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
Stand-Alone Inter-Frame Attention in Video Models
Stare at What You See: Masked Image Modeling without Reconstruction
STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes
Stereo Depth from Events Cameras: Concentrate and Focus on the Future
Stereo Magnification with Multi-Layer Images
Stereoscopic Universal Perturbations across Different Architectures and Datasets
ST++: Make Self-trainingWork Better for Semi-supervised Semantic Segmentation
ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion
Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability
Stratified Transformer for 3D Point Cloud Segmentation
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation
Structure-Aware Flow Generation for Human Body Reshaping
Structure-Aware Motion Transfer with Deformable Anchor Model
Structured Local Radiance Fields for Human Avatar Modeling
Structured Sparse R-CNN for Direct Scene Graph Generation
StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition
Style-Based Global Appearance Flow for Virtual Try-On
Style-ERD: Responsive and Coherent Online Motion Style Transfer
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2
StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions
Style Neophile: Constantly Seeking Novel Styles for Domain Generalization
StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation
Style-Structure Disentangled Features and Normalizing Flows for Diverse Icon Colorization
StyleSwin: Transformer-based GAN for High-resolution Image Generation
StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis
Style Transformer for Image Inversion and Editing
StyTr2: Image Style Transfer with Transformers
Subspace Adversarial Training
Sub-word Level Lip Reading With Visual Attention
Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning
Super-Fibonacci Spirals: Fast, Low-Discrepancy Sampling of SO(3)
Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis
Surface Reconstruction from Point Clouds by Learning Predictive Context Priors
Surface Representation for Point Clouds
SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings
Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning
SVFormer: Semi-supervised Video Transformer for Action Recognition
SVIP: Sequence VerIfication for Procedures in Videos
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization
SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning
SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
Swin Transformer V2: Scaling Up Capacity and Resolution
Switchable Representation Learning Framework with Self-Compatibility

« prev Page 43/50 next »