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
Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency
SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks
SGTR: End-to-end Scene Graph Generation with Transformer
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography
ShapeFormer: Transformer-based Shape Completion via Sparse Representation
Shape from Polarization for Complex Scenes in the Wild
Shape from Thermal Radiation: Passive Ranging Using Multi-spectral LWIR Measurements
Shape-invariant 3D Adversarial Point Clouds
Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion
Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search
SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
Shifted Diffusion for Text-to-image Generation
Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
Show, Deconfound and Tell: Image Captioning with Causal Inference
Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning
Shunted Self-Attention via Multi-Scale Token Aggregation
Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
Siamese Image Modeling for Self-Supervised Vision Representation Learning
SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection
Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production
SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization
SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks
SimMatch: Semi-supervised Learning with Similarity Matching
SimMIM: a Simple Framework for Masked Image Modeling
Simple but Effective: CLIP Embeddings for Embodied AI
Simple Cues Lead to a Strong Multi-Object Tracker
Simple Multi-dataset Detection
SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation
Simulated Adversarial Testing of Face Recognition Models
SimVP: Simpler yet Better Video Prediction
Sim VQA: Exploring Simulated Environments for Visual Question Answering
SINE: SINgle Image Editing with Text-to-Image Diffusion Models
Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation
Single-Photon Structured Light
Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data
Single-Stage is Enough: Multi-Person Absolute 3D Pose Estimation
SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene
SIOD: Single Instance Annotated Per Category Per Image for Object Detection
Sketch3T: Test-Time Training for Zero-Shot SBIR
SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval
SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
Slimmable Domain Adaptation
Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation

« prev Page 41/50 next »