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
Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian
Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data
Pose-disentangled Contrastive Learning for Self-supervised Facial Representation
PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound
PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking
Position-Guided Text Prompt for Vision-Language Pre-Training
Post-Processing Temporal Action Detection
Post-Training Quantization on Diffusion Models
PPDL: Predicate Probability Distribution based Loss for Unbiased Scene Graph Generation
Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack
Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain
Practical Network Acceleration with Tiny Sets
Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation
Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model
Prefix Conditioning Unifies Language and Label Supervision
Pretrain, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction
Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives
Privacy Leakage of Adversarial Training Models in Federated Learning Systems
Privacy-preserving Online AutoML for Domain-Specific Face Detection
Privacy Preserving Partial Localization
Proactive Image Manipulation Detection
Probabilistic Compositional Embeddings for Multimodal Image Retrieval
Probabilistic Representations for Video Contrastive Learning
Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
PROB: Probabilistic Objectness for Open World Object Detection
Programmatic Concept Learning for Human Motion Description and Synthesis
Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis
Progressive End-to-End Object Detection in Crowded Scenes
Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
Progressive Minimal Path Method with Embedded CNN
Projective Manifold Gradient Layer for Deep Rotation Regression
PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery
Prompt Distribution Learning
Propagation Regularizer for Semi-supervised Learning with Extremely Scarce Labeled Samples
Proper Reuse of Image Classification Features Improves Object Detection
ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues
Protecting Celebrities from DeepFake with Identity Consistency Transformer
Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer
Proto2Proto: Can you recognize the car, the way I do?
Prototypical Residual Networks for Anomaly Detection and Localization
PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems
Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving
PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation
PSTR: End-to-End One-Step Person Search With Transformers
PTTR: Relational 3D Point Cloud Object Tracking with Transformer
PubTables-1M: Towards comprehensive table extraction from unstructured documents

« prev Page 35/50 next »