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
Semi-Supervised Semantic Segmentation With Directional Context-Aware Consistency
Semi-Supervised Synthesis of High-Resolution Editable Textures for 3D Humans
Semi-Supervised Video Deraining With Dynamical Rain Generator
Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer
Separating Skills and Concepts for Novel Visual Question Answering
Sequence-to-Sequence Contrastive Learning for Text Recognition
Sequential Graph Convolutional Network for Active Learning
Sequential Voting with Relational Box Fields for Active Object Detection
SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud
SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data
Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark
SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation
SGTR: End-to-end Scene Graph Generation with Transformer
Shadow-Mapping for Unsupervised Neural Causal Discovery
Shallow Feature Matters for Weakly Supervised Object Localization
Shape and Material Capture at Home
Shape from Polarization for Complex Scenes in the Wild
Shape From Sky: Polarimetric Normal Recovery Under the Sky
Shared Cross-Modal Trajectory Prediction for Autonomous Driving
Shelf-Supervised Mesh Prediction in the Wild
Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
Siamese Natural Language Tracker: Tracking by Natural Language Descriptions With Siamese Trackers
SiamMOT: Siamese Multi-Object Tracking
Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction From Raw Point Clouds
Sign Language Production: A Review
SimMIM: A Simple Framework for Masked Image Modeling
Simple but Effective: CLIP Embeddings for Embodied AI
Simple Copy-Paste Is a Strong Data Augmentation Method for Instance Segmentation
Simple Multi-dataset Detection
Simpler Certified Radius Maximization by Propagating Covariances
SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification
SimPoE: Simulated Character Control for 3D Human Pose Estimation
Simulated Adversarial Testing of Face Recognition Models
Simulating Unknown Target Models for Query-Efficient Black-Box Attacks
Simultaneously Localize, Segment and Rank the Camouflaged Objects
Single Image Depth Prediction With Wavelet Decomposition
Single Image Reflection Removal With Absorption Effect
Single Pair Cross-Modality Super Resolution
Single-Shot Freestyle Dance Reenactment
Single-Stage Instance Shadow Detection With Bidirectional Relation Learning
Single-View 3D Object Reconstruction From Shape Priors in Memory
Single-View Robot Pose and Joint Angle Estimation via Render & Compare
SIPSA-Net: Shift-Invariant Pan Sharpening With Moving Object Alignment for Satellite Imagery
Skeleton Merger: An Unsupervised Aligned Keypoint Detector
Sketch2Model: View-Aware 3D Modeling From Single Free-Hand Sketches
SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
Sketch, Ground, and Refine: Top-Down Dense Video Captioning
SKFAC: Training Neural Networks With Faster Kronecker-Factored Approximate Curvature
Skip-Convolutions for Efficient Video Processing

« prev Page 35/42 next »