ECCV 2020

1,405 papers

Top Research Directions

Research directions most represented by ECCV 2020 papers.

Generalizing from Synthetic Data to the Real World 23
Adversarial Training for Domain Invariant Representations 16
Mitigating Error Propagation in Pseudo Labeling 16
Cascaded Error Propagation in 2D to 3D Lifting 15
Preserving Tiny Features Against Spatial Resolution Degradation 15
Domain Adaptation with Category Shift 14
Test Time Adaptation for Distribution Shift 14
Relational Scene Graphs for Visual Reasoning 13
Resolving Depth Ambiguity in Monocular 3D Reconstruction 13
The Sensitivity of Multi-Objective Loss Balancing 13
Eliminating the Optical Flow Bottleneck in Video Understanding 12
Deep Learning on Unstructured 3D Point Clouds 12
Composite Loss Functions for Perceptual Image Restoration 11
Loss Weighting via Predictive Uncertainty 11
Overcoming Local Receptive Field Constraints in Visual Models 11

Top Authors

AuthorPapers
Andrea Vedaldi15
Horst Bischof14
Ling Shao14
Thomas Brox14
Dahua Lin13
Luc Van Gool13
Leonidas Guibas12
Raquel Urtasun12
Chunhua Shen10
Ming-Hsuan Yang10
Qi Tian10
Christian Theobalt9
Jie Zhou9
Yu Qiao9
Chen Change Loy8
Dacheng Tao8
Huchuan Lu8
Manmohan Chandraker8
Rongrong Ji8
Alan Yuille7

Impactful Papers

Papers from ECCV 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference
Video-Based Remote Physiological Measurement via Cross-Verified Feature Disentangling
Video Object Detection via Object-Level Temporal Aggregation
Video Object Segmentation with Episodic Graph Memory Networks
Video Representation Learning by Recognizing Temporal Transformations
Video Super-Resolution with Recurrent Structure-Detail Network
View-Invariant Probabilistic Embedding for Human Pose
Virtual Multi-view Fusion for 3D Semantic Segmentation
VisualCOMET: Reasoning About the Dynamic Context of a Still Image
Visual Compositional Learning for Human-Object Interaction Detection
VisualEchoes: Spatial Image Representation Learning Through Echolocation
Visual Memorability for Robotic Interestingness via Unsupervised Online Learning
Visual Question Answering on Image Sets
Visual-Relation Conscious Image Generation from Structured-Text
Visual Relation Grounding in Videos
ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language
VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval
Volumetric Transformer Networks
VoxelPose: Towards Multi-camera 3D Human Pose Estimation in Wild Environment
VPN: Learning Video-Pose Embedding for Activities of Daily Living
VQA-LOL: Visual Question Answering Under the Lens of Logic
W2S: Microscopy Data with Joint Denoising and Super-Resolution for Widefield to SIM Mapping
Wavelet-Based Dual-Branch Network for Image Demoiréing
Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows
Weakly Supervised 3D Object Detection from Lidar Point Cloud
Weakly-Supervised 3D Shape Completion in the Wild
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning
Weakly-Supervised Cell Tracking via Backward-and-Forward Propagation
Weakly-Supervised Crowd Counting Learns from Sorting Rather Than Locations
Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances
Weakly-Supervised Learning of Human Dynamics
Weakly Supervised Learning with Side Information for Noisy Labeled Images
Weakly Supervised Semantic Segmentation with Boundary Exploration
Webly Supervised Image Classification with Self-contained Confidence
We Have So Much in Common: Modeling Semantic Relational Set Abstractions in Videos
Weighing Counts: Sequential Crowd Counting by Reinforcement Learning
Weight Decay Scheduling and Knowledge Distillation for Active Learning
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks
WeightNet: Revisiting the Design Space of Weight Networks
What Is Learned in Deep Uncalibrated Photometric Stereo?
What Makes Fake Images Detectable? Understanding Properties that Generalize
What Matters in Unsupervised Optical Flow
When Does Self-supervision Improve Few-Shot Learning?
Where to Explore Next? ExHistCNN for History-Aware Autonomous 3D Exploration
Whole-Body Human Pose Estimation in the Wild
Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
Why Are Deep Representations Good Perceptual Quality Features?
Why Do These Match? Explaining the Behavior of Image Similarity Models
World-Consistent Video-to-Video Synthesis

« prev Page 28/29 next »