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
MetaCLUE: Towards Comprehensive Visual Metaphors Research
Meta Convolutional Neural Networks for Single Domain Generalization
Meta Distribution Alignment for Generalizable Person Re-Identification
MetaFormer is Actually What You Need for Vision
MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
MIME: Human-Aware 3D Scene Generation
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks
Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation
Mining Multi-View Information: A Strong Self-Supervised Framework for Depth-based 3D Hand Pose and Mesh Estimation
MiniViT: Compressing Vision Transformers with Weight Multiplexing
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
MIST : Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering
Mix and Localize: Localizing Sound Sources in Mixtures
Mixed Differential Privacy in Computer Vision
MixFormer: End-to-End Tracking with Iterative Mixed Attention
MixFormer: Mixing Features across Windows and Dimensions
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing
MLSLT: Towards Multilingual Sign Language Translation
MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency
MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
MNSRNet: Multimodal Transformer Network for 3D Surface Super-Resolution
Mobile-Former: Bridging MobileNet and Transformer
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image
Modality-Agnostic Learning for Radar-Lidar Fusion in Vehicle Detection
Modeling 3D Layout For Group Re-Identification
Modeling Image Composition for Complex Scene Generation
Modeling Indirect Illumination for Inverse Rendering
Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery
Modeling Missing Annotations for Incremental Learning in Object Detection
Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation
Modeling sRGB Camera Noise with Normalizing Flows
Modular Action Concept Grounding in Semantic Video Prediction
Modulated Contrast for Versatile Image Synthesis
MoFusion: A Framework for Denoising-Diffusion-Based Motion Synthesis
MogFace: Towards a Deeper Appreciation on Face Detection
MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
MonoGround: Detecting Monocular 3D Objects from the Ground
MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection
MonoScene: Monocular 3D Semantic Scene Completion
More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech

« prev Page 28/50 next »