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
Learnable Companding Quantization for Accurate Low-Bit Neural Networks
Learnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object Tracking
Learnable Motion Coherence for Correspondence Pruning
Learned Initializations for Optimizing Coordinate-Based Neural Representations
Learned Queries for Efficient Local Attention
Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report
Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification
Learning Accurate Dense Correspondences and When To Trust Them
Learning a Facial Expression Embedding Disentangled From Identity
Learning Affinity-Aware Upsampling for Deep Image Matting
Learning an Explicit Weighting Scheme for Adapting Complex HSI Noise
Learning a Non-Blind Deblurring Network for Night Blurry Images
Learning a Proposal Classifier for Multiple Object Tracking
Learning a Self-Expressive Network for Subspace Clustering
Learning Asynchronous and Sparse Human-Object Interaction in Videos
Learning-Based Image Registration With Meta-Regularization
Learning Better Visual Dialog Agents With Pretrained Visual-Linguistic Representation
Learning by Aligning Videos in Time
Learning by Planning: Language-Guided Global Image Editing
Learning by Watching
Learning Calibrated Medical Image Segmentation via Multi-Rater Agreement Modeling
Learning Camera Localization via Dense Scene Matching
Learning Complete 3D Morphable Face Models From Images and Videos
Learning Compositional Radiance Fields of Dynamic Human Heads
Learning Compositional Representation for 4D Captures With Neural ODE
Learning Continuous Image Representation With Local Implicit Image Function
Learning Cross-Modal Retrieval With Noisy Labels
Learning Decision Trees Recurrently Through Communication
Learning Deep Classifiers Consistent With Fine-Grained Novelty Detection
Learning Deep Latent Variable Models by Short-Run MCMC Inference With Optimal Transport Correction
Learning Delaunay Surface Elements for Mesh Reconstruction
Learning Discriminative Prototypes With Dynamic Time Warping
Learning Dynamic Alignment via Meta-Filter for Few-Shot Learning
Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation
Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
Learning Fair Classifiers with Partially Annotated Group Labels
Learning Feature Aggregation for Deep 3D Morphable Models
Learning Fine-Grained Segmentation of 3D Shapes Without Part Labels
Learning from Temporal Gradient for Semi-supervised Action Recognition
Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading
Learning Goals From Failure
Learning Graph Embeddings for Compositional Zero-Shot Learning
Learning Graphs for Knowledge Transfer With Limited Labels
Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos
Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation
Learning Monocular 3D Reconstruction of Articulated Categories From Motion
Learning Multi-Scale Photo Exposure Correction
Learning Neural Representation of Camera Pose with Matrix Representation of Pose Shift via View Synthesis
Learning Normal Dynamics in Videos With Meta Prototype Network
Learning Optical Flow From a Few Matches

« prev Page 20/42 next »