ICCV2021論文サマリ

Spatial-Temporal Transformer for Dynamic Scene Graph Generation

by: QIU YUE

Learning Spatio-Temporal Transformer for Visual Tracking

by: QIU YUE

Object detection Video

HiFT: Hierarchical Feature Transformer for Aerial Tracking

by: QIU YUE

Object detection Video

High-Performance Discriminative Tracking With Transformers

by: QIU YUE

Object detection Video

KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPs

by: Naoya Chiba

3D Self supervised learning

Gradient Normalization for Generative Adversarial Networks

by: Hiroki Kobayashi

GAN Normalization

Divide-and-Assemble: Learning Block-Wise Memory for Unsupervised Anomaly Detection

by: Hiroki Kobayashi

Anomaly detection Unsupervised learning Memory module

DRAEM - A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection

by: Hiroki Kobayashi

Anomaly detection Anomaly localization

MDETR - Modulated Detection for End-to-End Multi-Modal Understanding

by: 飯田啄巳

Object detection Vision and language

A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection

by: Hiroki Kobayashi

Anomaly detection Anomaly localization Few-shot learning

Detector-Free Weakly Supervised Grounding by Separation

by: 飯田啄巳

Vision and language

Learning Unsupervised Metaformer for Anomaly Detection

by: Hiroki Kobayashi

Meta learning Anomaly detection Anomaly localization

CTRL-C: Camera Calibration TRansformer With Line-Classification

by: shoji sonoyama

Multi modal Segmentation camera calibration

FastNeRF: High-Fidelity Neural Rendering at 200FPS

by: Naoya Chiba

3D Self supervised learning

Query Adaptive Few-Shot Object Detection With Heterogeneous Graph Convolutional Networks

by: 日坂　幸次

Object detection

Benchmark Platform for Ultra-Fine-Grained Visual Categorization Beyond Human Performance

by: 日坂　幸次

Nerfies: Deformable Neural Radiance Fields

by: Naoya Chiba

Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-Point

by: K. Nakata

SmartShadow: Artistic Shadow Drawing Tool for Line Drawings

by: Yosuke Shinya

image synthesis shadow

Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding

by: SY

Object detection Recognition Transformer Network architecture

CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

by: SY

Recognition Transformer Network architecture

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

by: Naoya Chiba

BV-Person: A Large-Scale Dataset for Bird-View Person Re-Identification

by: Masanori YANO

Attention Dataset Person re-identification

Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis

by: Naoya Chiba

3D Representation learning

Exploring Cross-Image Pixel Contrast for Semantic Segmentation

by: 飯田啄巳

Segmentation Semantic segmentation Self supervised learning

Omni-GAN: On the Secrets of cGANs and Beyond

by: Teppei Kurita

Improving Low-Precision Network Quantization via Bin Regularization

by: K. Nakata

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

by: Masanori YANO

Autonomous driving Reinforcement learning Imitation Learning

Self-Supervised Product Quantization for Deep Unsupervised Image Retrieval

by: Masaki Inaba

Self supervised learning Image Retrieval

Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization

by: K. Nakata

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions

by: Akihiro FUJII

Object detection Recognition

Sketch Your Own GAN

by: Akihiro FUJII

UniT: Multimodal Multitask Learning With a Unified Transformer

by: Akihiro FUJII

Multi modal Object detection Segmentation Vision and language

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

by: Akihiro FUJII

Object detection Semantic segmentation

Vision Transformers for Dense Prediction

by: Akihiro FUJII

Depth estimation Segmentation

3D Shape Generation and Completion Through Point-Voxel Diffusion

by: Naoki Wada

3D Point cloud Generative Model Diffusion Model

GNeRF: GAN-Based Neural Radiance Field Without Posed Camera

by: Naoya Chiba

3D GAN Pose estimation Self supervised learning

Parametric Contrastive Learning

by: Masanori YANO

Recognition Contrastive learning

Pixel-Perfect Structure-From-Motion With Featuremetric Refinement

by: shoji sonoyama

3D reconstruction Depth estimation Pose estimation Structure from Motion

OpenGAN: Open-Set Recognition via Open Data Generation

by: Anonymous

GAN Open-set recognition

DetCo: Unsupervised Contrastive Learning for Object Detection

by: 渡部海/(Watabe Kai)

Object detection Self supervised learning

AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition

by: eikai

Action recognition

CodeNeRF: Disentangled Neural Radiance Fields for Object Categories

by: Naoya Chiba

3D Disentanglement Pose estimation

Hyperspectral Image Denoising With Realistic Data

by: Hiroki Okawa

Dataset Hyperspectral Denoising

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification

by: 日坂　幸次

Selective Feature Compression for Efficient Activity Recognition Inference

by: 日坂　幸次

Action recognition Recognition

Interpretable Image Recognition by Constructing Transparent Embedding Space

by: 日坂　幸次

Pyramid Point Cloud Transformer for Large-Scale Place Recognition

by: 日坂　幸次

Gait Recognition in the Wild: A Benchmark

by: 日坂　幸次

TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition

by: 日坂　幸次

Learning Canonical 3D Object Representation for Fine-Grained Recognition

by: 日坂　幸次

Class-Incremental Learning for Action Recognition in Videos

by: 日坂　幸次

Multi-Modal Multi-Action Video Recognition

by: 日坂　幸次

Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition

by: 日坂　幸次

Matching in the Dark: A Dataset for Matching Image Pairs of Low-Light Scenes

by: Masanori YANO

Dataset Image matching

Visual Scene Graphs for Audio Source Separation

by: Yoshiki Masuyama

Multi modal Self supervised learning

Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models

by: SY

Dataset Robustness Vision and language VQA

Contrast and Classify: Training Robust VQA Models

by: SY

Vision and language VQA

Face Image Retrieval With Attribute Manipulation

by: Masaki Inaba

Disentanglement GAN Image Retrieval

Few-Shot Semantic Segmentation With Cyclic Memory Network

by: Masanori YANO

N-shot learning Semantic segmentation Memory network

3DIAS: 3D Shape Reconstruction With Implicit Algebraic Surfaces

by: Naoya Chiba

3D 3D reconstruction Representation learning Semantic segmentation

Adaptive Focus for Efficient Video Recognition

by: 日坂　幸次

AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition

by: 日坂　幸次

StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery

by: Akihiro FUJII

GAN Vision and language

Hybrid Neural Fusion for Full-Frame Video Stabilization

by: Ryoto Matsuba

Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos

by: Yoshiki Masuyama

Multi modal Vision and language

SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition

by: 日坂　幸次

Distilling Virtual Examples for Long-Tailed Recognition

by: 日坂　幸次

Self-Mutual Distillation Learning for Continuous Sign Language Recognition

by: 日坂　幸次

Learning Canonical View Representation for 3D Shape Recognition With Arbitrary Views

by: 日坂　幸次

ID-Reveal: Identity-Aware DeepFake Video Detection

by: 日坂　幸次

Object detection

MicroNet: Improving Image Recognition With Extremely Low FLOPs

by: shoji sonoyama

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals

by: Masanori YANO

Semantic segmentation Unsupervised learning Contrastive learning Transfer learning Semi-supervised learning

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

by: Naoya Chiba

3D 3D reconstruction Depth estimation

Trash To Treasure: Harvesting OOD Data With Cross-Modal Matching for Open-Set Semi-Supervised Learning

by: Anonymous

Self supervised learning Semi-supervised learning

Multiresolution Deep Implicit Functions for 3D Shape Representation

by: Naoya Chiba

3D 3D reconstruction Point cloud

Dissecting Image Crops

by: Masanori YANO

Recognition Self supervised learning

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models

by: Naoki Wada

Diffusion model image transfer

Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval With Partial Query

by: SY

Multi modal Vision and language Retrieval

MVSNeRF: Fast Generalizable Radiance Field Reconstruction From Multi-View Stereo

by: Naoya Chiba

3D 3D reconstruction Depth estimation

Searching for Controllable Image Restoration Networks

by: Masanori YANO

Neural architecture search(NAS) Image restoration Denoising Deblurring

Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing

by: Naoya Chiba

3D 3D reconstruction Disentanglement

Video Autoencoder: Self-Supervised Disentanglement of Static 3D Structure and Motion

by: 松葉亮人

3D 3D reconstruction Disentanglement Video

SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes

by: Naoya Chiba

3D 3D reconstruction

Rethinking Coarse-To-Fine Approach in Single Image Deblurring

by: Masanori YANO

Deblurring U-Net

Preservational Learning Improves Self-Supervised Medical Image Models by Reconstructing Diverse Contexts

by: Shunsuke Yoshizawa

Segmentation Contrastive learning

Cross-Encoder for Unsupervised Gaze Representation Learning

by: Hiroki Nakamura

Representation learning Self supervised learning gaze estimation

Neural Strokes: Stylized Line Drawing of 3D Shapes

by: Yosuke Shinya

3D GAN image synthesis

Transparent Object Tracking Benchmark

by: Masanori YANO

Dataset Recognition Object tracking

Learning To Bundle-Adjust: A Graph Network Approach to Faster Optimization of Bundle Adjustment for Vehicular SLAM

by: shoji sonoyama

Pose estimation SLAM

Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks

by: Anonymous

Adversarial examples GAN Self supervised learning Facial landmark detection

Learning Facial Representations From the Cycle-Consistency of Face

by: Anonymous

Disentanglement Optical flow Representation learning Face recognition

Score-Based Point Cloud Denoising

by: Naoya Chiba

3D Point cloud Self supervised learning

A Robust Loss for Point Cloud Registration

by: Naoya Chiba

3D Point cloud Pose estimation Self supervised learning

Transfusion: A Novel SLAM Method Focused on Transparent Objects

by: Masanori YANO

3D 3D reconstruction Segmentation SLAM

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation

by: Naoya Chiba

3D 3D reconstruction Disentanglement Pose estimation

Big Self-Supervised Models Advance Medical Image Classification

by: Akihiro FUJII

Self supervised learning

An End-to-End Transformer Model for 3D Object Detection

by: Akihiro FUJII

3D 3D object detection Object detection

Segmenter: Transformer for Semantic Segmentation

by: Masanori YANO

Semantic segmentation

AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds

by: Naoya Chiba

Single-Shot Hyperspectral-Depth Imaging With Learned Diffractive Optics

by: Hiroki Okawa

Dataset Depth estimation Hyperspectral Diffractive Optics

VariTex: Variational Neural Face Textures

by: hayamizu ryo

T-AutoML: Automated Machine Learning for Lesion Segmentation Using Transformers in 3D Medical Imaging

by: Ryuichi Nakahara

3D Segmentation

Point-Set Distances for Learning Representations of 3D Point Clouds

by: Naoya Chiba

3D 3D reconstruction Point cloud Representation learning

Distillation-Guided Image Inpainting

by: Masanori YANO

Image inpainting Distillation

Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity

by: Hiroki Nakamura

3D Action recognition Representation learning Self supervised learning

CANet: A Context-Aware Network for Shadow Removal

by: Masanori YANO

Shadow removal Deraining Image translation

A Backdoor Attack Against 3D Point Cloud Classifiers

by: Naoya Chiba

3D Adversarial examples Point cloud

Deep Edge-Aware Interactive Colorization Against Color-Bleeding Effects

by: yasud

GAN Sketch Colorization

Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone

by: hayamizu ryo

3D Dataset Pose estimation

Deep Virtual Markers for Articulated 3D Shapes

by: Anonymous

3D 3D object detection 3D reconstruction

Topologically Consistent Multi-View Face Inference Using Volumetric Sampling

by: hayamizu ryo

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer

by: Naoya Chiba

Image Harmonization With Transformer

by: Masanori YANO

Image harmonization Image composition

LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving

by: Masanori YANO

Object detection Autonomous driving Self-driving GNN VAE

Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis

by: Yosuke Shinya

Depth estimation GAN Multi modal

Scaling-Up Disentanglement for Image Translation

by: Masanori YANO

Disentanglement GAN Image translation

GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal Transformer

by: Chihiro Nakatani

Action recognition Recognition Video Group activity recognition

PARE: Part Attention Regressor for 3D Human Body Estimation

by: hayamizu ryo

Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic Segmentation

by: Naoya Chiba

3D Point cloud Representation learning Segmentation Semantic segmentation

SynFace: Face Recognition With Synthetic Data

by: Masanori YANO

Recognition Synthetic data Mixup

DOLG: Single-Stage Image Retrieval With Deep Orthogonal Fusion of Local and Global Features

by: Takayuki Semitsu

Disentanglement Representation learning

Disentangled Representation for Age-Invariant Face Recognition: A Mutual Information Minimization Perspective

by: Anonymous

Disentanglement Recognition Robustness Face recognition

Learn To Cluster Faces via Pairwise Classification

by: Anonymous

Recognition Face clustering

GAN-Control: Explicitly Controllable GANs

by: Anonymous

Disentanglement GAN

Road Anomaly Detection by Partial Image Reconstruction With Segmentation Coupling

by: Masanori YANO

Semantic segmentation Anomaly detection

Vis2Mesh: Efficient Mesh Reconstruction From Unstructured Point Clouds of Large Scenes With Learned Virtual View Visibility

by: Naoya Chiba

3D 3D reconstruction Depth estimation Point cloud

Persistent Homology Based Graph Convolution Network for Fine-Grained 3D Shape Segmentation

by: Anonymous

3D 3D reconstruction GAN Segmentation Semantic segmentation

MeshTalk: 3D Face Animation From Speech Using Cross-Modality Disentanglement

by: 松澤郁哉

3D 3D reconstruction Disentanglement Multi modal

Orthogonal Projection Loss

by: Masanori YANO

SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix

by: Naoya Chiba

CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification

by: Anonymous

Neural architecture search(NAS) Object detection Person re-identification Recognition

UltraPose: Synthesizing Dense Pose With 1 Billion Points by Human-Body Decoupling 3D Model

by: hayamizu ryo

3D Dataset Pose estimation

SemIE: Semantically-Aware Image Extrapolation

by: Masanori YANO

GAN Image extrapolation Outpainting

PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds

by: Naoya Chiba

3D Attetion Point cloud Pose estimation

Full-Body Motion From a Single Head-Mounted Device: Generating SMPL Poses From Partial Observations

by: hayamizu ryo

Social Fabric: Tubelet Compositions for Video Relation Detection

by: Kensho Hara

3D Human Texture Estimation From a Single Image With Transformers

by: Anonymous

3D Segmentation

ViViT: A Video Vision Transformer

by: Kensho Hara

Action recognition Video

Unsupervised Point Cloud Pre-Training via Occlusion Completion

by: Naoya Chiba

3D 3D object detection Point cloud Representation learning Self supervised learning

Learning To Resize Images for Computer Vision Tasks

by: Masanori YANO

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

by: Naoya Chiba

Distance-Aware Quantization

by: K. Nakata

Move2Hear: Active Audio-Visual Source Separation

by: Masuyama Yoshiki

Describing and Localizing Multiple Changes With Transformers

by: Masanori YANO

Dataset Vision and language VQA

iMAP: Implicit Mapping and Positioning in Real-Time

by: shoji sonoyama

ME-PCN: Point Completion Conditioned on Mask Emptiness

by: Naoya Chiba

3D 3D reconstruction Point cloud

How To Train Neural Networks for Flare Removal

by: Masanori YANO

Image translation Flare removal U-Net

Learning To Adversarially Blur Visual Object Tracking

by: Anonymous

Dataset GAN object tracking

CrackFormer: Transformer Network for Fine-Grained Crack Detection

by: 近藤佑樹 (Yuki Kondo)

Segmentation Semantic segmentation Transformer Crack Segmentation

Adaptive Label Noise Cleaning With Meta-Supervision for Deep Face Recognition

by: Anonymous

Domain adaptation Meta learning Recognition Self supervised learning Face Recognition

Light Source Guided Single-Image Flare Removal From Unpaired Data

by: Masanori YANO

Dataset GAN Image translation Flare removal

ELLIPSDF: Joint Object Pose and Shape Optimization With a Bi-Level Ellipsoid and Signed Distance Function Description

by: Naoya Chiba

3D 3D object detection 3D reconstruction Point cloud Pose estimation

Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

by: Naoya Chiba

Env-QA: A Video Question Answering Benchmark for Comprehensive Understanding of Dynamic Environments

by: SY

Dataset Video Vision and language

Localize to Binauralize: Audio Spatialization From Visual Sound Source Localization

by: Yoshiki Masuyama

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving

by: Lei Xu

3D object detection Point cloud Self supervised learning Motion and Tracking Self-driving

SSH: A Self-Supervised Framework for Image Harmonization

by: Masanori YANO

Self supervised learning Image harmonization Image composition

HRegNet: A Hierarchical Network for Large-Scale Outdoor LiDAR Point Cloud Registration

by: Naoya Chiba

3D Point cloud Pose estimation

RobustNav: Towards Benchmarking Robustness in Embodied Navigation

by: SY

Dataset Robustness Navigation

Detecting Invisible People

by: Masanori YANO

Object tracking MOT

PR-GCN: A Deep Graph Convolutional Network With Point Refinement for 6D Pose Estimation

by: Naoya Chiba

3D Point cloud Pose estimation

Geometry-Based Distance Decomposition for Monocular 3D Object Detection

by: yoshiki miyazawa

3D 3D object detection Depth estimation Object detection

X-World: Accessibility, Vision, and Autonomy Meet

by: Godel

Dataset Instance segmentation Multi modal Object detection Recognition Semantic segmentation Vision for robotics and autonomous vehicles

Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark

by: Godel

Depth estimation Self supervised learning Vision for robotics and autonomous vehicles

Rank & Sort Loss for Object Detection and Instance Segmentation

by: Masanori YANO

Instance segmentation Object detection

AI Choreographer: Music Conditioned 3D Dance Generation With AIST++

by: 松澤郁哉

3D Dataset Multi modal

Full-Velocity Radar Returns by Radar-Camera Fusion

by: Godel

Multi modal Object detection Optical flow Pose estimation Vision for robotics and autonomous vehicles

MGNet: Monocular Geometric Scene Understanding for Autonomous Driving

by: Godel

Depth estimation Point cloud Segmentation Self supervised learning Realtime，Vision for robotics and autonomous vehicles

Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective

by: 近藤佑樹 (Yuki Kondo)

Domain adaptation GAN Super resolution Unsupervised learning

Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning Search

by: Anonymous

Neural architecture search(NAS)

BN-NAS: Neural Architecture Search With Batch Normalization

by: Anonymous

Neural architecture search(NAS)

C2N: Practical Generative Noise Modeling for Real-World Denoising

by: Hiroki Okawa

Adversarial examples GAN Self supervised learning Denoising

Cascade Image Matting With Deformable Graph Refinement

by: Masanori YANO

Segmentation Image matting GNN

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective With Transformers

by: shoji sonoyama

Attention Depth estimation

CrossDet: Crossline Representation for Object Detection

by: Masanori YANO

Object detection

RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object Detection

by: 山田亮佑 (Ryosuke Yamada)

3D object detection Dataset Self supervised learning

Internal Video Inpainting by Implicit Long-Range Propagation

by: Hiroki Okawa

N-shot learning Object detection Optical flow Robustness Self supervised learning Super resolution Video Internal Learning

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm Under Mixed Illumination

by: Masanori YANO

Dataset Image transfer White balancing

Occlusion-Aware Video Object Inpainting

by: Hiroki Okawa

Attention Dataset GAN Instance segmentation Optical flow Recognition Segmentation Semantic segmentation Video

ACDC: The Adverse Conditions Dataset With Correspondences for Semantic Driving Scene Understanding

by: Masanori YANO

Dataset Domain adaptation Semantic segmentation Autonomous driving Self-driving

Semantic-Embedded Unsupervised Spectral Reconstruction From Single RGB Images in the Wild

by: Hiroki Okawa

Adversarial examples GAN Hyperspectral Reconstruction

XVFI: eXtreme Video Frame Interpolation

by: Masanori YANO

Dataset Optical flow Video Video frame interpolation

Self-Supervised Neural Networks for Spectral Snapshot Compressive Imaging

by: Hiroki Okawa

Robustness Self supervised learning Super resolution Hyperspectral Compressive

FcaNet: Frequency Channel Attention Networks

by: Masanori YANO

Attention Instance segmentation Object detection Recognition

Audio-Visual Floorplan Reconstruction

by: Masanori YANO

3D 3D reconstruction Multi modal Floorplan reconstruction

When Do GANs Replicate? On the Choice of Dataset Size

by: Masanori YANO

Neural Articulated Radiance Field

by: Masanori YANO

3D 3D reconstruction Representation learning Segmentation

Multitask AET With Orthogonal Tangent Regularity for Dark Object Detection

by: Masanori YANO

Disentanglement Object detection

Rethinking Transformer-Based Set Prediction for Object Detection

by: Masanori YANO

Object detection

Multispectral Illumination Estimation Using Deep Unrolling Network

by: Hiroki Okawa

Dataset Hyperspectral

Fast Convergence of DETR With Spatially Modulated Co-Attention

by: Masanori YANO

Attention Object detection

Learning To Cut by Watching Movies

by: Hiroki Okawa

Dataset Multi modal Video

Conditional DETR for Fast Training Convergence

by: Masanori YANO

Attention Object detection

Flow-Guided Video Inpainting With Scene Templates

by: Hiroki Okawa

Object detection Optical flow Video Inpainting

Dynamic DETR: End-to-End Object Detection With Dynamic Attention

by: Masanori YANO

Attention Object detection

Towards Learning Spatially Discriminative Feature Representations

by: Takayuki Semitsu

Knowledge distillation Recognition Representation learning Robustness

WB-DETR: Transformer-Based Detector Without Backbone

by: Masanori YANO

Object detection

GLiT: Neural Architecture Search for Global and Local Image Transformer

by: Anonymous

Neural architecture search(NAS)

Detecting Human-Object Relationships in Videos

by: Anonymous

Attention Object detection Video

Active Universal Domain Adaptation

by: Hiroki Kobayashi

Domain adaptation Universal domain adaptation Active learning

Instances As Queries

by: Masanori YANO

Instance segmentation Object detection Video

Direct Differentiable Augmentation Search

by: Masanori YANO

Object detection Recognition

PlenOctrees for Real-Time Rendering of Neural Radiance Fields

by: Itsuki Ueda

3D 3D reconstruction

Towards Rotation Invariance in Object Detection

by: 古澤嘉久

Object detection

Evolving Search Space for Neural Architecture Search

by: Anonymous

Neural architecture search(NAS)

An Empirical Study of Training Self-Supervised Vision Transformers

by: Hirokatsu Kataoka

Representation learning Self supervised learning

Influence Selection for Active Learning

by: Kawano Yasufumi

Active Learning

Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction

by: Hirokatsu Kataoka

3D Dataset Novel View Synthesis NeRF