CVPR 2022

2,477 papers

Top Research Directions

Research directions most represented by CVPR 2022 papers.

Generalizing from Synthetic Data to the Real World 41
Overcoming Local Receptive Field Constraints in Visual Models 38
Scaling Visual Attention Beyond Quadratic Complexity 36
Mitigating Error Propagation in Pseudo Labeling 28
Disentangling Attribute Control in Generative Models 23
Bypassing the Computational Bottleneck of Adversarial Training 23
Adversarial Training for Domain Invariant Representations 20
Addressing Inductive Bias Deficiency in Vision Transformers 19
Probabilistic Trajectory Forecasting for Autonomous Systems 18
Resolving Geometric Symmetry Ambiguity in 3D Pose Estimation 18
Decoupling Geometry and Appearance in Generative Models 17
Preserving Tiny Features Against Spatial Resolution Degradation 17
Resolving Depth Ambiguity in Monocular 3D Reconstruction 16
Cross Task Generalization in Image Restoration 15
The Representational Bottleneck of Frozen Foundation Models 15

Top Authors

AuthorPapers
Luc Van Gool24
Dacheng Tao20
Alan Yuille12
Dongdong Chen12
Jiaya Jia12
Antonio Torralba11
Jie Zhou11
Bernt Schiele10
Cewu Lu10
Errui Ding10
Jitendra Malik10
Yanwei Fu10
Yi Yang10
Chen Change Loy9
Fahad Shahbaz Khan9
Leonidas Guibas9
Minsu Cho9
Qi Tian9
Xian-Sheng Hua9
Xiaodan Liang9

Impactful Papers

Papers from CVPR 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Unsupervised Change Detection Based on Image Reconstruction Loss
Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity
Unsupervised Domain Adaptation for Nighttime Aerial Tracking
Unsupervised Domain Generalization by Learning a Bridge Across Domains
Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers
Unsupervised Homography Estimation with Coplanarity-Aware GAN
Unsupervised Image-to-Image Translation with Generative Prior
Unsupervised Learning of Accurate Siamese Tracking
Unsupervised Learning of Debiased Representations with Pseudo-Attributes
Unsupervised Pre-training for Temporal Action Localization Tasks
Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning
Unsupervised Salient Object Detection with Spectral Cluster Voting
Unsupervised Vision-and-Language Pretraining via Retrieval-based Multi-Granular Alignment
Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships
Unsupervised Visual Representation Learning by Online Constrained K-Means
UnweaveNet: Unweaving Activity Stories
Upright-Net: Learning Upright Orientation for 3D Point Cloud
URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework
Using 3D Topological Connectivity for Ghost Particle Reduction in Flow Reconstruction
UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
UV Volumes for Real-time Rendering of Editable Free-view Human Performance
V2C: Visual Voice Cloning
VALHALLA: Visual Hallucination for Machine Translation
vCLIMB: A Novel Video Class Incremental Learning Benchmark
V-Doc : Visual questions answers with Documents
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Vehicle trajectory prediction works, but not everywhere
Versatile Multi-Modal Pre-Training for Human-Centric Perception
VGFlow: Visibility guided Flow Network for Human Reposing
VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
Video Demoireing with Relation-Based Temporal Consistency
Video Demoiréing with Relation-Based Temporal Consistency
Video Frame Interpolation Transformer
Video Frame Interpolation with Transformer
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
Video Swin Transformer
Video Test-Time Adaptation for Action Recognition
Video-Text Representation Learning via Differentiable Weak Temporal Alignment
ViM: Out-Of-Distribution with Virtual-logit Matching
VindLU: A Recipe for Effective Video-and-Language Pretraining
ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries
Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
Virtual Elastic Objects
VIsCUIT: Visual Auditor for Bias in CNN Image Classifier
Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline
Vision-Language Pre-Training for Boosting Scene Text Detectors
Vision-Language Pre-Training with Triple Contrastive Learning

« prev Page 48/50 next »