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
Task-Conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery
TCGM: An Information-Theoretic Framework for Semi-supervised Multi-modality Learning
Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces from Images
Temporal Aggregate Representations for Long-Range Video Understanding
Temporal Coherence or Temporal Motion: Which Is More Critical for Video-Based Person Re-identification?
Temporal Complementary Learning for Video Person Re-identification
Temporal Distinct Representation Learning for Action Recognition
Temporal Keypoint Matching and Refinement Network for Pose Estimation and Tracking
TENet: Triple Excitation Network for Video Salient Object Detection
Tensor Low-Rank Reconstruction for Semantic Segmentation
Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction
TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video
TextCaps: A Dataset for Image Captioning with Reading Comprehension
Texture Hallucination for Large-Factor Painting Super-Resolution
TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search
Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks
The Average Mixing Kernel Signature
The Devil Is in Classification: A Simple Framework for Long-Tail Instance Segmentation
The Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification
The Group Loss for Deep Metric Learning
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale
The Phong Surface: Efficient 3D Model Fitting Using Lifted Optimization
The Semantic Mutex Watershed for Efficient Bottom-Up Semantic Instance Segmentation
Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
TIDE: A General Toolbox for Identifying Object Detection Errors
TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation
TopoGAN: A Topology-Aware Generative Adversarial Network
Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction
Topology-Preserving Class-Incremental Learning
Toward Faster and Simpler Matrix Normalization via Rank-1 Update
Toward Fine-Grained Facial Expression Manipulation
Towards Analyzing Semantic Robustness of Deep Neural Networks
Towards Automated Testing and Robustification by Semantic Adversarial Data Generation
Towards Causal Benchmarking of Bias in Face Analysis Algorithms
Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation
Towards Efficient Coarse-to-Fine Networks for Action and Gesture Recognition
Towards End-to-End Video-Based Eye-Tracking
Towards Fast, Accurate and Stable 3D Dense Face Alignment
Towards Generalization Across Depth for Monocular 3D Object Detection
Towards Part-Aware Monocular 3D Human Pose Estimation: An Architecture Search Approach
Towards Practical and Efficient High-Resolution HDR Deghosting with CNN
Towards Precise Completion of Deformable Shapes
Towards Real-Time Multi-Object Tracking
Towards Recognizing Unseen Categories in Unseen Domains
Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images
Towards Streaming Perception
Towards Unique and Informative Captioning of Images
Toward Unsupervised, Multi-object Discovery in Large-Scale Image Collections
TPFN: Applying Outer Product Along Time to Multimodal Sentiment Analysis Fusion on Incomplete Data

« prev Page 26/29 next »