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
Ranking Distance Calibration for Cross-Domain Few-Shot Learning
Ranking Neural Checkpoints
Rank-One Prior: Toward Real-Time Scene Recovery
RaScaNet: Learning Tiny Models by Raster-Scanning Images
Raw High-Definition Radar for Multi-Task Learning
Read and Attend: Temporal Localisation in Sign Language Videos
Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
ReAgent: Point Cloud Registration Using Imitation and Reinforcement Learning
Real-Time High-Resolution Background Matting
Real-Time Selfie Video Stabilization
Real-Time Sphere Sweeping Stereo From Multiview Fisheye Images
Real-Time Video Super-Resolution on Smartphones With Deep Learning, Mobile AI 2021 Challenge: Report
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
Reciprocal Landmark Detection and Tracking With Extremely Few Annotations
Reciprocal Transformations for Unsupervised Video Object Segmentation
Recognizing Actions in Videos From Unseen Viewpoints
Reconsidering Representation Alignment for Multi-View Clustering
Reconstructing 3D Human Pose by Watching Humans in the Mirror
Recorrupted-to-Recorrupted: Unsupervised Deep Learning for Image Denoising
Rectification-based Knowledge Retention for Continual Learning
Recurrent Glimpse-based Decoder for Detection with Transformer
Recurrent Multi-View Alignment Network for Unsupervised Surface Registration
ReDet: A Rotation-Equivariant Detector for Aerial Object Detection
Reducing Domain Gap by Reducing Style Bias
Refer-It-in-RGBD: A Bottom-Up Approach for 3D Visual Grounding in RGBD Images
RefineMask: Towards High-Quality Instance Segmentation With Fine-Grained Features
Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
Refining Pseudo Labels With Clustering Consensus Over Generations for Unsupervised Object Re-Identification
Reflash Dropout in Image Super-Resolution
Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields
Reformulating HOI Detection As Adaptive Set Prediction
Region-Aware Adaptive Instance Normalization for Image Harmonization
RegionCLIP: Region-based Language-Image Pretraining
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
Regressive Domain Adaptation for Unsupervised Keypoint Detection
Regularization Strategy for Point Cloud via Rigidly Mixed Sample
Regularizing Generative Adversarial Networks Under Limited Data
Regularizing Neural Networks via Adversarial Model Perturbation
Reinforced Attention for Few-Shot Learning and Beyond
Reinforced Coloring for End-to-End Instance Segmentation
Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels
Relation-aware Instance Refinement for Weakly Supervised Visual Grounding
Relative Order Analysis and Optimization for Unsupervised Deep Metric Learning
Relevance-CAM: Your Model Already Knows Where To Look
RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
ReMix: Towards Image-to-Image Translation With Limited Data
Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network
Removing Raindrops and Rain Streaks in One Go
Removing the Background by Adding the Background: Towards Background Robust Self-Supervised Video Representation Learning
ReNAS: Relativistic Evaluation of Neural Architecture Search

« prev Page 31/42 next »