-supervised Learning
Central Similarity Quantization for Efficient Image and Video Retrieval
by: Anonymous
hash CSQ image retrieval
Towards Inheritable Models for Open-Set Domain Adaptation
by: kiyo
Unsupervised Domain Adaptation Domain Adaptation
Spatially Attentive Output Layer for Image Classification
by: Masanori YANO
Recognition Image Classification Attention Distillaion
Polarized Reflection Removal With Perfect Alignment in the Wild
by: Teppei Kurita
Reflection Removal Polarization Sensor Polarization
Warp to the Future: Joint Forecasting of Features and Feature Motion
by: 日坂　幸次
Semantic Segmentation Warp to the Future
Deepstrip: High-Resolution Boundary Refinement
by: 日坂　幸次
h Resolution Boundary
Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification
by: 日坂　幸次
Person Re-Identification
Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection
by: 日坂　幸次
Weakly Supervised Object Detection
Density-Based Clustering for 3D Object Detection in Point Clouds
by: 日坂　幸次
3D Object Detection
Densely Connected Search Space for More Flexible Neural Architecture Search
by: 日坂　幸次
Neural architecture search
Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio
by: 日坂　幸次
Network Adjustmen
Learning Longterm Representations for Person Re-Identification Using Radio Signals
by: 日坂　幸次
Person Re-Identificatio
What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective
by: 日坂　幸次
Global Covariance Pooling
Learning to Measure the Static Friction Coefficient in Cloth Contact
by: 日坂　幸次
Static Friction Coefficient
Fast Template Matching and Update for Video Object Tracking and Segmentation
by: 日坂　幸次
Video Object Tracking and Segmentation
Probabilistic Video Prediction From Noisy Data With a Posterior Confidence
by: 日坂　幸次
Video Prediction
Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation
by: Naoya Chiba
Point Cloud Semantic Segmentation Few Shot Learning
Neuromorphic Camera Guided High Dynamic Range Imaging
by: Teppei Kurita
Neuromorphic Camera DVS FSM HDR High Dynamic Range Sensor Fusion
TetraTSDF: 3D Human Reconstruction From a Single Image With a Tetrahedral Outer Shell
by: Naoya Chiba
3D Human Reconstruction Tetrahedral Volumetric Representation
Graph-Guided Architecture Search for Real-Time Semantic Segmentation
by: 福沢栄治
セマンティックセグメンテーション、軽量化、Cityscapes
All in One Bad Weather Removal Using Architectural Search
by: Anonymous
weather Architectural Search
Norm-Aware Embedding for Efficient Person Search
by: Masanori YANO
Person Search Person Re-Identification Object Detection
An Investigation Into the Stochasticity of Batch Whitening
by: kiyo
Normalization Principal Component Analysis Cholesky Decomposition Zero-phase Component Analysis
Joint Demosaicing and Denoising With Self Guidance
by: Teppei Kurita
JDD Demosaic NR Noise Reduction Bayer
StegaStamp: Invisible Hyperlinks in Physical Photographs
by: Tomoki Tanimura
Watermarking Steganography AR Augmented Reality Robustness
3D Human Mesh Regression With Dense Correspondence
by: Naoya Chiba
Human Mesh Regression Human Pose Estimation
DSGN: Deep Stereo Geometry Network for 3D Object Detection
by: Shoji Sonoyama
object detection depth estimation
TCTS: A Task-Consistent Two-Stage Framework for Person Search
by: Masanori YANO
Person Search Person Re-Identification Object Detection
Polarized Non-Line-of-Sight Imaging
by: Teppei Kurita
NLOS Polarization BRDF Transport Matrix
Learning a Reinforced Agent for Flexible Exposure Bracketing Selection
by: Teppei Kurita
Reinforcement Learning HDR Bracketing
Superpixel Segmentation With Fully Convolutional Networks
by: Anonymous
Superpixel Stereo matching
Robust Design of Deep Neural Networks Against Adversarial Attacks Based on Lyapunov Theory
by: 福原吉博 (Yoshihiro Fukuhara)
adversarial examples adversarial robustness
Learning to Observe: Approximating Human Perceptual Thresholds for Detection of Suprathreshold Image Transformations
by: Hiroaki Aizawa
KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
by: Naoya Chiba
Transparent Object Detection 3D Pose Estimation Passive Stereo
GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping
by: 福原吉博 (Yoshihiro Fukuhara)
dataset grasping grasp pose prediction
Improving the Robustness of Capsule Networks to Image Affine Transformations
by: 綱島 秀樹
CapsNet Affine Transformation Routing
PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
by: 福原吉博 (Yoshihiro Fukuhara)
unsupervised learning action recognition
Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection
by: Ryo Takahashi
GP-NAS: Gaussian Process Based Neural Architecture Search
by: Obi
NAS neural architecture search Gaussian Process
Bi-Directional Interaction Network for Person Search
by: Masanori YANO
Person Search Person Re-Identification Object Detection Siamese Network
Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data
by: a2kiti
pose estimation data augmentation
BANet: Bidirectional Aggregation Network With Occlusion Handling for Panoptic Segmentation
by: 古川 遼
panoptic segmentation occlusion handling
Perceptual Quality Assessment of Smartphone Photography
by: Teppei Kurita
Perceptual Quality Dataset
Learning Invariant Representation for Unsupervised Image Restoration
by: fnakamura
cross domain transfer image restoration disentangling representation
Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction
by: Rei Tamaru
Video Prediction Human Vision System Discrete Wavelet Transform
Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer
by: Ryota Suzuki
style transfer metric learning graph convolution
Neural Cages for Detail-Preserving 3D Deformations
by: Naoya Chiba
Deformation Transfer Cage-based Deformation
Robust Partial Matching for Person Search in the Wild
by: Masanori YANO
Person Search Person Re-Identification Object Detection Dataset
CRNet: Cross-Reference Networks for Few-Shot Segmentation
by: Hiroki.Yamamoto
FewShot Segmentation
Multi-Scale Progressive Fusion Network for Single Image Deraining
by: Hiroki.Yamamoto
Deraining Segmentation
A Lighting-Invariant Point Processor for Shading
by: Hirokatsu Kataoka
Shading Geometry Depth
Projection & Probability-Driven Black-Box Attack
by: Hirokatsu Kataoka
Adversarial Examples
Adaptive Interaction Modeling via Graph Operations Search
by: Hirokatsu Kataoka
Graph Convolution Graph Operation Neural Architecture Search
Ensemble Generative Cleaning With Feedback Loops for Defending Adversarial Attacks
by: Hirokatsu Kataoka
Defense Adversarial Attack
In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks
by: Hirokatsu Kataoka
2D Landmark 3D Shape Reconstruction
Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image
by: Teppei Kurita
Self-Supervised Learning NR Denoising Dropout
Recursive Social Behavior Graph for Trajectory Prediction
by: Hirokatsu Kataoka
Social Interaction Graph Convolutional Network
Lightweight Photometric Stereo for Facial Details Recovery
by: Hirokatsu Kataoka
CNN Photometric Stereo
Bi-Directional Relationship Inferring Network for Referring Image Segmentation
by: Anonymous
referring segmentation language attention
StructEdit: Learning Structural Shape Variations
by: Hirokatsu Kataoka
3D Model 3D Shape
Harmonizing Transferability and Discriminability for Adapting Object Detectors
by: Hirokatsu Kataoka
コードはこちらで公開: https://github.com/chaoqichen/HTCN
Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching
by: Hirokatsu Kataoka
Video Segmentation DAVIS dataset
Correlating Edge, Pose With Parsing
by: Hirokatsu Kataoka
Human Parsing Human Pose Estimation
VecRoad: Point-Based Iterative Graph Exploration for Road Graphs Extraction
by: Hirokatsu Kataoka
Road Graph Extraction Road Segmentation
3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation
by: Hirokatsu Kataoka
3D Point Cloud 3D Instance Segmentation
EcoNAS: Finding Proxies for Economical Neural Architecture Search
by: Hirokatsu Kataoka
NAS
Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
by: Naoya Chiba
3D Object Tracking Stereo Trajectory Tracking
Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification
by: Masanori YANO
Unsupervised Learning Person Re-Identification
MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
by: Hiroki.Yamamoto
GAN
Normal Assisted Stereo Depth Estimation
by: Teppei Kurita
Surface Normal Depth Multi-View Cost Volume 3D CNN
Deep Non-Line-of-Sight Reconstruction
by: Naoya Chiba
Non-Line-of-Sight 3D Repnstrgion NLoS Depth Measurement
Context-Aware Human Motion Prediction
by: hirotaka hiraki
Motion Prediction Context Awareness Context RNN Graph Attention Network Edge Convolution
Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features
by: kiyo
Semi-Supervised Laerning Disentangled Representation Learning gait recognition
Visually Imbalanced Stereo Matching
by: Teppei Kurita
Stereo Depth Imbalanced
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
by: Hirokatsu Kataoka
Object Detection NAS
Geometrically Principled Connections in Graph Neural Networks
by: Hirokatsu Kataoka
Graph Convolution GCN Geometry
Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation
by: Hirokatsu Kataoka
Unsupervised Domain Adaptation Cityscapes SYNTHIA GTA5
Robust Object Detection Under Occlusion With Context-Aware CompositionalNets
by: Hirokatsu Kataoka
Object Detection Occlusion Context
Resolution Adaptive Networks for Efficient Inference
by: Masanori YANO
Recognition Image Classification
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning
by: Naoya Chiba
Multi Object Tracking Graph Neural Networks
Self-Supervised Human Depth Estimation From Monocular Videos
by: 福沢　栄治
深度推定、単眼カメラ、3D非剛体運動
VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines
by: 福沢　栄治
消失点の推定、マンハッタン線マップ、RGB画像
MEBOW: Monocular Estimation of Body Orientation in the Wild
by: 福沢　栄治
３次元姿勢推定、データセット、COCO-MEBOW
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
by: 福沢　栄治
超解像度、時空間情報、ビデオフレーム補間
FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
by: 福沢　栄治
3D顔データセット、3D顔モデル、単一画像
Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification
by: 福沢　栄治
同一人物判定、時空間情報、グラフ畳み込みネットワーク
Online Depth Learning Against Forgetting in Monocular Videos
by: 福沢　栄治
オンライン深度学習、忘却学習、単眼ビデオ
Relation-Aware Global Attention for Person Re-Identification
by: 福沢　栄治
同一人物判定、注目機制、グローバル構造情報、相関
Deep Metric Learning via Adaptive Learnable Assessment
by: 福沢　栄治
ディープメトリックラーニング、適応学習可能評価、エピソードに基づくトレーニング
Exemplar Normalization for Learning Deep Representation
by: Hirokatsu Kataoka
Exemplar Normalization Image Recognition
Imitative Non-Autoregressive Modeling for Trajectory Forecasting and Imputation
by: Hirokatsu Kataoka
Trajectory Forecasting VAE
Sparse Layered Graphs for Multi-Object Segmentation
by: Hirokatsu Kataoka
Segmentation Ishikawa Layered Technique
End-to-End 3D Point Cloud Instance Segmentation Without Detection
by: Hirokatsu Kataoka
3D Point Cloud Instance Segmentation
Exploring Bottom-Up and Top-Down Cues With Attentive Learning for Webly Supervised Object Detection
by: Hirokatsu Kataoka
Webly Supervision Object Detection
IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving
by: Hirokatsu Kataoka
Stereo Vision 3D Object Detection
Learning to Restore Low-Light Images via Decomposition-and-Enhancement
by: Teppei Kurita
Low-Light Frequency Decomposition
EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera
by: a2kiti
pose estimation; event camera
Structure Aware Single-Stage 3D Object Detection From Point Cloud
by: Anonymous
3D object detection
OccuSeg: Occupancy-Aware 3D Instance Segmentation
by: Naoya Chiba
3D Instance Segmentation Spatial Segmentaiton
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification
by: Masanori YANO
Transfer Learning Person Re-Identification Domain Adaptation
Neural Head Reenactment with Latent Pose Descriptors
by: Anonymous
Deep Shutter Unrolling Network
by: Teppei Kurita
Rolling Shutter Global Shutter
Object-Occluded Human Shape and Pose Estimation From a Single Color Image
by: a2kiti
pose estimation shape estimation
PolarMask: Single Shot Instance Segmentation With Polar Representation
by: Masanori YANO
Instance Segmentation
Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation
by: Naoya Chiba
Non-Line-Of-Sight Human Pose Estimation
Epipolar Transformers
by: Shoji Sonoyama
pose estimation keypoint detection
DeepLPF: Deep Local Parametric Filters for Image Enhancement
by: Teppei Kurita
Local Parametric Filter Image Enhancement
Explainable Object-Induced Action Decision for Autonomous Vehicles
by: Ryo Takahashi
Salience-Guided Cascaded Suppression Network for Person Re-Identification
by: Masanori YANO
Person Re-Identification Attention
Learning Fast and Robust Target Models for Video Object Segmentation
by: Yukitaka Tsuchiya
VOS segmentation
Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data
by: Masanori YANO
Recognition Image Classification
Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose Reconstruction
by: a2kiti
pose estimaiton
Revisiting the Sibling Head in Object Detector
by: Hirokatsu Kataoka
Object Detection Sibling Head
Visual Reaction: Learning to Play Catch With Your Drone
by: Hirokatsu Kataoka
Visual Reactino Drone
Assessing Image Quality Issues for Real-World Problems
by: Teppei Kurita
Image Quality Assessment Blind
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
by: Hirokatsu Kataoka
MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning
by: Hirokatsu Kataoka
NAS Multi-task Learning
Learning to Segment the Tail
by: Hirokatsu Kataoka
Instance Segmentation LVIS dataset Few-show Learning
CoverNet: Multimodal Behavior Prediction Using Trajectory Sets
by: Hirokatsu Kataoka
Trajectory Prediction
Multi-Scale Interactive Network for Salient Object Detection
by: 綱島 秀樹
SOD Salient Object Detection
Learning to See Through Obstructions
by: Hirokatsu Kataoka
See Through Vision Obstruction
MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
by: Hirokatsu Kataoka
6D Pose Estimation MoreFusion DenseFusion
Instance Guided Proposal Network for Person Search
by: 渡部 海
Person Re-ID ObjectDetection
Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
by: Hirokatsu Kataoka
Domain Adaptatino Coarse-to-Fine
FGN: Fully Guided Network for Few-Shot Instance Segmentation
by: Hirokatsu Kataoka
Instance Segmentation Few-Shot Learning
LSM: Learning Subspace Minimization for Low-Level Vision
by: Teppei Kurita
Low-Level Vision Energy Minimization
GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models
by: a2kiti
human shape estimation
Coherent Reconstruction of Multiple Humans From a Single Image
by: a2kiti
human shape estimation
"Looking at the Right Stuff" - Guided Semantic-Gaze for Autonomous Driving
by: Anonymous
Dynamic Convolution: Attention Over Convolution Kernels
by: Masanori YANO
Recognition Image Classification Pose Estimation Attention
Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
by: Masanori YANO
Recognition Image Classification Pose Estimation Sparsity
Bidirectional Graph Reasoning Network for Panoptic Segmentation
by: Anonymous
panoptic segmentation semantic segmentation instance segmentation
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
by: Anonymous