CVPR2019論文サマリ

Mask Scoring R-CNN
by: Ryota Suzuki
Mask R-CNN Instance segmentation
Double-DIP: Unsupervised Image Decomposition via Coupled Deep-Image-Priors
by: Yoshiki
画像分解 教師なし学習 deep image prior
SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints
by: Kazuma_Asano
歩行者 予測 LSTM Prediction path prediction multiple interacting agents GAN
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
by: Kazuma_Asano
雨除去 雨 豪雨 Heavy rain derain dehaze GAN
Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition
by: GOTO Keita
弱教師あり学習 Action Recognition pre-training
Dance With Flow: Two-In-One Stream Action Detection
by: Tsubura Kazuki
Action Detection Two-in-One stream Two stream
Feature Denoising for Improving Adversarial Robustness
by: Hideki Tsunashima
Adversarial_Examples defense self_attention
On Stabilizing Generative Adversarial Training With Noise
by: yasud
GAN Training Stabilize 学習安定化
Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring
by: shirouchi satoshi
Recurrent Neural Networks Video Deblurring
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
by: Hirokatsu Kataoka
Temporal Action Localization Weakly Supervised Learning
Unsupervised Deep Tracking
by: Hirokatsu Kataoka
Unsupervised Tracking Correlation Filter SIamese Network
Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
by: Hirokatsu Kataoka
Multiple Object Tracking Tracking-by-detection
Fast Online Object Tracking and Segmentation: A Unifying Approach
by: Hirokatsu Kataoka
Tracking Semi-supervised Learning Video Object Segmentation
Practical Full Resolution Learned Lossless Image Compression
by: Takaya Yamazoe
lossless compression parallel
Privacy Protection in Street-View Panoramas Using Depth and Multi-View Imagery
by: Takaya Yamazoe
street view privacy GAN multi view
Cross-Modality Personalization for Retrieval
by: maokura
cross-modal search gaze personality caption
Towards Universal Object Detection by Domain Attention
by: Shuhei M Yoshida
物体検知 universal object detection domain attention
A Cross-Season Correspondence Dataset for Robust Semantic Segmentation
by: Tomoki Tanimura
Dataset Domain Semantic Segmentation point cloud 3D
Toward Convolutional Blind Denoising of Real Photographs
by: Katsuya Shimabukuro
Image Denoising Blind Denoising Noise Level Estimation
Engaging Image Captioning via Personality
by: Eisuke Yamagata
image-captioning personality
A Content Transformation Block for Image Style Transfer
by: Sou Uchida
style-transfer
Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks
by: Koki Obinata
learning paradigm learning framework
Representation Flow for Action Recognition
by: Tsubura Kazuki
optical flow action recognition representation flow
AE2-Nets: Autoencoder in Autoencoder Networks
by: kodai nakashima
Event-Based High Dynamic Range Image and Very High Frame Rate Video Generation Using Conditional Generative Adversarial Networks
by: Sou Uchida
Event Camera HDR High Frame Rate
Self-Supervised GANs via Auxiliary Rotation Loss
by: yasud
GAN 学習安定化 Discriminator Forgetting
All-Weather Deep Outdoor Lighting Estimation
by: Sou Uchida
Lighting Estimation HDR Panorama
Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters
by: Hirokatsu Kataoka
Correlation Filter
Grid R-CNN
by: Shuhei M Yoshida
Grid RCNN 物体検知 two-stage detection
Photo Wake-Up: 3D Character Animation From a Single Photo
by: Anonymous
3D SMPL animation
Leveraging Shape Completion for 3D Siamese Tracking
by: Hirokatsu Kataoka
3D Siamese Network Point Cloud
Target-Aware Deep Tracking
by: Hirokatsu Kataoka
Object Tracking Siamese Network
Learning Binary Code for Personalized Fashion Recommendation
by: Takaya Yamazoe
Fashion Recommendation Hash technique
Spatiotemporal CNN for Video Object Segmentation
by: Hirokatsu Kataoka
Video Object Segmentation
Character Region Awareness for Text Detection
by: Tomoki Tanimura
Text Detection Arbitrary Shape Pseudo Labling Weakly Supervised Dataset Polygon
Learning Multi-Class Segmentations From Single-Class Datasets
by: Yuta Tokuoka
multi-class segmentation conditioning biomedical image
Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification
by: Hirokatsu Kataoka
Person Re-identification Class Activation Maps
Text2Scene: Generating Compositional Scenes From Textual Descriptions
by: Kiro Otsu
network compression
Inverse Cooking: Recipe Generation From Food Images
by: Takaya Yamazoe
Food Recipe Cooking
Wide-Context Semantic Image Extrapolation
by: Hirokatsu Kataoka
Image Extrapolation
A Compact Embedding for Facial Expression Similarity
by: rindybell
画像埋め込み リソース 表情解析
Spatially Variant Linear Representation Models for Joint Filtering
by: Katsuya Shimabukuro
Joint Filtering Upsampling Image Denoising Image Deblurring
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
by: Kazuma_Asano
GAN mode collapse モード崩壊 Diverse Image Synthesis 多様性
Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
by: Shuhei M Yoshida
unsupervised domain adaptation domain-specific batch normalization
Atlas of Digital Pathology: A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep Learning
by: Yuta Nakamura
Dataset Medical Pathology Diagnosis Hierarchial
RENAS: Reinforced Evolutionary Neural Architecture Search
by: neka-nat
Pluralistic Image Completion
by: Kazuma_Asano
GAN 画像補完 image completion pluralistic diversity 多様性
A Generative Adversarial Density Estimator
by: Yoshiki
生成モデル
Structured Knowledge Distillation for Semantic Segmentation
by: kodai nakashima
Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation
by: kodai nakashima
Tell Me Where I Am: Object-Level Scene Context Prediction
by: kodai nakashima
End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image
by: Hirokatsu Kataoka
Time Lapse Video
Do Better ImageNet Models Transfer Better?
by: kodai nakashima
GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images
by: Hirokatsu Kataoka
GIF to Video
Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
by: kodai nakashima
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
by: Kensho Hara
Action Recognition GAN
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
by: Munetaka Minoguchi
Weakly Supervised Object Detection Multiple Instance Learning
Attention-Based Dropout Layer for Weakly Supervised Object Localization
by: Munetaka Minoguchi
Weakly Supervised Object Detection self-attention
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
by: shirouchi satoshi
Joint Detection and Description
ScratchDet: Training Single-Shot Object Detectors From Scratch
by: Munetaka Minoguchi
Object Detection pretrain
Style Transfer by Relaxed Optimal Transport and Self-Similarity
by: Sou Uchida
Style-transfer Earth Mover Distance
Learning Correspondence From the Cycle-Consistency of Time
by: Kensho Hara
Self-supervised Learning Visual Correspondence
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
by: Munetaka Minoguchi
Salient Object Detection
A Simple Pooling-Based Design for Real-Time Salient Object Detection
by: Munetaka MInoguchi
Salient Object Detection
MirrorGAN: Learning Text-To-Image Generation by Redescription
by: Kazuma_Asano
Text2Image Cycle Consistency GAN NLP
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection
by: Munetaka MInoguchi
Salient Object Detection
Grounding Human-To-Vehicle Advice for Self-Driving Vehicles
by: Takaya Yamazoe
Self Driving HAD Honda NLP
X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks
by: Takaya Yamazoe
CT X-ray reconstruction GAN 3D
Semi-Supervised Learning With Graph Learning-Convolutional Networks
by: Yusuke Mori
Graph Convolutional Network Semi-supervised Learning
Label Efficient Semi-Supervised Learning via Graph Filtering
by: uchi_k
graph graph convolutional neural network semi-supervised learning graph signal processing
Learning Active Contour Models for Medical Image Segmentation
by: Yuta Nakamura
segmentation active contour model medical image loss function
Salient Object Detection With Pyramid Attention and Salient Edges
by: Kzuma_Asano
Object Detection SOTA Saliency
Deep Network Interpolation for Continuous Imagery Effect Transition
by: Katsuya Shimabukuro
Image Interpolation Image Denoising Super Resolution Style Transfer Image-to-Image
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis
by: Anonymous
GAN
Catastrophic Child's Play: Easy to Perform, Hard to Defend Adversarial Attacks
by: Yoshihiro Fukuhara
Adversarial_Examples AEs Adversarial_Attack
FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation
by: Yuta Tokuoka
video object segmentatioon pixel-wise metric learning embedding
Explore-Exploit Graph Traversal for Image Retrieval
by: uchi_k
Weakly Supervised Deep Image Hashing Through Tag Embeddings
by: maokura
hashing word2vec search weakly-supervised
Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation
by: Kazuma_Asano
GAN Image-to-Image Translation Multimodal Unsupervised Image-to-Image Translation
Learning to Detect Human-Object Interactions With Knowledge
by: kota yoshida
human-object interactions 
Complete the Look: Scene-Based Complementary Product Recommendation
by: Takaya Yamazoe
Fashion Recommendation Scene
Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural Networks
by: Takaya Yamazoe
Self Driving OGM RNN
Panoptic Segmentation
by: Tomoki Tanimura
Panoptic Segmentation Segmentation Semantic Segmentation Instance Segmentation Task Metrics
Hardness-Aware Deep Metric Learning
by: Akihiro Yoshida
Metric Learning Data Augmentation
Attention-Aware Multi-Stroke Style Transfer
by: Kazuma_Asano
style transfer スタイル変換 attention
Zoom-In-To-Check: Boosting Video Interpolation via Instance-Level Discrimination
by: yasud
GAN フレーム補完 Frame Interpolation RoI Align
Convolutional Recurrent Network for Road Boundary Extraction
by: Tomoki Tanimura
Road Detection Autonomous Driving Feature Extraction Iterative
Action4D: Online Action Recognition in the Crowd and Clutter
by: Tenga Wakamiya
Action recognition
A Generative Appearance Model for End-To-End Video Object Segmentation
by: Takuma Yagi
video object segmentation gaussian mixture model
Deformable ConvNets V2: More Deformable, Better Results
by: Takuma Yagi
object detection instance segmentation deformable convolution
Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning
by: Takuma Yagi
computer vision and art unsupervised feature learning metric learning
SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360deg Images
by: Takuma Yagi
omni-directional images image representation equirectangular projection
Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks
by: Shuhei M Yoshida
keypoint detection occlusion graph networks
Unsupervised Image Captioning
by: Munetaka Minoguchi
Image Captioning Unsupervised
Learning Shape-Aware Embedding for Scene Text Detection
by: Munetaka Minoguchi
Text Detection
Describing Like Humans: On Diversity in Image Captioning
by: Munetaka Minoguchi
Image Captioning
LSTA: Long Short-Term Attention for Egocentric Action Recognition
by: Tsubura Kazuki
LSTM LSTA attention Action Recognition
Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting
by: Kazuma_Asano
Inpainting Pyramid Encoder Network
Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss
by: uchi_k
Learning Personalized Modular Network Guided by Structured Knowledge
by: SohOhara
classification segmentation structured knowledge graph modular network PMN
SketchGAN: Joint Sketch Completion and Recognition With Generative Adversarial Network
by: Ryosuke Araki
GANs Sketch Completion
Action Recognition From Single Timestamp Supervision in Untrimmed Videos
by: Tsubura Kazuki
action recognition timestamp
Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks
by: takumuikeya
visual explanation
Gait Recognition via Disentangled Representation Learning
by: Koki Obinata
gait disentanglement auto encoder dataset
Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions
by: Takuma Yagi
image restoration attention
Modulating Image Restoration With Continual Levels via Adaptive Feature Modification Layers
by: Yoshiki
Denoising Super resolution DeJPEG Adaptive layer
Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics
by: Takuma Yagi
recurrent neural network spatiotemporal dynamics non-stationarity forecasting
Deep Multimodal Clustering for Unsupervised Audiovisual Learning
by: Takuma Yagi
audiovisual learning clustering sound localization multisource detection
Multi-Task Learning of Hierarchical Vision-Language Representation
by: Takaya Yamazoe
Multi Task Vision Language VQA Coattention
TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning
by: Takuma Yagi
image-to-image translation siamese network
Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video
by: Shunsuke NAKATSUKA
abnormal event detection
Class-Balanced Loss Based on Effective Number of Samples
by: Takuma Yagi
image classification
Dual Encoding for Zero-Example Video Retrieval
by: Takuma Yagi
video retrieval
Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic Inferences
by: Takuma Yagi
confidence calibration stochastic infrence deep neural networks
IRLAS: Inverse Reinforcement Learning for Architecture Search
by: Takuma Yagi
inverse reinforcement learning architecture search
A Variational Auto-Encoder Model for Stochastic Point Processes
by: maokura
VAE PointProcess ActionPrediction 動画
Hybrid Task Cascade for Instance Segmentation
by: neka-nat
RENAS: Reinforced Evolutionary Neural Architecture Search
by: neka-nat
Object Instance Annotation With Deep Extreme Level Set Evolution
by: Anonymous
Cross-Modal Self-Attention Network for Referring Image Segmentation
by: Yasuhide Miura
Referring Image Segmentation cross-modal
Deep Supervised Cross-Modal Retrieval
by: Yasuhide Miura
Cross-modal cross-modal retrieval
Image-Question-Answer Synergistic Network for Visual Dialog
by: Yasuhide Miura
Visual dialog
Adversarial Semantic Alignment for Improved Image Captions
by: Yasuhide Miura
Image captioning NLP
Example-Guided Style-Consistent Image Synthesis From Semantic Labeling
by: Kazuma_Asano
Image2Image Translation Style Consistent Semantic Labeling
Soft Labels for Ordinal Regression
by: Koki Obinata
ordinal regression
BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative Network
by: Sou Uchida
Makeup Transfer Glow
Learning Parallax Attention for Stereo Image Super-Resolution
by: yasud
GAN SR ステレオ画像 Attention Atrous Convolution
Answer Them All! Toward Universal Visual Question Answering Models
by: Yasuhide Miura
VQA NLP CV
Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural Networks
by: Takaya Yamazoe
tactile vision cross-modal
TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection
by: GOTO Keita
Spatio-Temporal Action Detection Action Recognition ConvLSTM
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
by: Yusuke Mori
continual learning catastrophic forgetting
Attention Based Glaucoma Detection: A Large-Scale Database and CNN Model
by: Yasuhide Miura
Glaucoma attention
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
by: Yasuhide Miura
scene text detection
Adapting Object Detectors via Selective Cross-Domain Alignment
by: Takanori Ebihara
物体認識、cross-domain、強化学習
AIRD: Adversarial Learning Framework for Image Repurposing Detection
by: Yusuke Mori
Image repurposing
Im2Pencil: Controllable Pencil Illustration From Photographs
by: Kazuma_Asano
Image2Image Translation Style Transfer Image2Pencil
LO-Net: Deep Real-Time Lidar Odometry
by: Anonymous
LiDAR Odometry
Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
by: Anonymous
Stereo Depth point cloud
Linkage Based Face Clustering via Graph Convolution Network
by: Hiromasa Sakata
faceclassification graph
Attentive Region Embedding Network for Zero-Shot Learning
by: uchi_k
zero-shot generalized zero-shot embedding
MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition
by: Shuhei M Yoshida
MetaCleaner noisy labels meta learning
Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph
by: Takaya Yamazoe
Video Relationship Graph
PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation
by: Yuta Tokuoka
fine-grained segmentation hierarchical shape segmentation recursive neural network
Capture, Learning, and Synthesis of 3D Speaking Styles
by: Shintaro Yamamoto
Speech synthesis 3D character animation
A Parametric Top-View Representation of Complex Road Scenes
by: Takaya Yamazoe
Driving Top View parametric
MVTec AD -- A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
by: Yuta Tokuoka
unsupervised anomaly detection anomaly detection dataset segmentation of anomalous regions
Automatic Face Aging in Videos via Deep Reinforcement Learning
by: Shintaro Yamamoto
age progression reinforcement learning
Efficient Featurized Image Pyramid Network for Single Shot Detector
by: Shuhei M Yoshida
object detection feature pyramid featurized image pyramid
Peeking Into the Future: Predicting Future Person Activities and Locations in Videos
by: Anonymous
Explicit Bias Discovery in Visual Question Answering Models
by: Tomoki Tanimura
VQA statistical correlation rule bias discover mining
Triply Supervised Decoder Networks for Joint Detection and Segmentation
by: Shuhei M Yoshida
joint detection and segmentation object detection semantic segmentation
Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration
by: SohOhara
Neural Task Graph conjugate task graph video
Learning Actor Relation Graphs for Group Activity Recognition
by: Tsubura Kazuki
GCN Activity Recognition
Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
by: Satoshi Inose
mixture density networks multimodal prediction
Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features
by: Tomoki Tanimura
Aesthetics Quality Assessment Inception pretrained feature map AVA
LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
by: Eisuke Yamagata
自動運転 物体検知 3Dobjectdetection LiDAR
Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds
by: takeshi miura
Time-Conditioned Action Anticipation in One Shot
by: Tsubura Kazuki
Action Anticipation
Improving Action Localization by Progressive Cross-Stream Cooperation
by: GOTO Keita
Action Localization R-CNN
Max-Sliced Wasserstein Distance and Its Use for GANs
by: Hideki Tsunashima
Generative Adversarial Nets GANs Wasserstein Distance word translation image generation
Light Field Messaging With Deep Photographic Steganography
by: Hirokatsu Kataoka
When Color Constancy Goes Wrong: Correcting Improperly White-Balanced Images
by: Hirokatsu Kataoka
Relational Knowledge Distillation
by: Munetaka Minoguchi
Knowledge Distillation
Global Second-Order Pooling Convolutional Networks
by: Hideki Tsunashima
CNN Pooling Global Average Pooling second-order pooling CIFAR-100 ImageNet 1k
Beyond Volumetric Albedo -- A Surface Optimization Framework for Non-Line-Of-Sight Imaging
by: Hirokatsu Kataoka
Events-To-Video: Bringing Modern Computer Vision to Event Cameras
by: Munetaka Minoguchi
Event Camera
Emotion-Aware Human Attention Prediction
by: Masaki Miyamoto
AttI EASal DNN human gaze prediction
Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks
by: Kazuma_Asano
GAN Image2Image pix2pix voxel voxelGAN feedback
Understanding and Visualizing Deep Visual Saliency Models
by: Yamada Yoshihiro
SoDeep: A Sorting Deep Net to Learn Ranking Loss Surrogates
by: Yoshiki
Ranking Cross-modal retrieval Multi-label classification Visual memorability ranking
Reasoning-RCNN: Unifying Adaptive Global Reasoning Into Large-Scale Object Detection
by: Ryota Suzuki
object detection RCNN visual reasoning
Composing Text and Image for Image Retrieval - an Empirical Odyssey
by: Ryota Suzuki
image retrieval vision and language
Unsupervised Domain-Specific Deblurring via Disentangled Representations
by: Takaya Yamazoe
deblurring blur unsupervised
3D Appearance Super-Resolution With Deep Learning
by: Yuta Tokuoka
super resolution 3D appearance super-resolution dataset texture map 3D geometric information
An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
by: Hiromasa Sakata
actionrecognition skeletonbased
Inverse Discriminative Networks for Handwritten Signature Verification
by: rindybell
署名認識 手書き署名認識 署名
Exploring the Bounds of the Utility of Context for Object Detection
by: Shuhei M Yoshida
object detection context utility
AutoAugment: Learning Augmentation Strategies From Data
by: cfiken
Data Augmentation Image Classification Transfer Learning
Semantics Disentangling for Text-To-Image Generation
by: Keito Ishihara
text2image GAN
The Visual Centrifuge: Model-Free Layered Video Representations
by: Kensho Hara
Layer Decomposition
Did It Change? Learning to Detect Point-Of-Interest Changes for Proactive Map Updates
by: Munetaka Minoguchi
Point-of-Interest(PoI) Detect Point-of-Interest Changes
Unsupervised Person Re-Identification by Soft Multilabel Learning
by: Kensho Hara
Person Reidentification Unsupservised Learning
Animating Arbitrary Objects via Deep Motion Transfer
by: Kensho Hara
Motion Transfer
Sensitive-Sample Fingerprinting of Deep Neural Networks
by: Koki Obinata
security attack detection
Learning Context Graph for Person Search
by: Kensho Hara
Person Search Group Reidentification
Speech2Face: Learning the Face Behind a Voice
by: Shion Honda
cross-modal learning speech recognition image generation
Improved Road Connectivity by Joint Learning of Orientation and Segmentation
by: Takaya Yamazoe
Road Map Satellite Orientation SpaceNet DeepGlobe
Lending Orientation to Neural Networks for Cross-View Geo-Localization
by: rindybell
衛星画像 位置推定
Attentive Feedback Network for Boundary-Aware Salient Object Detection
by: Kazuma_Asano
Salient Object Detection RealTime SOTA
Towards Natural and Accurate Future Motion Prediction of Humans and Animals
by: Shintaro Yamamoto
Motion prediction
Attention-Guided Network for Ghost-Free High Dynamic Range Imaging
by: Takeru Suda
HDR Attention
3D Guided Fine-Grained Face Manipulation
by: Shintaro Yamamoto
facial expression 3D face model
Dual Attention Network for Scene Segmentation
by: Hideki Tsunashima
Semantic Segmentation SOTA Attention Cityscapes PASCAL Context COCO stuff dataset
Reflection Removal Using a Dual-Pixel Sensor
by: Hirokatsu Kataoka
Reflection Removal Dual Pixel Sensor Photography
Practical Coding Function Design for Time-Of-Flight Imaging
by: Hirokatsu Kataoka
Time-of-Flight (ToF) Coding Function 3D Reconstruction
Neural Sequential Phrase Grounding (SeqGROUND)
by: Keito Ishihara
PhraseGrounding LSTM
Temporal Cycle-Consistency Learning
by: kotayoshida
Cycle-Consistency 動画認識 Few-shot learning
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
by: Hirokatsu Kataoka
Super Resolution
Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
by: Hirokatsu Kataoka
Multispectral Image Hyperspectral Image FusionNet
Object-Driven Text-To-Image Synthesis via Adversarial Training
by: Mitani Tomohiro
GAN COCO text-to-image
Learning Attraction Field Representation for Robust Line Segment Detection
by: Hirokatsu Kataoka
Line Segment Detection (LSD) U-Net
Self-Calibrating Deep Photometric Stereo Networks
by: Takeru Suda
フォトメトリックステレオ 光源推定
Blind Super-Resolution With Iterative Kernel Correction
by: Kazuma_Asano
SR Super Resolution SOTA blind SR
Learning Spatio-Temporal Representation With Local and Global Diffusion
by: GOTO Keita
Action Recognition Spatio-Temporal Action Detection
Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis
by: Mitani Tomohiro
Gaze redirection gaze adaptation
PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds
by: shirouchi satoshi
Ridge Motion Estimation
Learning to Explain With Complemental Examples
by: SohOhara
multimodal explanation complemental explanation classification
Unifying Heterogeneous Classifiers With Distillation
by: Hideki Tsunashima
Distillation Classifier Heterogeneous Classifiers ImageNet LSUN Places365
AdaFrame: Adaptive Frame Selection for Fast Video Recognition
by: Hiromasa Sakata
videorecognition lstm reinforcementlearning
Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learning
by: Shuhei M Yoshida
few-shot learning metric learning local descriptor naive-Bayes nearest neighbor
Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution
by: Kazuma_Asano
Video Magnification Fractional Anisotropy NTT
Graph-Based Global Reasoning Networks
by: cfiken
Global Reasoning Relational Reasoning CNN Graph Convolution
Learning to Calibrate Straight Lines for Fisheye Image Rectification
by: Hirokatsu Kataoka
Distortion Fisheye Camera Line
Sea-Thru: A Method for Removing Water From Underwater Images
by: Katsuya Shimabukuro
Image Reconstruction Removing Water
Towards Robust Curve Text Detection With Conditional Spatial Expansion
by: Shuhei M Yoshida
curve text detection conditional spatial expansion
Camera Lens Super-Resolution
by: Hirokatsu Kataoka
Super Resolution Camera Lens
Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels
by: Katsuya Shimabukuro
Image Restoration Super Resolution
Frame-Consistent Recurrent Video Deraining With Dual-Level Flow
by: Kazuma_Asano
Frame-Consistent Recurrent Video deraining
Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translation
by: Anonymous
Cycle-GAN Artworks Image2Image
Revisiting Perspective Information for Efficient Crowd Counting
by: Shuhei M Yoshida
crowd counting perspective map
KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing
by: Rei Tamaru
semantic segmentation generative adversarial networks knowledge graph
OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge
by: maokura
VQA dataset
Enhanced Pix2pix Dehazing Network
by: Anonymous
Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss
by: Shunsuke NAKATSUKA
Face Generation Audio Signal GANs
EventNet: Asynchronous Recursive Event Processing
by: Munetaka Minoguchi
イベントカメラ
Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables
by: Munetaka Minoguchi
Image Captioning Adversarial Noise Adversarial Attack
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
by: Hideki Tsunashima
6D Object Pose Estimation YCB-Video LineMOD Point Cloud Object Detection SOTA
Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments
by: Eisuke Yamagata
affordance prediction
Unsupervised Learning of Action Classes With Continuous Temporal Embedding
by: GOTO Keita
教師なし学習 Temporal Segmantation
Interaction-And-Aggregation Network for Person Re-Identification
by: takumuikeya
preid
CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency
by: Hiroaki Aizawa
Unsupervised Domain Adaptation
Shape Robust Text Detection With Progressive Scale Expansion Network
by: takumuikeya
text detection
Attention-Guided Unified Network for Panoptic Segmentation
by: Ryuta Shitomi
Panoptic Segmentation Attention
Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach
by: Hiroaki Aizawa
Cross-domain Semantic Segmentation Domain Adaptation
All About Structure: Adapting Structural Information Across Domains for Boosting Semantic Segmentation
by: Hiroaki Aizawa
Unsupervised Domain Adaptation Semantic Segmentation
Predicting Future Frames Using Retrospective Cycle GAN
by: kotayoshida
video recognition cycle-constraints フレーム予測
Towards Accurate One-Stage Object Detection With AP-Loss
by: Ryota Nishijima
detection one-shot loss
SpotTune: Transfer Learning Through Adaptive Fine-Tuning
by: Koki Obinata
fine-tuning transfer learning
Adversarial Defense Through Network Profiling Based Path Extraction
by: neka-nat
Tightness-Aware Evaluation Protocol for Scene Text Detection
by: Tomoki Tanimura
Text detection Evaluation metrics Score
Listen to the Image
by: shirouhi satoshi
Sensory Substitution devices Generation Adversarial Networks
F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
by: Takaya Yamazoe
Few shot learning zero shot learning GAN VAE
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception
by: Shintaro Yamamoto
depth prediction optical flow unsupervised learning
Monocular Depth Estimation Using Relative Depth Maps
by: Tomoki Tanimura
Depth estimation Relative depth
MSCap: Multi-Style Image Captioning With Unpaired Stylized Text
by: Keito Ishihara
image captioning
COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis
by: Hiromasa Sakata
crowdcounting
SparseFool: A Few Pixels Make a Big Difference
by: Yoshihiro Fukuhara
Adversarial Example Adversarial Attack Sparse Attack
Deep Spectral Clustering Using Dual Autoencoder Network
by: Munetaka Minoguchi
Clustering Deep Clustering Unsupervised
Unsupervised Multi-Modal Neural Machine Translation
by: Yasuhide Miura
multi-modal unsupervised NMT
Attentive Relational Networks for Mapping Images to Scene Graphs
by: Munetaka Minoguchi
Scene Graph
Compressing Convolutional Neural Networks via Factorized Convolutional Filters
by: Munetaka Minoguchi
Filter Pruning
Gradient Matching Generative Networks for Zero-Shot Learning
by: Kensho Hara
Zero-shot Learning GAN
On the Intrinsic Dimensionality of Image Representations
by: Munetaka Minoguchi
Robot Arm 3D model
Gradient Matching Generative Networks for Zero-Shot Learning
by: Kensho Hara
Zero-shot Learning GAN
Adaptive NMS: Refining Pedestrian Detection in a Crowd
by: Ryota Suzuki
non maximum suppression detection
Point in, Box Out: Beyond Counting Persons in Crowds
by: Ryota Suzuki
cloud counting detection annotation cost
Locating Objects Without Bounding Boxes
by: Ryota Suzuki
object detection Hausdorff distance
Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution
by: Takaya Yamazoe
Deconvolution Blur Blind Douglas-Rachfold
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations
by: Ryota Nishijima
self-supervised learning object detection multi-task learning
Towards Visual Feature Translation
by: maokura
feature-transfer handcraft search
3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
by: Naoya Chiba
3D semantic instance segmentation RGB-D 3D CNN
Occupancy Networks: Learning 3D Reconstruction in Function Space
by: Naoya Chiba
Occupancy Networks 3D mesh point cloud 3D reconstruction
Efficient Neural Network Compression
by: Kiro Otsu
ネットワーク圧縮 固有値分解
Revisiting Self-Supervised Visual Representation Learning
by: Hiroaki Aizawa
Self-supervised Learning
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
by: Rei Tamaru
DeepFashion Mask R-CNN Image Detection Match R-CNN
Taking a Deeper Look at the Inverse Compositional Algorithm
by: Naoya Chiba
Lucas-Kanade (LK) Inverse Compositional (IC) Algorithm 6DoF Estimation Registration Rigid Motion Estimation
PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation
by: Naoya Chiba
6DoF Estimation Vector Field Keypoints Detection
VITAMIN-E: VIsual Tracking and MappINg With Extremely Dense Feature Points
by: Tomoki Tanimura
SLAM Indirect method Dense geometry reconstruction dense feature points dominant flow optical flow 3D
NetTailor: Tuning the Architecture, Not Just the Weights
by: Hideki Tsunashima
Image Recognition Pretrained model fine-tuning Task Transfer Distillation Pruning SVHN Flowers PASCAL VOC
PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Image
by: Naoya Chiba
Plane Estimation Plane Segmentation
Causes and Corrections for Bimodal Multi-Path Scanning With Structured Light
by: Naoya Chiba
Structured Light Phase Measuring Profilometry 3D Measurement 3D Scanning
H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions
by: Naoya Chiba
Hand-Object Pose Action Recognition
Multimodal Explanations by Predicting Counterfactuality in Videos
by: SohOhara
multimodal explanation counterfactuality explanation video classification clipping
Deep Asymmetric Metric Learning via Rich Relationship Mining
by: Keito Ishihara
metric learning graph
Ensemble Deep Manifold Similarity Learning Using Hard Proxies
by: Shuhei M Yoshida
metric learning ensemble learning N-pair loss hard proxy estimation
Audio Visual Scene-Aware Dialog
by: Shion Honda
question answering video audio dialogue
Constrained Generative Adversarial Networks for Interactive Image Generation
by: Yoshiki
GAN Generative model Interactive
StoryGAN: A Sequential Conditional GAN for Story Visualization
by: Ryosuke Tanno
StoryGAN story-to-image-sequence generation 画像生成
Noise-Aware Unsupervised Deep Lidar-Stereo Fusion
by: Ryosuke Tanno
Lidar-Stereo Unsupervised stereo matching depth completion
Versatile Multiple Choice Learning and Its Application to Vision Computing
by: Ryosuke Tanno
ensemble method multiple choice learning MCL
EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors
by: Ryosuke Tanno
Gait Recognition Dinamic Vision Sensor Event Camera
Learning 3D Human Dynamics From Video
by: Anonymous
3D motion
ToothNet: Automatic Tooth Instance Segmentation and Identification From Cone Beam CT Images
by: Ryosuke Tanno
Instance Segmentation Identification CBCT image RPN medical image teeth
Image Generation From Layout
by: Takeru Suda
生成モデル Disentangle
Inverse Procedural Modeling of Knitwear
by: Takeru Suda
Knitwear fashion 教師なし学習
Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects
by: Ryota Suzuki
object detection sparse annotation sampling
Barrage of Random Transforms for Adversarially Robust Defense
by: Ryota Suzuki
adversarial example
Large-Scale Interactive Object Segmentation With Human Annotators
by: Anonymous
segmentation annotation dataset
Iterative Reorganization With Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning
by: Hiroaki Aizawa
Self-supervised Learning Jigsaw Puzzle
Iterative Alignment Network for Continuous Sign Language Recognition
by: Masaki Miyamoto
sign language recognition 3D-ResNet SLR LSTM CTC
TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
by: Hiroaki Aizawa
Few-shot Learning Meta Learning
PPGNet: Learning Point-Pair Graph for Line Segment Detection
by: Ryuta Shitomi
Line Segment Detection Graph theory
Collaborative Spatiotemporal Feature Learning for Video Action Recognition
by: Shunsuke NAKATSUKA
Spatiotemporal Feature Learning Video Action Recognition Conv3D
Pyramid Feature Attention Network for Saliency Detection
by: Hideki Tsunashima
saliency detection object detection visual tracking image retrieval semantic segmentation SOTA DUTS-test ECSSD HKU-IS PASCAL-S DUT-OMRON
End-To-End Interpretable Neural Motion Planner
by: Takeru Suda
自動運転 LiDAR HDmap
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image
by: Yoitsu Takahashi
Pose Estimation 3D Human Body Model
Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation
by: Tomoki Tanimura
depth estimation disparity map cycle inconsistency distilation
Fast Spatially-Varying Indoor Lighting Estimation
by: Satoshi Inose
CNN Spherical harmonics
Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras
by: Takaya Yamazoe
Event Camera Corner Detection Classifier
What's to Know? Uncertainty as a Guide to Asking Goal-Oriented Questions
by: Masaki Miyamoto
rainforcement agent visual dialogue bayesian
CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
by: takeshi miura
multi target multi-camera tracking image-based vehicle re-identification a city-scale benchmark
Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video
by: takeshi miura
Estimating 3D Motion and Forces MoCap
Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry
by: takeshi miura
monocular Visual Odometry CNN RNN
Assessment of Faster R-CNN in Man-Machine Collaborative Search
by: maokura
ubiquitous search eye-tracking
What Correspondences Reveal About Unknown Camera and Motion Models?
by: takeshi miura
3D vision
Unsupervised Face Normalization With Extreme Pose and Expression in the Wild
by: Shintaro Yamamoto
GAN face recognition
Rethinking the Evaluation of Video Summaries
by: Shion Honda
video summarization metrics
Feedback Network for Image Super-Resolution
by: Masaki Miyamoto
feedback block Image Super Resolution SR image
Learning Monocular Depth Estimation Infusing Traditional Stereo Knowledge
by: Shintaro Yamamoto
depth prediction unsupervised learning
Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning
by: neka-nat
Information Maximizing Visual Question Generation
by: kotayoshida
visual question generation visual question answering language and vision
IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition
by: takeshi miura
dataset pest recognition
Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search
by: Takeru Suda
Adversarial Attack Nearest-Neighbor Search Big Data
ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification
by: kota yoshida
text text recognition image refrection
Argoverse: 3D Tracking and Forecasting With Rich Maps
by: takeshi miura
dataset
Learning Not to Learn: Training Deep Neural Networks With Biased Data
by: Yoshihiro Fukuhara
UPSNet: A Unified Panoptic Segmentation Network
by: Takeru Suda
semantic segmentation instance segmentation panoptic segmentation
Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
by: Shintaro Yamamoto
depth prediction domain adaptation
Side Window Filtering
by: Takeru Suda
Window Filtering image smoothing denoising enhancement structure preserving texture-removing mutual-structure extraction and high dynamic range image tone mapping Colorization
Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition
by: hiroki iida
DomainAdaptation TextImageRecognition
Quantization Networks
by: Shuhei M Yoshida
quantization
RES-PCA: A Scalable Approach to Recovering Low-Rank Matrices
by: Shuhei M Yoshida
ロバスト主成分分析 RPCA
Neuro-Inspired Eye Tracking With Eye Movement Dynamics
by: Shintaro Yamamoto
eye tracking
ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation
by: Shuhei M Yoshida
semantic segmentation instance segmentation multi-scale context ZigZagNet
Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally
by: Shintaro Yamamoto
facial emotion
Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes
by: Tomoki Tanimura
SLAM 3D reconstruction odometry cauchy probabilistic bayes data association loop-closures
Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation
by: Takanori Ebihara
弱教師あり学習 物体認識 物体セグメンテーション
Variational Prototyping-Encoder: One-Shot Learning With Prototypical Images
by: Yuta Tokuoka
one-shot learning embedding variational encoder
Rare Event Detection Using Disentangled Representation Learning
by: Tomoki Tsujimura
disentanglement learning representation learning change detection
DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality
by: Anonymous
CNN 3D HDR
DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
by: Shunsuke NAKATSUKA
Video Action Recognition Cross Domain
Deep Dual Relation Modeling for Egocentric Interaction Recognition
by: Shunsuke NAKATSUKA
Egocentric Interaction Recognition Relation Modeling
Hyperspectral Imaging With Random Printed Mask
by: Sou Uchida
Hyperspectral Imaging
PA3D: Pose-Action 3D Machine for Video Recognition
by: Shunsuke NAKATSUKA
Conv3D Video Action Recognition Pose
Visual Localization by Learning Objects-Of-Interest Dense Match Regression
by: Anonymous
CNN localization
Inserting Videos Into Videos
by: Sou Uchida
Video Insertion
ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification
by: kota yoshida
video question answering video
DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
by: Yuta Tokuoka
real-time semantic segmentation feature aggregation multi scale
MOTS: Multi-Object Tracking and Segmentation
by: Shunsuke NAKATSUKA
Multi-Object Tracking and Segmentation Dataset
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
by: GOTO Keita
Graph Convolutional Networks Two-stream Skeleton Action Recognition
Noise2Void - Learning Denoising From Single Noisy Images
by: kota yoshida
denoising biomedical
Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking
by: Shunsuke NAKATSUKA
Object Tracking Region Proposal Network Siamese Network
Learning Image and Video Compression Through Spatial-Temporal Energy Compaction
by: Sou Uchida
Image Compression Video Compression Energy Function
Object Discovery in Videos as Foreground Motion Clustering
by: Tsubura Kazuki
object detection segmentation pixel-trajectory RNN U-Net Y-Net
Deep RNN Framework for Visual Sequential Applications
by: cfiken
Visual sequence Deep RNN
Pose2Seg: Detection Free Human Instance Segmentation
by: Hiromasa Sakata
instance-segmentetion
Neighbourhood Watch: Referring Expression Comprehension via Language-Guided Graph Attention Networks
by: kota yoshida
referring expression comprehension language and vision
Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence
by: Keito Ishihara
decaptioning encoder decoder
Scene Graph Generation With External Knowledge and Image Reconstruction
by: kota yoshida
Scene Graph Generation Image Reconstruction
Long-Term Feature Banks for Detailed Video Understanding
by: cfiken
Video Understanding
SSN: Learning Sparse Switchable Normalization via SparsestMax
by: Daisuke Makino
Normalization
Semantic Component Decomposition for Face Attribute Manipulation
by: Shintaro Yamamoto
facial attribute image editing
What Object Should I Use? - Task Driven Object Detection
by: Shuhei M Yoshida
task driven object detection graph neural network
Multi-Task Multi-Sensor Fusion for 3D Object Detection
by: Shuhei M Yoshida
3D object detection multi-task learning LiDAR
Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning
by: Koki Obinata
metric learning pair loss framework
Domain-Symmetric Networks for Adversarial Domain Adaptation
by: Koki Obinata
domain adaptation adversarial learning
Learning to Learn From Noisy Labeled Data
by: Koki Obinata
meta learning noisy data
ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
by: Rei Tamaru
3D Car Dataset 3D-RCNN DeepMANTA
Task-Free Continual Learning
by: NSD
Continual Learning
Context-Aware Visual Compatibility Prediction
by: Eisuke Yamagata
fashion compatibility
Scalable Convolutional Neural Network for Image Compressed Sensing
by: yasud
CS 圧縮センシング SCSNet
Edge-Labeling Graph Neural Network for Few-Shot Learning
by: Akihiro Yoshida
graph neural network few-shot learning
Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations
by: Kensho Hara
Instance Segmentation Weakly Supervised Learning
Efficient Video Classification Using Fewer Frames
by: Akihiro Yoshida
video classification distillation
A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture Recognition
by: GOTO Keita
Manifold Learning Gesture Recognition
Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
by: Hiroaki Aizawa
3D object detection point cloud
Adaptively Connected Neural Networks
by: Hiroaki Aizawa
Attentive Single-Tasking of Multiple Tasks
by: Hiroaki Aizawa
Multi-task Learning Attention
End-To-End Multi-Task Learning With Attention
by: Hiroaki Aizawa
Multi-task Learning Attention
Joint Discriminative and Generative Learning for Person Re-Identification
by: Hiroaki Aizawa
Person Re-Identification
Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
by: Mitani Tomohiro
anomaly detection skelton features
A Structured Model for Action Detection
by: Tsubura Kazuki
Action Detection Graph Convolutional Network I3D Mask R-CNN
Learning Words by Drawing Images
by: Hiroaki Aizawa
Audio-visual Model GAN
What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
by: Akihiro Yoshida
Action Quality Assessment Multi Task Learning
DSFD: Dual Shot Face Detector
by: Ryota Nishijima
face detection object detection
MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors
by: takumuikeya
NMS objectdetection detection 物体検出
Context-Reinforced Semantic Segmentation
by: Masaki Miyamoto
segmentation p-map context reinforce
Translate-to-Recognize Networks for RGB-D Scene Recognition
by: Tenga Wakamiya
RGB-D Scene Recognition
AdaptiveFace: Adaptive Margin and Sampling for Face Recognition
by: yasud
Face Recognition 顔認識 cos face margin based loss arc face
Self-Supervised Learning via Conditional Motion Propagation
by: Hiroaki Aizawa
Self-supervised Learning
SR-LSTM: State Refinement for LSTM Towards Pedestrian Trajectory Prediction
by: Mitani Tomohiro
Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images
by: Hiroaki Aizawa
Semi-supervised Learning
Curls & Whey: Boosting Black-Box Adversarial Attacks
by: Ryota Suzuki
adversarial example
Disentangled Representation Learning for 3D Face Shape
by: Mitani Tomohiro
3d mesh face model disentagle spectal graph convolution
Distilling Object Detectors With Fine-Grained Feature Imitation
by: Ryota Nishijima
knowledge distillation object detection
NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction
by: Hideki Tsunashima
Multi Task Learning NYU v2 dataset IMDB-WIKI dataset
Min-Max Statistical Alignment for Transfer Learning
by: Takuma Yagi
statistical alignment unsupervised domain adaptation zero-shot learning
On Exploring Undetermined Relationships for Visual Relationship Detection
by: QIUYUE
Visual Relationship Detection
Densely Semantically Aligned Person Re-Identification
by: Takanori Ebihara
人物検出
Weakly Supervised Image Classification Through Noise Regularization
by: Tenga Wakamiya
weakly supervised Image Classification
Stochastic Class-Based Hard Example Mining for Deep Metric Learning
by: s.kasai
Metric Learning Sample Mining
Learning Without Memorizing
by: QIUYUE
Incremental Learning
Dynamic Recursive Neural Network
by: QIUYUE
Recursive nerual network
Weakly Supervised Video Moment Retrieval From Text Queries
by: Tenga Wakamiya
weakly supervised
Learning Loss for Active Learning
by: cfiken
Active Learning
Classification-Reconstruction Learning for Open-Set Recognition
by: Masaki Miyamoto
Open-set classification CROSR reconstruction recognition
Deep Sky Modeling for Single Image Outdoor Lighting Estimation
by: Satoshi Inose
outdoor lighting HDR
GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
by: Hiromasa Sakata
GAN face-reconstruction
A Flexible Convolutional Solver for Fast Style Transfers
by: Takuma Yagi
style transfer
Mapping, Localization and Path Planning for Image-Based Navigation Using Visual Features and Map
by: Shuhei M Yoshida
image-based navigation retrieval-based localization map construction
Face Parsing With RoI Tanh-Warping
by: Anonymous
face parsing Mask R-CNN FCN
LiveSketch: Query Perturbations for Guided Sketch-Based Visual Search
by: Anonymous
LiveSketch Visual Search
Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Images
by: Yuta Nakamura
recipe food cross-modal adversarial loss retrieval loss metric learning modality alignment
Deep Embedding Learning With Discriminative Sampling Policy
by: neka-nat
InverseRenderNet: Learning Single Image Inverse Rendering
by: maokura
InverseRendering Renderer MultiViewStereo
Destruction and Construction Learning for Fine-Grained Image Recognition
by: QIUYUE
Fine-grained Image Recognition
Distraction-Aware Shadow Detection
by: QIUYUE
Shadow Detection
Mask-Guided Portrait Editing With Conditional GANs
by: kubo.takahiro
GAN
Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
by: Hirokatsu Kataoka
Neural Rejuvenation Initialization Reallocation
Group Sampling for Scale Invariant Face Detection
by: kubo.takahiro
Object Detection
Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification
by: Akihiro Yoshida
re-identification metric learning
Revealing Scenes by Inverting Structure From Motion Reconstructions
by: Kazuma_Asano
GAN Structure from Motion Reconstructions SfM
Dichromatic Model Based Temporal Color Constancy for AC Light Sources
by: Anonymous
Multi-Label Image Recognition With Graph Convolutional Networks
by: QIUYUE
Multi-label image recognition Graph Convolutional Network
High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection
by: QIUYUE
Pedestrian Detection
Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in a Triadic Interaction
by: Takuma Yagi
social interaction social signal prediction motion capture
Kernel Transformer Networks for Compact Spherical Convolution
by: Tomoki Tanimura
spherical convolution scalability transfer
Isospectralization, or How to Hear Shape, Style, and Correspondence
by: Shion Honda
mesh object reconstruction graph
Semantic Image Synthesis With Spatially-Adaptive Normalization
by: Shion Honda
GAN semantic segmentation
Social Relation Recognition From Videos via Multi-Scale Spatial-Temporal Reasoning
by: kubo.takahiro
GraphConvolution Video
Relational Action Forecasting
by: Takuma Yagi
action forecasting early action prediction graph neural networks
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation
by: Masaki Taniguchi
Temporal Action Segmentation Temporal Convolutional Network
Semi-Supervised Transfer Learning for Image Rain Removal
by: Masaki Miyamoto
Semi supervised transfer rain removal SIRR deep
Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction
by: Takuma Yagi
mesh reconstruction photometric consistency shape prior
3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis
by: Takuma Yagi
future prediction visual forecasting motion decomposition
Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation
by: kubo.takahiro
Face
DeepVoxels: Learning Persistent 3D Feature Embeddings
by: Takuma Yagi
novel view synthesis 3d vision scene representation
What Do Single-View 3D Reconstruction Networks Learn?
by: Hideki Tsunashima
3D reconstruction Reconstruction Single-view 3D reconstruction
Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark Detection
by: kubo.takahiro
FaceLandmark
Efficient Parameter-Free Clustering Using First Neighbor Relations
by: Takeru Suda
hierarchical agglomerative method clustering DeepClustering
Learning View Priors for Single-View 3D Reconstruction
by: Takuma Yagi
single-view 3D reconstruction view prior
Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D Shapes
by: Takeru Suda
point cloud mobility PointNet
Image Super-Resolution by Neural Texture Transfer
by: shirouchi satoshi
Neural Texture Transfer
Deep Single Image Camera Calibration With Radial Distortion
by: Tenga Wakamiya
Camera Calibration
Second-Order Attention Network for Single Image Super-Resolution
by: Sou Uchida
Super Resolution Attention
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
by: Takeru Suda
Segmentation Memory-Efficient
RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection
by: QIUYUE
Object Detection Distance Metric Learning few-shot learning
Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
by: Takuma Yagi
relative pose estimation scene completion spectral matching
Ranked List Loss for Deep Metric Learning
by: QIUYUE
Deep Metric Learning (DML) Ranking-motivated structured loss function
CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning
by: QIUYUE
Semantic Segmentation few-shot learning
R3 Adversarial Network for Cross Model Face Recognition
by: Shintaro Yamamoto
feature transformation
Co-Occurrent Features in Semantic Segmentation
by: ERLYN MANGUILIMOTAN
semantic segmentation co-occurent features
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding
by: Hiromasa Sakata
Deep Spherical Quantization for Image Search
by: Anonymous
image search quantization sparse coding
Learning Joint Reconstruction of Hands and Manipulated Objects
by: Anonymous
hand-object manipulation reconstruction
PifPaf: Composite Fields for Human Pose Estimation
by: yasud
Human Pose Estimation ポーズ推定 HPE
Fully Learnable Group Convolution for Acceleration of Deep Neural Networks
by: takumuikeya
高速化 DNN
Local Temporal Bilinear Pooling for Fine-Grained Action Parsing
by: GOTO Keita
Temporal Action Segmantation Bilinear Pooling
Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer
by: yasud
3D Hand Pose Estimation Point Net
Divergence Triangle for Joint Training of Generator Model, Energy-Based Model, and Inferential Model
by: takeshi miura
Learning Single-Image Depth From Videos Using Quality Assessment Networks
by: Anonymous
SfM
Sliced Wasserstein Generative Models
by: asato matsumoto
画像生成 AE GAN Wasserstein Distribution
Deep Flow-Guided Video Inpainting
by: asato matsumoto
Video Inpainting Optical Flow Field
Video Generation From Single Semantic Label Map
by: asato matsumoto
image-to-video Video Generation Semantic
Cross-Modal Relationship Inference for Grounding Referring Expressions
by: Keito Ishihara
grounding Cross-Modal
CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions
by: Keito Ishihara
dataset Visual Reasoning
Precise Detection in Densely Packed Scenes
by: QIUYUE
Precise Object Detection Densely Packed Scenes
Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth
by: QIUYUE
Depth Estimation Odometry Estimation Recurrent Neural Network
The Perfect Match: 3D Point Cloud Matching With Smoothed Densities
by: QIUYUE
Point Cloud Matching;
Efficient Multi-Domain Learning by Covariance Normalization
by: NSD
Multi Domain Learning
Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks
by: QIUYUE
Video Object Segmentation Interactive
LAEO-Net: Revisiting People Looking at Each Other in Videos
by: kubo.takahiro
Video Face
Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks
by: kubo.takahiro
Face
Learning Individual Styles of Conversational Gesture
by: kubo.takahiro
GestureGeneration Multimodal
Object Counting and Instance Segmentation With Image-Level Supervision
by: Eisuke Yamagata
common object counting desity map
CRAVES: Controlling Robotic Arm With a Vision-Based Economic System
by: Masaki Miyamoto
robot arm 3D pose estimation key point reinforcement robot
Coordinate-Based Texture Inpainting for Pose-Guided Human Image Generation
by: yasud
Hourglass Deep Fashion Coordinate-Based 再合成
Learning to Film From Professional Human Motion Videos
by: Masaki Miyamoto
film drone ConvLSTM planning motion DOF
How to Make a Pizza: Learning a Compositional Layer-Based GAN Model
by: shirouchi satoshi
Pizza GAN
UniformFace: Learning Deep Equidistributed Representation for Face Recognition
by: maiki.okura
FaceVerification FaceIdentification Loss
Generalizing Eye Tracking With Bayesian Adversarial Learning
by: GOTO Keita
Gaze Estimation Eye Tracking Bayesian Adversarial Learning
Learning to Learn Image Classifiers With Visual Analogy
by: Yuta Nakamura
graph embedding visual analogy few-shot learning
Spatial Fusion GAN for Image Synthesis
by: KazumaAasano
GAN Spatial Fusion Image Synthesis
Efficient Neural Network Compression
by: Kiro Otsu
3D CNN human identification multi-spectral image
Part-Regularized Near-Duplicate Vehicle Re-Identification
by: Masaki Miyamoto
Near-duplicate vehicle re-identification part-regularized framework
Spatial-Aware Graph Relation Network for Large-Scale Object Detection
by: takumuikeya
object detection 物体検出 detection
Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition
by: Daisuke Makino
Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network
by: Tsubura Kazuki
3D pose estimation
Recurrent Back-Projection Network for Video Super-Resolution
by: Masaki Miyamoto
SR RBPN RNN Super-Resolution video VSR
A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision
by: Munetaka Minoguchi
Salient Object Detection Contour Detection Edge Detection
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
by: Munetaka Minoguchi
Image Captioning
Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
by: yasud
Texture GAN
Dissimilarity Coefficient Based Weakly Supervised Object Detection
by: Tomoki Tanimura
object detection weakly supervised conditional distribution discrete generative model
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
by: Ryota Nishijima
convolution CNN architecture
Detect-To-Retrieve: Efficient Regional Aggregation for Image Search
by: Ryota Nishijima
image retrieval image search
Transferable Interactiveness Knowledge for Human-Object Interaction Detection
by: Masaki Taniguchi
HOI Detection Interactiveness Network Spatial Map
Fast Interactive Object Annotation With Curve-GCN
by: QIUYUE
Interactive Object Annotation Graph Convolutional Network
TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translation
by: shirouchi satoshi
Unsupervised image-to-image translation
FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference
by: QIUYUE
Weakly Supervised Learning Semi-supervised Learning Semantic Segmentation
Robustness via Curvature Regularization, and Vice Versa
by: Yoshihiro Fukuhara
adversarial examples adversarial training adversarial robustness geometry curvature
RVOS: End-To-End Recurrent Network for Video Object Segmentation
by: QIUYUE
Video Object Segmentation
Disentangling Latent Hands for Image Synthesis and Pose Estimation
by: Shintaro Yamamoto
hand pose estimation dientangled representation
Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition
by: Masaki Taniguchi
Skeleton-Based Action Recognition Graph Convolutional Network
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
by: Hideki Tsunashima
3D Video point cloud semantic segmentation SOTA LIDAR ScanNet Stanford 3D Indoor Spaces(S3DIS) RueMonge 2014(Varcity) Synthia 4D
3D Point Capsule Networks
by: Hiromasa Sakata
point-clouds
Towards VQA Models That Can Read
by: siida
Visual QA VQA QA multimodal
Content-Aware Multi-Level Guidance for Interactive Instance Segmentation
by: Yuta Nakamura
segmentation interactive instance segmentation superpixel FCN
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
by: Anonymous
Learning Independent Object Motion From Unlabelled Stereoscopic Videos
by: Anonymous
scene flow prediction
Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translation
by: Anonymous
Large Scale Incremental Learning
by: cfiken
Incremental Learning Catastrophic Forgetting
Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification
by: ERLYN MANGUILIMOTAN
diffusion methods re-ranking retrieval
Dissecting Person Re-Identification From the Viewpoint of Viewpoint
by: Takanori Ebihara
データセットの水増し
Viewport Proposal CNN for 360deg Video Quality Assessment
by: Shintaro Yamamoto
360° video video quality assessment
Leveraging the Invariant Side of Generative Zero-Shot Learning
by: Shuhei M Yoshida
zero-shot learning GAN soul sample regularization
P2SGrad: Refined Gradients for Optimizing Deep Face Models
by: Shintaro Yamamoto
face recognition gradient
A-CNN: Annularly Convolutional Neural Networks on Point Clouds
by: Shuhei M Yoshida
point cloud annular convolution
Amodal Instance Segmentation With KINS Dataset
by: maokura
Segmentation dataset Mask R-CNN AmodalSegmentation
Video Action Transformer Network
by: Hirokatsu Kataoka
Action Localization ActionRecognition Self-attention
MARS: Motion-Augmented RGB Stream for Action Recognition
by: Hirokatsu Kataoka
Action Recognition Video Recognition Knowledge Distillation Optical Flow
Face Anti-Spoofing: Model Matters, so Does Data
by: kubo.takahiro
Face
Fast Human Pose Estimation
by: kubo.takahiro
PoseEstimation
Learning Unsupervised Video Object Segmentation Through Visual Attention
by: Kotaro Kitayama
UVOS dataset unsupervised
Decorrelated Adversarial Learning for Age-Invariant Face Recognition
by: kubo.takahiro
Face
Segmentation-Driven 6D Object Pose Estimation
by: Kotaro Kitayama
pose-estimation
Pointing Novel Objects in Image Captioning
by: Eisuke Yamagata
novel object image captioning
VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild
by: Kotaro Kitayama
dataset VERI-Wild
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses
by: Motokawa Tetsuya
AEs
Cross-Task Weakly Supervised Learning From Instructional Videos
by: kubo.takahiro
ActionDetection
A General and Adaptive Robust Loss Function
by: Motokawa Tetsuya
Adaptive loss function
DeepFlux for Skeletons in the Wild
by: QIUYUE
Skeleton Detection
D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation
by: kubo.takahiro
ActionDetection
Progressive Teacher-Student Learning for Early Action Prediction
by: kubo.takahiro
ActionPrediction
Depth-Attentional Features for Single-Image Rain Removal
by: shirouchi satoshi
Depth-attentional Features Single-image Rain Removal
Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
by: Tenga Wakamiya
3D 物体検出
Multi-Granularity Generator for Temporal Action Proposal
by: Masaki Taniguchi
Temporal Action Proposal 行動認識
Interactive Image Segmentation via Backpropagating Refinement Scheme
by: QIUYUE
Interactive Image Segmentation
Polarimetric Camera Calibration Using an LCD Monitor
by: asato matsumoto
Calibration LCD Monitor CRF
Scene Parsing via Integrated Classification Model and Variance-Based Regularization
by: QIUYUE
Scene Parsing
RAVEN: A Dataset for Relational and Analogical Visual REasoNing
by: QIUYUE
Dataset Visual Reasoning Visual Question Answering
Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval
by: Anonymous
CrossInfoNet: Multi-Task Information Sharing Based Hand Pose Estimation
by: Tsubura Kazuki
hand pose estimation heat-map depth
Analysis of Feature Visibility in Non-Line-Of-Sight Measurements
by: Tsubura Kazuki
Non-Line-of-Sight Measurements
Learning to Cluster Faces on an Affinity Graph
by: Keita Yanome
Learning to Cluster Faces on an Affinity Graph
by: Anonymous
Spectral Metric for Dataset Complexity Assessment
by: Hideki Tsunashima
Dataset Complexity c-measure dataset reduction
Surface Reconstruction From Normals: A Robust DGP-Based Discontinuity Preservation Approach
by: QIUYUE
3D surface reconstruction surface reconstruction from normals
DARNet: Deep Active Ray Network for Building Segmentation
by: Shuhei M Yoshida
segmentation active ray DARNet
Beyond Gradient Descent for Regularized Segmentation Losses
by: Tsubura Kazuki
Gradient decent Loss Segmentation
Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
by: Sou Uchida
Domain Generalization Anti-spoofing
Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification
by: Tsubura Kazuki
GAN TripleGAN Semi-Supervised Classification Instance Synthesis
Privacy Preserving Image-Based Localization
by: QIUYUE
Image-based localization Privacy Preserving
Cascaded Generative and Discriminative Learning for Microcalcification Detection in Breast Mammograms
by: Anonymous
A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring
by: Tsubura Kazuki
blind motion deblurring Bayes inference
FilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterization
by: neka-nat
Variational Convolutional Neural Network Pruning
by: hiroki iida
Learning Metrics From Teachers: Compact Networks for Image Embedding
by: Anonymous
Metric learning network distillation
MAGSAC: Marginalizing Sample Consensus
by: Sou Uchida
Sample Consensus
Fully Automatic Video Colorization With Self-Regularization and Diversity
by: asato matsumoto
Video Colorization Self-Regularization Diversity
SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without Correspondences
by: neka-nat
Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks
by: Sou Uchida
Point Cloud Normal Estimation Unstructed Point Cloud
Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
by: neka-nat
Zoom to Learn, Learn to Zoom
by: asato matsumoto
Zoom Super-Resolution Raw sensor data sensor data
Single Image Reflection Removal Beyond Linearity
by: asato matsumoto
反射除去 Reflection Removal non-linearity synthesize
Re-Identification With Consistent Attentive Siamese Networks
by: Anonymous
Consistent Attentive Siamese Network Attention
Deep Rigid Instance Scene Flow
by: Masaki Taniguchi
Scene Flow Optical Flow Stereo
Learning to Separate Multiple Illuminants in a Single Image
by: asato matsumoto
Sparate Multiple Illuminats reflecance chromaticity shading chromaticity Separated Images
Graphonomy: Universal Human Parsing via Graph Transfer Learning
by: Shion Honda
semantic segmentation human parsing graph neural networks
Explicit Spatial Encoding for Deep Local Descriptors
by: uchi_k
Shape Unicode: A Unified Shape Representation
by: asato matsumoto
3D Shape Representaion Voxel Point Cloud Multi View Auto Encoder
Point Cloud Oversegmentation With Graph-Structured Deep Metric Learning
by: Shuhei M Yoshida
3D point cloud oversegmentation metric learning
Learning-Based Sampling for Natural Image Matting
by: maokura
ImageMatting inpainting 画像修復
Deep High-Resolution Representation Learning for Human Pose Estimation
by: yasud
Human Pose Estimation ポーズ推定 HRNet
Robust Video Stabilization by Optimization in CNN Weight Space
by: asato matsumoto
Video Stabilization Optimization CNN Weight Space Optical Flow
Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up
by: maokura
Classification fine-grained CRF CAM MaskR-CNN
Networks for Joint Affine and Non-Parametric Image Registration
by: Masaki Miyamoto
end-to-end framework medical registration vSVF affine 3D non-parametric
Learning Linear Transformations for Fast Image and Video Style Transfer
by: asato matsumoto
Style Transfer Image Video SPN data-drive
Variational Information Distillation for Knowledge Transfer
by: Tomoki Tsujimura
transfer learning distillation
Jumping Manifolds: Geometry Aware Dense Non-Rigid Structure From Motion
by: QIUYUE
Non-rigid 3D Shape Reconstruction Grassmann manifold
What Does It Mean to Learn in Deep Networks? And, How Does One Detect Adversarial Attacks?
by: Yoshihro Fukuhara
interpretability explainability generalization adversarial attack
Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
by: ERLYN MANGUILIMOTAN
unsupervised domain adaptation gcn
LVIS: A Dataset for Large Vocabulary Instance Segmentation
by: QIUYUE
Instance Segmentation Large Scale Dataset
LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking
by: QIUYUE
Single Object Tracking Large Scale Dataset
Local Detection of Stereo Occlusion Boundaries
by: asato matsumoto
Local Detection Stereo Occlusion Boundaries Small NN
Bi-Directional Cascade Network for Perceptual Edge Detection
by: asato matsumoto
Edge Detection dilated vonvoltion individual layer Bi-Directional Cascade multi-scale
C3AE: Exploring the Limits of Compact Model for Age Estimation
by: Eisuke Yamagata
age estimation
Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection
by: GOTO Keita
Action Unit Detection Regularization
Single Image Deraining: A Comprehensive Benchmark Analysis
by: asato matsumoto
De-Raining Dataset Detection Car Analysis
Aggregation Cross-Entropy for Sequence Recognition
by: Ryota Suzuki
sequence recognition
LaSO: Label-Set Operations Networks for Multi-Label Few-Shot Learning
by: Ryota Suzuki
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding
by: Hideki Tsunashima
Crowd Crowd understanding Attention SOTA ShanghaiTech dataset UCF_CC_50 dataset WorldExpo'10 dataset UCSD dataset
Ray-Space Projection Model for Light Field Camera
by: Sou Uchida
Light Field Camera Camera Calibration Plucker Coordinates
Few-Shot Learning With Localization in Realistic Settings
by: Ryota Suzuki
few-shot learning
Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections
by: asato matsumoto
ぼけ除去 Deblurring Parameter Sharing Skip Connection Dataset
Learning With Batch-Wise Optimal Transport Loss for 3D Shape Recognition
by: Hideki Tsunashima
metric learning 3D shape recognition 3D shape retreival classification MNIST CIFAR-10 SHREC13 SHREC14 ModelNet10 ModelNet40 metric
Deep Geometric Prior for Surface Reconstruction
by: Sou Uchida
Geometric Prior Point Cloud Surface Reconstruction
Weakly Supervised Person Re-Identification
by: ERLYN MANGUILIMOTAN
weakly supervised person re-id
Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing
by: maokura
SaliencyDetection MaskLearning
Scene Categorization From Contours: Medial Axis Based Salience Measures
by: Masaki Miyamoto
scene categorization CNN line classification medial-axis contour
A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations
by: Yusuke Mori
adversarial perturbations Mahalanobis-like distance radial basis function
Domain Generalization by Solving Jigsaw Puzzles
by: Kensho Hara
Domain Generalizatoin Self-supervised Learning
Pay Attention! - Robustifying a Deep Visuomotor Policy Through Task-Focused Visual Attention
by: Masaki Miyamoto
visuomotor manipulator policy TFA attention visual natural language
DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama
by: Hideki Tsunashima
single RGB panorama room rayout E2P 3D room layout.Realtor360 SOTA
AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs
by: Ryota Suzuki
domain adaptation graph
A Neural Temporal Model for Human Motion Prediction
by: yasud
Human Motion Prediction 評価指標
SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks
by: Kensho Hara
Descriptor Dense Matching
SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines
by: maokura
dataset synthetic VideoSegmentation AmodalSegmentation MaskR-CNN
ContextDesc: Local Descriptor Augmentation With Cross-Modality Context
by: Kensho Hara
Local Descriptor
Deep Exemplar-Based Video Colorization
by: shirouchi satoshi
Video Colorization
C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition
by: Kensho Hara
Open-set Recognition Auto Encoder
Creative Flow+ Dataset
by: QIUYUE
Large Scale Dataset Optical Flow Messy Stylized Content
Textured Neural Avatars
by: Kensho Hara
Renderer Graphics
Content Authentication for Neural Imaging Pipelines: End-To-End Optimization of Photo Provenance in Complex Distribution Channels
by: Takeru Suda
DLOW: Domain Flow for Adaptation and Generalization
by: Kensho Hara
Domain Adaptation Style Transfer
Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration
by: QIUYUE
Domain Adaptation Weakly Supervised Learning Open-set
3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training
by: yasud
3D Human Pose Estimation ポーズ推定 dilated convolution
Shifting More Attention to Video Salient Object Detection
by: Takeru Suda
VSOD Attention object detection video
A Neurobiological Evaluation Metric for Neural Network Model Search
by: QIUYUE
fMRI(functional Magnetic Resonance Imaging) Neuroscience
Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks
by: Tenga Wakamiya
Iterative Projection and Matching: Finding Structure-Preserving Representatives and Its Application to Computer Vision
by: QIUYUE
Data Selection Algorithm
See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks
by: Masaki Taniguchi
Unsupervised Video Object Segmentation Co-attention COSNet 被写体抽出
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
by: ERLYN MANGUILIMOTAN
3D object detection
Fitting Multiple Heterogeneous Models by Multi-Class Cascaded T-Linkage
by: Shuhei M Yoshida
model fitting T-linkage
Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
by: Keito Ishihara
Video self supervised CNN
A Late Fusion CNN for Digital Matting
by: Shuhei M Yoshida
alpha matting FCN
Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery
by: Shuhei M Yoshida
GPS 航空写真
Residual Networks for Light Field Image Super-Resolution
by: Yoitsu Takahashi
Light Field Image Super-Resolution resLF
Automatic Adaptation of Object Detectors to New Domains Using Self-Training
by: ERLYN MANGUILIMOTAN
domain adaptation self-training unsupervised
Fast Single Image Reflection Suppression via Convex Optimization
by: Anonymous
Convex Optimization
RF-Net: An End-To-End Image Matching Network Based on Receptive Field
by: Anonymous
Image Matching
Towards Real Scene Super-Resolution With Raw Images
by: Kobayashi Koga
Informative Object Annotations: Tell Me Something I Don't Know
by: Kiro Otsu
Predicting Visible Image Differences Under Varying Display Brightness and Viewing Distance
by: NSD
Image Difference
Compressing Unknown Images With Product Quantizer for Efficient Zero-Shot Classification
by: QIUYUE
Zero-Shot Learning Nearest Neighbor Search
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing
by: ERLYN MANGUILIMOTAN
Sketch-based 3D shape retrieval
Multi-Level Context Ultra-Aggregation for Stereo Matching
by: Hideki Tsunashima
stereo matching The Scene Flow datasets KITTI2015/2012 datasets PSM-Net SOTA
Self-Supervised Convolutional Subspace Clustering Network
by: QIUYUE
Self-supervised Learning Subspace Clustering
Multi-Scale Geometric Consistency Guided Multi-View Stereo
by: QIUYUE
Depth Map Estimation
Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
by: Hideki Tsunashima
semantic segmentation upsampling 1x1 convolution DUpsampling SOTA PASCAL VOC PASCAL Context Cityscapes
Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference
by: QIUYUE
Multi-view Stereo Depth Map Estimation
Hierarchical Deep Stereo Matching on High-Resolution Images
by: QIUYUE
Stereo Matching High-resolution Images
Trust Region Based Adversarial Attack on Neural Networks
by: Yusuke Mori
adversarial attack trust region
SimulCap : Single-View Human Performance Capture With Cloth Simulation
by: QIUYUE
Human Performance Capture Cloth Simulation
Metric Learning for Image Registration
by: Anonymous
registration
Isospectralization, or How to Hear Shape, Style, and Correspondence
by: Shion Honda
semantic segmentation
World From Blur
by: Anonymous
Depth Estimation Camera Pose Estimation Blur 3D reconstruction
PointPillars: Fast Encoders for Object Detection From Point Clouds
by: Akihiro Matsufuji
Point Cloud Object Detection Convolutional Neural Networks LIDAR
Deep Defocus Map Estimation Using Domain Adaptation
by: GOTO Keita
Defocus Map Estimation Domain Adaptation
Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks
by: Akihiro Matsufuji
Explicit Bias Discovery in Visual Question Answering Models
by: uchi_k
zero-shot ImageNet バイアス 半自動化
Object Detection With Location-Aware Deformable Convolution and Backward Attention Filtering
by: Tomoki Tanimura
object detection deformable convolution attention context infromation high resolution
End-To-End Efficient Representation Learning via Cascading Combinatorial Optimization
by: Yusuke Mori
quantizable representations hierarchically similarity-based search
An Alternative Deep Feature Approach to Line Level Keyword Spotting
by: Akihiro Matsufuji
Keyword Spotting Matching Convolutional Neural Networks
Representation Similarity Analysis for Efficient Task Taxonomy & Transfer Learning
by: Akihiro Matsufuji
Transfer Learning Relation Estimation
Residual Regression With Semantic Prior for Crowd Counting
by: Keito Ishihara
crowd counting
Good News, Everyone! Context Driven Entity-Aware Captioning for News Images
by: Akihiro Matsufuji
Image Captioning Convolutional Neural Networks Recurrent Neural Networks Natural Language Processing
Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation
by: Yusuke Mori
3D indoor navigation adversarial feature adaption policy mimic
Factor Graph Attention
by: kota yoshida
visual dialog attention mechanism
Learning Structure-And-Motion-Aware Rolling Shutter Correction
by: Naoya Chiba
Rolling Shutter RS SfM
SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines
by: maokura
InstanceSegmentation ActivationMap DifferentialFillingModule
Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video
by: Takeru Suda
semantic segmentation video
T-Net: Parametrizing Fully Convolutional Nets With a Single High-Order Tensor
by: Shunsuke NAKATSUKA
Tensorization Network Compression
Multi-Person Articulated Tracking With Spatial and Temporal Embeddings
by: Anonymous
pose estimation pose tracking
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
by: Takaya Yamazoe
metric learning DML triplet loss clustering
Large-Scale, Metric Structure From Motion for Unordered Light Fields
by: maokura
LightFieldCamera StructureFromMotion
3D Hand Shape and Pose Estimation From a Single RGB Image
by: Yoitsu Takahashi
3D Hand Pose Estimation Single RGB image Graph CNN
Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation
by: Mitani Tomohiro
segmentation medical image few-shot one-shot
Learning Video Representations From Correspondence Proposals
by: Keito Ishihara
video point cloud
Progressive Image Deraining Networks: A Better and Simpler Baseline
by: Keito Ishihara
ResNet RNN rain
Octree Guided CNN With Spherical Kernels for 3D Point Clouds
by: uchi_k
3D point cloud convolution deconvolution computational efficiency
Understanding the Limitations of CNN-Based Absolute Camera Pose Regression
by: maokura
VisualLocalization SfM SLAM PoseRegression
Learning to Explore Intrinsic Saliency for Stereoscopic Video
by: uchi_k
unsupervised learning 3D Generative Model
Elastic Boundary Projection for 3D Medical Image Segmentation
by: Mitani Tomohiro
3D segmentation medical image
Panoptic Segmentation
by: uchi_k
convolution spatial encoding local descriptor
Tightness-Aware Evaluation Protocol for Scene Text Detection
by: uchi_k
dataset CAD surface normal
Joint Face Detection and Facial Motion Retargeting for Multiple Faces
by: uchi_k
facial motion retargeting joint face detection
Octree Guided CNN With Spherical Kernels for 3D Point Clouds
by: uchi_k
3D point cloud spherical kernel CNN convolution
You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection
by: uchi_k
weakly-supervised object detection selective search object mining
Learning to Adapt for Stereo
by: uchi_k
streo depth estimation domain adaptation unsupervised online adaptation real-world
3D Hand Shape and Pose From Images in the Wild
by: Yoitsu Takahashi
3D Hand Pose Estimation Single RGB image E2E
Conditional Single-View Shape Generation for Multi-View Stereo Reconstruction
by: uchi_k
shape generation stereo reconstruction conditional gan
Self-Supervised 3D Hand Pose Estimation Through Training by Fitting
by: Yoitsu Takahashi
3D Hand Pose Estimation Self-supervision Depth Map
ODE-Inspired Network Design for Single Image Super-Resolution
by: Kobayashi Koga
Generative Dual Adversarial Network for Generalized Zero-Shot Learning
by: ERLYN MANGUILIMOTAN
generalized zero-shot learning GAN DualGAN
Fast Object Class Labelling via Speech
by: QIUYUE
Object Class Labelling Annotation Tool
Query-Guided End-To-End Person Search
by: ERLYN MANGUILIMOTAN
person search person re-id person detection
SFNet: Learning Object-Aware Semantic Correspondence
by: Anonymous
Deep Metric Learning Beyond Binary Supervision
by: Anonymous
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks
by: Motokawa Tetsuya
DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds
by: SohOhara
mapping registration unsupervised learning
Zero-Shot Task Transfer
by: Anonymous
Adversarial Attacks Beyond the Image Space
by: Motokawa Tetsuya
AEs CG
MUREL: Multimodal Relational Reasoning for Visual Question Answering
by: kota yoshida
VQA
Robust Histopathology Image Analysis: To Label or to Synthesize?
by: SohOhara
segmentation data augmentation histopathology image
Libra R-CNN: Towards Balanced Learning for Object Detection
by: ERLYN MANGUILIMOTAN
object detection training process imbalance
Blind Image Deblurring With Local Maximum Gradient Prior
by: kota yoshida
deblurring image prior
Image Deformation Meta-Networks for One-Shot Learning
by: SohOhara
data augmentation one-shot learning image deformation
ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features
by: Yuta Tokuoka
anomaly detection localization image forgeries anomalous feature
A Style-Based Generator Architecture for Generative Adversarial Networks
by: Motokawa Tetsuya
GAN
Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification
by: Masaki Taniguchi
Re-Identification Patch-Based 人物照合 教師なし学習
Learning a Unified Classifier Incrementally via Rebalancing
by: ERLYN MANGUILIMOTAN
incremental learning
Online High Rank Matrix Completion
by: SohOhara
matrix completion online method high rank matrix completion
From Coarse to Fine: Robust Hierarchical Localization at Large Scale
by: Katsuya Shimabukuro
Visual Localization Hierarchical Localization
Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks
by: Motokawa Tetsuya
Second-order-Optimizer Distributed
Progressive Attention Memory Network for Movie Story Question Answering
by: siida
MovieQA multimodal multi encoder multi source
The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long Videos
by: Shunsuke NAKATSUKA
Skill Determination Video Attention
Memory-Attended Recurrent Network for Video Captioning
by: siida
Video captioning Image captioning RNN multi decoder
SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
by: Masaki Taniguchi
Visual Object Tracking 物体トラッキング
A Simple Baseline for Audio-Visual Scene-Aware Dialog
by: Katsuya Shimabukuro
Audio-Visual Scene Aware Dialog Dialog Multimodal
TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes
by: Naoya Chiba
4-RoSy Semantic Segmentation Texture
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
by: siida
Visual QA VQA OOV out-of-vocabulary transfer learning unsupervised learning
CollaGAN: Collaborative GAN for Missing Image Data Imputation
by: Kyota Masuyama
GAN StarGAN CycleGAN Image imputation
Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
by: Katsuya Shimabukuro
Video Captioning
A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images
by: Naoya Chiba
Skelton 3D Reconstruction
Look Back and Predict Forward in Image Captioning
by: siida
Image Captioning context coherence RNN
Joint Manifold Diffusion for Combining Predictions on Decoupled Observations
by: Shuhei M Yoshida
manifold denoising
Generalized Zero-Shot Recognition Based on Visually Semantic Embedding
by: hiroki iida
Learning to Minify Photometric Stereo
by: Shuhei M Yoshida
photometric stereo
Noise-Tolerant Paradigm for Training Face Recognition CNNs
by: Tenga Wakamiya
顔認識
Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition
by: Tenga Wakamiya
顔認識
Text Guided Person Image Synthesis
by: Masaki Taniguchi
GAN NLP Person Image Synthesis
Reflective and Fluorescent Separation Under Narrow-Band Illumination
by: Shuhei M Yoshida
reflective and fluorescent separation
Multi-Level Multimodal Common Semantic Space for Image-Phrase Grounding
by: Katsuya Shimabukuro
Phrase Grounding Weakly Supervised Learning Multimodal
Dense Depth Posterior (DDP) From Single Image and Sparse Range
by: maokura
Depth Map KITTI Point Cloud
Intention Oriented Image Captions With Guiding Objects
by: siida
Image Captioning multimodal
Greedy Structure Learning of Hierarchical Compositional Models
by: Tenga Wakamiya
Hierarchical Compositional Models
Object-Aware Aggregation With Bidirectional Temporal Graph for Video Captioning
by: siida
Video Captioning multi encoder hiearchical attention multimodal
Feature Selective Anchor-Free Module for Single-Shot Object Detection
by: ERLYN MANGUILIMOTAN
single-shot object detection
Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition
by: Takahiro Itazuri
adversarial examples black-box attack face recognition
Visual Query Answering by Entity-Attribute Graph Matching and Reasoning
by: siida
Visual QA VQA
Single Image Depth Estimation Trained via Depth From Defocus Cues
by: Takahiro Itazuri
depth estimation depth from defocus unsupervised
RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion
by: Takahiro Itazuri
3D Semantic Scene Completion 3D Shape Completion Dimensional Decomposition Residual block
Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks
by: NSD
GAN MP-GAN
Video Summarization by Learning From Unpaired Data
by: Shunsuke NAKATSUKA
Video Summarization
Neural Scene Decomposition for Multi-Person Motion Capture
by: Takahiro Itazuri
Neural Scene Decomposition
Bottom-Up Object Detection by Grouping Extreme and Center Points
by: ERLYN MANGUILIMOTAN
object detection bottom-up approach bound box
Multi-Person Pose Estimation With Enhanced Channel-Wise and Spatial Information
by: Anonymous
multi pose estimation CSM SCARB
FA-RPN: Floating Region Proposals for Face Detection
by: Takahiro itazuri
face detection floating anchor region proposal network FA-RPN
A Bayesian Perspective on the Deep Image Prior
by: Rei Tamaru
Bayes Deep Image Prior stochastic gradient Langevin dynamics Gaussian Process
In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images
by: Eisuke Yamagata
semantic segmentation
Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning From Radiology Reports and Label Ontology
by: Mitani Tomohiro
medical image classification lesion annotation
Explainable and Explicit Visual Reasoning Over Scene Graphs
by: siida
Visual QA NMN Neural Module Networks Scene Graphs
Local Features and Visual Words Emerge in Activations
by: Katsuya Shimabukuro
Image Retrieval Local Feature Detection Local Feature Matching Reranking
Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining
by: siida
Image de-raining
Grounded Video Description
by: Ryota Suzuki
video description
Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting
by: Eisuke Yamagata
crowd counting density estimation
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes
by: GOTO Keita
Optical Flow 教師なし学習 Epipolar Geometry
Bringing Alive Blurred Moments
by: Ryota Suzuki
motion reconstruction deblurring
Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camera
by: Ryota Suzuki
event-based camera deblurring
End-To-End Projector Photometric Compensation
by: Ryota Suzuki
projector compensation projector-camera
Incremental Object Learning From Contiguous Views
by: SohOhara
incremental learning learning environment baby infants
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset
by: GOTO Keita
Single-Image Deraining Deraining
SiCloPe: Silhouette-Based Clothed People
by: yasud
3D Reconstruction Silhouette visual hull
Toward Realistic Image Compositing With Adversarial Learning
by: siida
GAN Image Compositing
Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?
by: Ryota Nishijima
binary neural network ensemble
Direct Object Recognition Without Line-Of-Sight Using Optical Coherence
by: Tenga Wakamiya
コヒーレント光 物体認識
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
by: ERLYN MANGUILIMOTAN
JPEG Compression
Unsupervised Learning of Dense Shape Correspondence
by: Naoya Chiba
Shape Deformation Mesh Deformation Functional Maps Correspondence Estimation
GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
by: Masaki Miyamoto
instance segmentation proposal 3D GSPN framework
Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh Deformation
by: Naoya Chiba
Human Shape Estimation Human Pose Estimation Mesh Deformation
Associatively Segmenting Instances and Semantics in Point Clouds
by: Masaki Miyamoto
segmentation 3D point cloud instance win-win
Streamlined Dense Video Captioning
by: QIUYUE
Dense Video Captioning
Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations
by: QIUYUE
Visual-Semantic Embedding Image Captioning Contrastive Example Mining
Cycle-Consistency for Robust Visual Question Answering
by: QIUYUE
Visual Question Answering Robustness Cycle-Consistency
Embodied Question Answering in Photorealistic Environments With Point Cloud Perception
by: QIUYUE
Embodied Question Answering Point Cloud Visual Question Answering Matterport 3D
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering
by: QIUYUE
Visual Question Answering Dataset Compositional Visual Reasoning
Variational Autoencoders Pursue PCA Directions (by Accident)
by: Kiro Otsu
LBS Autoencoder: Self-Supervised Fitting of Articulated Meshes to Point Clouds
by: yasud
autoencoder Structured Chamfer Distance self-supervised unsupervised
UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos
by: shirouchi satoshi
Unsupervised Optical-flow and Stereo-depth Estimation
Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs
by: siida
Crowd Counting CNN
Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
by: Hideki Tsunashima
semantic segmentation PASCAL VOC 2012 SOTA weakly supervised learning bounding box
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
by: Kiro Otsu
NAS semantic segmentation Neural Architecture Search
Convolutional Relational Machine for Group Activity Recognition
by: Shunsuke NAKATSUKA
Group Activity Recognition Relation
Depth From a Polarisation + RGB Stereo Pair
by: Shuhei M Yoshida
polarization image
Timeception for Complex Action Recognition
by: cfiken
Video Action Recognition
Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Search
by: Kiro Otsu
PEPSI : Fast Image Inpainting With Parallel Decoding Network
by: Katsuya Shimabukuro
Inpainting Coarse-to-Fine
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
by: Kiro Otsu
NAS AutoML edge AI
Exploiting Temporal Context for 3D Human Pose Estimation in the Wild
by: mokura
Pose Estimation 3D Pose Video bundle adjustment
Hybrid Scene Compression for Visual Localization
by: Shuhei M Yoshida
MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction
by: Shuhei M Yoshida
face reconstruction
Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction
by: Anonymous
depth prediction make3d
Semantic Graph Convolutional Networks for 3D Human Pose Regression
by: mokura
Graph Convolutional Network 3D Pose Estimation Regression
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
by: Yoshitaka Ushiku
Two Body Problem: Collaborative Visual Task Completion
by: QIUYUE
Vision-Language Navigation Embodied Two Agents Collaboration
Text2Scene: Generating Compositional Scenes From Textual Descriptions
by: QIUYUE
Image Generation from Text Sequence-to-Sequence
Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation
by: QIUYUE
Vision-Language Navigation (VLN)
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds
by: Hideki Tsunashima
point cloud scene flow SLAM LIDAR Bilateral Convolutional Layers permutohedral lattice FlyingThings3D KITTI Cene Flow 2015
Actor-Critic Instance Segmentation
by: siida
Instance Segmentation reinforcement learning
Robust Subspace Clustering With Independent and Piecewise Identically Distributed Noise Modeling
by: takeshi miura
RobustSC I.p.i.d
Interactive Full Image Segmentation by Considering All Regions Jointly
by: Anonymous
segmentation interactive segmentation
Group-Wise Correlation Stereo Network
by: mokura
Stereo Maching PSMNet Depth Prediction
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
by: Masaki Taniguchi
GAN Image Attribute Editing 画像変換
Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior
by: shirouchi satoshi
Hyperspectral Image Reconstruction
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
by: QIUYUE
Meta Learning Reinforcement Learning Visual Navigation
Dense Intrinsic Appearance Flow for Human Pose Transfer
by: Masaki Taniguchi
Human Pose Transfer GAN
GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matrices
by: Hideki Tsunashima
SfM algebra SOTA
Improving Semantic Segmentation via Video Propagation and Label Relaxation
by: Takeru Suda
Semantic segmentation video Label Relaxation data augmentation
Depth-Aware Video Frame Interpolation
by: Masaki Taniguchi
Video Frame Interpolation フレーム補完
Towards Instance-Level Image-To-Image Translation
by: Masaki Taniguchi
Image-To-Image Translation 画像ドメイン変換
Graph Convolutional Tracking
by: Naoya Chiba
Tracking Graph Convolution
LiFF: Light Field Features in Scale and Depth
by: shirouchi satoshi
Light Field Features
PoseFix: Model-Agnostic General Human Pose Refinement Network
by: Takahiro Itazuri
pose estimation pose refinement
Face-Focused Cross-Stream Network for Deception Detection in Videos
by: Takahiro Itazuri
automated deception detection cross-stream network
Fast and Robust Multi-Person 3D Pose Estimation From Multiple Views
by: Takahiro Itazuri
3D pose estimation
Learning to Explore Intrinsic Saliency for Stereoscopic Video
by: Tomoki Tanimura
saliency detection stereoscopic video dataset spatio-temporal depth
BASNet: Boundary-Aware Salient Object Detection
by: Anonymous
Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech
by: Katsuya Shimabukuro
Image Captioning POS-tag
Learning a Deep ConvNet for Multi-Label Classification With Partial Labels
by: Shuhei M Yoshida
partial labels multi-label problem
Scan2Mesh: From Unstructured Range Scans to 3D Meshes
by: Anonymous
graph neural networks tsdf
Triangulation Learning Network: From Monocular to Stereo 3D Object Detection
by: Shion Honda
object detection 3D
Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on N-Spheres
by: Takuma Yagi
regression viewpoint estimation surface normal estimation 3d rotation estimation.n-sphere
DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image
by: mokura
depth prediction LiDAR attention
Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment
by: Yuta Tokuoka
3D scan alignment registration
Deep Video Inpainting
by: rindybell
画像修復 動画修復 CNN DNN 修復
Foreground-Aware Image Inpainting
by: rindybell
画像修復 輪郭抽出 前景
Learning Non-Volumetric Depth Fusion Using Successive Reprojections
by: Anonymous
DynTypo: Example-Based Dynamic Text Effects Transfer
by: rindybell
スタイルトランスファー PatchMatch フォント
Stereo R-CNN Based 3D Object Detection for Autonomous Driving
by: Anonymous
Coloring With Limited Data: Few-Shot Colorization via Memory Augmented Networks
by: yasud
few-shot learning 自動着色 colorization memory network
GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation
by: Takehiko Ohkawa
Domain Adaptation Graph Convolution
Deep ChArUco: Dark ChArUco Marker Pose Estimation
by: Takehiko Ohkawa
ChArUco Detection Pose Estimation
On Finding Gray Pixels
by: shirouchi satoshi
grayness index
IM-Net for High Resolution Video Frame Interpolation
by: Kensho Hara
Video Frame Interpolation
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
by: Daiki Kimura
ネットワーク探索
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
by: Naoya Chiba
Mesh Regression Human Shape Estimation Human Pose Graph CNN
VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People
by: Kensho Hara
Privacy
GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching
by: Naoya Chiba
Local Reference Frame 3D Descriptor
R2GAN: Cross-Modal Recipe Retrieval With Generative Adversarial Network
by: Yukitaka Tsuchiya
GAN cross-modal retrieval
3D Shape Reconstruction From Images in the Frequency Domain
by: Naoya Chiba
3D Reconstruction Thickness Map Voxel
Neural RGB(r)D Sensing: Depth and Uncertainty From a Video Camera
by: Takuma Yagi
monocular depth estimation uncertainty bayesian filtering
Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data
by: Takahiro Itazuri
face recognition
Learning the Depths of Moving People by Watching Frozen People
by: Takuma Yagi
deoth estimation motion parallax moving people multi-view stereo
Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions
by: Takuma Yagi
trajectory prediction driving behavior
Sphere Generative Adversarial Network Based on Geometric Moment Matching
by: Motokawa Tetsuya
GAN
Probabilistic End-To-End Noise Correction for Learning With Noisy Labels
by: Shuhei M Yoshida
noisy labels label correction
Parallel Optimal Transport GAN
by: Motokawa Tetsuya
GAN
PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing
by: Anonymous
kNN point cloud
Cross Domain Model Compression by Structurally Weight Sharing
by: Kiro Otsu
Network compression graph embedding weight sharing
From Recognition to Cognition: Visual Commonsense Reasoning
by: QIUYUE
Commonsense Reasoning Visual Question Answering
FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
by: Ryota Natsume
Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling
by: Hideki Tsunashima
point cloud ModelNet40 Stanford Large-Scale 3D Indoor Spaces Dataset(S3DIS) DVS128 Gesture Dataset PAT GSA subset sampling PointCNN DGCNN
Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation
by: Keito Ishihara
cross-task
Connecting the Dots: Learning Representations for Active Monocular Depth Estimation
by: Shion Honda
depth estimation monocular camera photometry geometry
Devil Is in the Edges: Learning Semantic Boundaries From Noisy Annotations
by: Yukitaka Tsuchiya
semantic boundary segmentation
Radial Distortion Triangulation
by: Tomoki Tanimura
radial distortion triangulation grobner basis optimization
A Theory of Fermat Paths for Non-Line-Of-Sight Shape Reconstruction
by: Ryota Suzuki
Non-Line-of-Sight reconstruction transient measurement
SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks
by: Naoya Chiba
Visual Tracking Shamese Network Cross Correlation
Steady-State Non-Line-Of-Sight Imaging
by: Ryota Suzuki
Non-Light-of-Sight
Acoustic Non-Line-Of-Sight Imaging
by: Ryota Suzuki
Non-Line-of-Sight acoustic imaging
Less Is More: Learning Highlight Detection From Video Duration
by: Mitani Tomohiro
video highlight highlight detection FAIR weak supervised learning
Deeper and Wider Siamese Networks for Real-Time Visual Tracking
by: Naoya Chiba
Siamese Tracker Visual Tracking
Learning Transformation Synchronization
by: shirouchi satoshi
Transformation Synchronization
Mutual Learning of Complementary Networks via Residual Correction for Improving Semi-Supervised Classification
by: Shuhei M Yoshida
semi-supervised learning mutual learning
Pixel-Adaptive Convolutional Neural Networks
by: Yoshiki
Adaptive filtering Dynamic Filter Networks Upsampling Conditional random field
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
by: Yoshiki
Optical flow Occlusion estimation Iterative refinement
An End-To-End Network for Panoptic Segmentation
by: Ryuta Shitomi
Panoptic Segmentation Semantic Segmentation
Recursive Visual Attention in Visual Dialog
by: Ryota Natsume
Reasoning Visual Dialogs With Structural and Partial Observations
by: Ryota Natsume
Adversarial Inference for Multi-Sentence Video Description
by: Ryota Natsume
Generalising Fine-Grained Sketch-Based Image Retrieval
by: yasud
FG-SBIR
Actively Seeking and Learning From Live Data
by: QIUYUE
Visual Question Answering Meta Learning
The Regretful Agent: Heuristic-Aided Navigation Through Progress Estimation
by: QIUYUE
Vision-Language Navigation Self-monitoring Mechanism
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters
by: Naoya Chiba
Visual Tracking Correlation Filter ADMM
SelFlow: Self-Supervised Learning of Optical Flow
by: Naoya Chiba
Optical Flow Semi-supervised Occlusion
EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching From Scratch
by: Kiro Otsu
NAS genetic approach 遺伝的アルゴリズム automl
MnasNet: Platform-Aware Neural Architecture Search for Mobile
by: Kiro Otsu
NAS AutoML Edge AI
Iterative Residual CNNs for Burst Photography Applications
by: Anonymous
cnn burst photography
Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering
by: Keito Ishihara
VQA attention
Learning to Compose Dynamic Tree Structures for Visual Contexts
by: QIUYUE
Visual Reasoning Scene Graph Generation Visual Question Answering
Bounding Box Regression With Uncertainty for Accurate Object Detection
by: Shuhei M Yoshida
object detection uncertainty
ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation
by: Yusuke Mori
platform-aware model adaptation adaptive genetic algorithm accuracy latency energy consumption
Regularizing Activation Distribution for Training Binarized Deep Networks
by: Yusuke Mori
Binarized Neural Network Activation Distribution Degeneration Saturation Gradient Mismatch
Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem
by: Shuhei M Yoshida
theory ReLU adversarial training
Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields
by: Naoya Chiba
Pose Estimation Part Affinity Field Human Pose Estimation
Selective Sensor Fusion for Neural Visual-Inertial Odometry
by: Takaya Yamazoe
Sensor VIO robust
2.5D Visual Sound
by: cfiken
2.5D Visual Sound audio visual source separation generating sound
Fast Spatio-Temporal Residual Network for Video Super-Resolution
by: Takaya Yamazoe
Super Resolution Video Residual Skip Connection
On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions
by: Shuhei M Yoshida
adversarial examples universal adversarial perturbations
Fast Spatio-Temporal Residual Network for Video Super-Resolution
by: Takaya Yamazoe
CT MAR Reconstruction Dual Domain Medical
Self-Supervised Representation Learning by Rotation Feature Decoupling
by: Takaya Yamazoe
Self supervised Rotation Representation Learning
Learning Implicit Fields for Generative Shape Modeling
by: Anonymous
gan 3d
Learning Spatial Common Sense With Geometry-Aware Recurrent Networks
by: QIUYUE
3D CNN mobile visual scene understanding
The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation
by: Yuta Nakamura
2D-3D correspondence position orientation cross-modality 3D model mixture model
Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
by: Katsuya Shimabukuro
Visual Explanation Response-Based Visual Explanation Fine-Grained recognition Multi-Task Learning
Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing
by: kota yoshida
Referring Expression attention
Multi-Source Weak Supervision for Saliency Detection
by: roy29fuku
saliency detection weak supervision
APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs
by: Katsuya Shimabukuro
GAN Hierarchical GANs Portrait Drawings Face Photos
Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval
by: kota yoshida
Visual-semantic embedding
Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking
by: Naoya Chiba
Multiple Object Tracking MOT
Progressive Pose Attention Transfer for Person Image Generation
by: Kyota Masuyama
GAN Pose-Transfer Attention
Striking the Right Balance With Uncertainty
by: cfiken
Class Imbalanced Bayesian Uncertainty Estimates
WarpGAN: Automatic Caricature Generation
by: Katsuya Shimabukuro
GAN Style Transfer Caricature Warping
Deep Transfer Learning for Multiple Class Novelty Detection
by: Yuta Nakamura
novelty detection loss function transfer learning fine-tuning
Skeleton-Based Action Recognition With Directed Graph Neural Networks
by: Shunsuke NAKATSUKA
Action Recognition Graph Graph Convolution
An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection
by: rindybell
物体検出 顕著的物体検出
Graphical Contrastive Losses for Scene Graph Parsing
by: Yuta Nakamura
scene graph parsing loss function graph semantic relationship
Label-Noise Robust Generative Adversarial Networks
by: Kensho Hara
GAN Label Noise
Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation
by: Kensho Hara
Image-to-Image Translation
Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss
by: Naoya Chiba
Quantization low bit
Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection
by: Naoya Chiba
Semantic Segmentation Transfer Learning
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
by: cfiken
BNN Binary Neural Networks Structure approximation
Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope
by: Yukitaka Tsuchiya
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
by: Anonymous
depth estimation camera parameter
Robustness Verification of Classification Deep Neural Networks via Linear Programming
by: Yusuke Mori
classification deep neural networks linear programming robustness verification sigmoid
Rob-GAN: Generator, Discriminator, and Adversarial Attacker
by: Yukitaka Tsuchiya
GAN Adversarial training
StereoDRNet: Dilated Residual StereoNet
by: Anonymous
3D reconstruction passive stereo image depth estimation 3d KITTI
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
by: Shuhei M Yoshida
face recognition metric leanring additive angular margin loss
Blind Visual Motif Removal From a Single Image
by: Katsuya Shimabukuro
Inpainting Blind Inpainting Motif Removal
Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
by: Anonymous
zero shot zero-shot generalized zero-shot learning
Progressive Ensemble Networks for Zero-Shot Recognition
by: Anonymous
zero-shot progressive ensemble
Volumetric Capture of Humans With a Single RGBD Camera via Semi-Parametric Learning
by: Yuta Tokuoka
image rendering RGBD image volumetric capture
Rethinking Knowledge Graph Propagation for Zero-Shot Learning
by: Anonymous
zero-shot learning graph convolution
ATOM: Accurate Tracking by Overlap Maximization
by: Naoya Chiba
Visual Tracking Bounding Box
Robustness of 3D Deep Learning in an Adversarial Setting
by: OKIMOTO Yusuke
Conditional Adversarial Generative Flow for Controllable Image Synthesis
by: shirouchi satoshi
Conditional Adversarial Generative Flow
Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation
by: Ruka Funaki
scene text detection
Shapes and Context: In-The-Wild Image Synthesis & Manipulation
by: Kensho Hara
Image Synthesis
Learning Joint Gait Representation via Quintuplet Loss Minimization
by: Naoya Chiba
Gait Recognition Metric Learning Quintuplet Loss
Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification
by: Ryosuke Sato
Few-ShotLearning ImageClassification ReinforcementLearning Q-Learning
Context-Aware Crowd Counting
by: Ryota Nishijima
crowd counting density map
Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach
by: Kotaro Kitayama
A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes
by: Ryuta Shitomi
Semantic Segmentation
SceneCode: Monocular Dense Semantic Reconstruction Using Learned Encoded Scene Representations
by: Yuta Nakamura
SLAM semantic segmentation 3D CodeSLAM monocular dense reconstruction
Task Agnostic Meta-Learning for Few-Shot Learning
by: Anonymous
meta learning few-shot learninng MAML
RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
by: Takahiro Itazuri
3D Pose Estimation Reproject Error
Re-Identification Supervised Texture Generation
by: Anonymous
re-identification texture generation 3D human pose SMPL
GeoNet: Deep Geodesic Networks for Point Cloud Analysis
by: Satoshi Inose
PointNet PU-Net geodesic neighborhood
PoseFix: Model-Agnostic General Human Pose Refinement Network
by: Takahiro Itazuri
3D Face Shape Estimation RingNet
Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples
by: Masahito Kumada
RaCNN Local Mixup adversarial examples
QATM: Quality-Aware Template Matching for Deep Learning
by: Yuta Nakamura
template matching semantic image alignment image-to-GPS
Latent Space Autoregression for Novelty Detection
by: Shunsuke NAKATSUKA
Anomaly Detection Autoregression Autoencoder
Guaranteed Matrix Completion Under Multiple Linear Transformations
by: Yukitaka Tsuchiya
LRMC
A Poisson-Gaussian Denoising Dataset With Real Fluorescence Microscopy Images
by: Yuta Nakamura
denoising Poisson-Gaussian noise dataset biology microscope
CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark
by: Anonymous
Multi-person pose estimation Crowd Pose Crowd Index JC SPPE
ROI Pooled Correlation Filters for Visual Tracking
by: Anonymous
ROI correlation filter
Data-Driven Neuron Allocation for Scale Aggregation Networks
by: Anonymous
multi scale convolutional neural network image classification object detection
Exploiting Edge Features for Graph Neural Networks
by: Tomoki Tsujimura
graph neural network
Neural Illumination: Lighting Prediction for Indoor Environments
by: Satoshi Inose
geometry estimation scene completion LDR to HDR U-Net ResNet50
Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology
by: Anonymous
病理学 セマンティックセグメンテーション
Auto-Encoding Scene Graphs for Image Captioning
by: Anonymous
Scene Graph Auto-Encoder Image Captioning
Visual Question Answering as Reading Comprehension
by: Katsuya Shimabukuro
Visual Question Answering Machine Reading Comprehension
Knowledge Distillation via Instance Relationship Graph
by: Satoshi Inose
knowledge distillation teacher-student framework
Deeply-Supervised Knowledge Synergy
by: Satoshi Inose
deeply-supervised learning knowladge distillation
Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval
by: Koki Obinata
sketch-based image retrieval zero-shot cycle-consistency
Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
by: Motokawa Tetsuya
DomainAdaption UDA
Transferrable Prototypical Networks for Unsupervised Domain Adaptation
by: Kensho Hara
Unsupervised Domain Adaptation
Label Propagation for Deep Semi-Supervised Learning
by: Koki Obinata
semi-supervised learning transductive learning
Balanced Self-Paced Learning for Generative Adversarial Clustering Network
by: Motokawa Tetsuya
GAN ClusterGAN
Balanced Self-Paced Learning for Generative Adversarial Clustering Network
by: Motokawa Tetsuya
GAN ClusterGAN
K-Nearest Neighbors Hashing
by: mokura
ANN search hashing entropy
Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning
by: Koki Obinata
adversarial learning data augmentation handwritten word recognition handwritten word spotting
Meta-Transfer Learning for Few-Shot Learning
by: cfiken
Few-Shot Learning Meta Learning Transfer Learning
Contrastive Adaptation Network for Unsupervised Domain Adaptation
by: Koki Obinata
unsupervised domain adaptation unsupervised learning
STEP: Spatio-Temporal Progressive Learning for Video Action Detection
by: Shuhei M Yoshida
action localization