CVPR 2021

2,096 papers

Top Research Directions

Research directions most represented by CVPR 2021 papers.

Generalizing from Synthetic Data to the Real World 40
Resolving Depth Ambiguity in Monocular 3D Reconstruction 22
Accelerating Neural Architecture Search Without Full Model Training 20
Mitigating Error Propagation in Pseudo Labeling 19
Global Context Modeling via Non-Local Spatial Attention 18
Disentangling Attribute Control in Generative Models 17
Loss Weighting via Predictive Uncertainty 17
Why Theoretical FLOPs Fail to Predict Real Latency 17
Generative Hallucination for Disoccluded Region Synthesis 17
Deep Learning on Unstructured 3D Point Clouds 17
Preserving Tiny Features Against Spatial Resolution Degradation 16
Reconstructing Complete Geometry from Partial Point Clouds 16
The Sensitivity of Multi-Objective Loss Balancing 16
Cross Task Generalization in Image Restoration 15
Overcoming the Static Scene Assumption 15

Top Authors

AuthorPapers
Luc Van Gool15
Chunhua Shen13
Dacheng Tao12
Chang Xu11
Chen Change Loy11
Ling Shao11
Yi Yang11
Jiaya Jia10
Marc Pollefeys10
Ziwei Liu10
Alan Yuille9
Hongsheng Li9
Jie Zhou9
Yunhe Wang9
Christian Theobalt8
Hongdong Li8
Houqiang Li8
Huchuan Lu8
Lei Zhang8
Leonidas Guibas8

Impactful Papers

Papers from CVPR 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Learning Optical Flow From Still Images
Learning Parallel Dense Correspondence From Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction
Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles
Learning Placeholders for Open-Set Recognition
Learning Position and Target Consistency for Memory-Based Video Object Segmentation
Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
Learning Progressive Point Embeddings for 3D Point Cloud Generation
Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
Learning Scalable lY=-Constrained Near-Lossless Image Compression via Joint Lossy Image and Residual Compression
Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution
Learning Semantic-Aware Dynamics for Video Prediction
Learning Semantic Person Image Generation by Region-Adaptive Normalization
Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring
Learning Spatial-Semantic Relationship for Facial Attribute Recognition With Limited Labeled Data
Learning Statistical Texture for Semantic Segmentation
Learning Student Networks in the Wild
Learning Temporal Consistency for Low Light Video Enhancement From Single Images
Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction
Learning the Best Pooling Strategy for Visual Semantic Embedding
Learning the Non-Differentiable Optimization for Blind Super-Resolution
Learning the Predictability of the Future
Learning the Superpixel in a Non-Iterative and Lifelong Manner
Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification
Learning To Aggregate and Personalize 3D Face From In-the-Wild Photo Collection
Learning to Align Sequential Actions in the Wild
Learning To Associate Every Segment for Video Panoptic Segmentation
Learning To Count Everything
Learning To Filter: Siamese Relation Network for Robust Tracking
Learning To Fuse Asymmetric Feature Maps in Siamese Trackers
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
Learning To Identify Correct 2D-2D Line Correspondences on Sphere
Learning To Predict Visual Attributes in the Wild
Learning to Prompt for Continual Learning
Learning To Recommend Frame for Interactive Video Object Segmentation in the Wild
Learning To Reconstruct High Speed and High Dynamic Range Videos From Events
Learning To Recover 3D Scene Shape From a Single Image
Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation
Learning To Restore Hazy Video: A New Real-World Dataset and a New Method
Learning To Segment Actions From Visual and Language Instructions via Differentiable Weak Sequence Alignment
Learning To Segment Rigid Motions From Two Frames
Learning to Track Instances without Video Annotations
Learning To Warp for Style Transfer
Learning Triadic Belief Dynamics in Nonverbal Communication From Videos
Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization
Learning View Selection for 3D Scenes
LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering
Lepard: Learning partial point cloud matching in rigid and deformable scenes
Lesion-Aware Transformers for Diabetic Retinopathy Grading
Less Is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
Less is More: Generating Grounded Navigation Instructions from Landmarks

« prev Page 21/42 next »