Computer vision -- ECCV 2020 : 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings. Part XVIII / by Andrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm (eds.).

Intro
Foreword
Preface
Organization
Contents
Part XVIII
3D Bird Reconstruction: A Dataset, Model, and Shape Recovery from a Single View
1 Introduction
2 Related Work
3 Approach
4 The Cowbird Dataset
5 Experiments
6 Conclusions
References
We Have So Much in Common: Modeling Semantic Relational Set Abstractions in Videos*-6pt
1 Introduction
2 Related Work
3 A Dataset for Relational Event Abstraction
3.1 Human Performance on Event Abstraction
4 Approach
4.1 Relational Set Abstraction Model
4.2 Learning
5 Experiments

5.1 Recognizing Set Abstractions
5.2 Set Completion
5.3 Finding the Odd One Out
6 Conclusion
References
Joint Optimization for Multi-person Shape Models from Markerless 3D-Scans
1 Introduction
2 Related Work
2.1 Human Shape Models
2.2 Subdivision Surfaces
2.3 Joint Optimization
3 Articulated Morphable Shape Model
4 Objective and Optimization
5 Experimental Evaluation
5.1 Training
5.2 Inference
6 Discussion and Conclusion
References
Accurate RGB-D Salient Object Detection via Collaborative Learning
1 Introduction
2 Related Work

3 Collaborative Learning Framework
3.1 The Overall Architecture
3.2 Feature Preprocessing
3.3 Collaborative Learning
4 Experiments
4.1 Dataset
4.2 Experimental Setup
4.3 Ablation Analysis
4.4 Comparison with State-of-the-Arts
5 Conclusion
References
Finding Your (3D) Center: 3D Object Detection Using a Learned Loss
1 Introduction
2 PreviousWork
3 OurApproach
3.1 Training
3.2 Network
4 Evaluation
4.1 Network
4.2 Results
5 Discussion
6 Conclusion
References

Collaborative Training Between Region Proposal Localization and Classification for Domain Adaptive Object Detection
1 Introduction
2 Related Works
3 Method
3.1 Framework Overview
3.2 Collaborative Self-training
3.3 Maximize Discrepancy Classifier on Detectors
3.4 RPN Weighted Alignment
3.5 Overall Objective
4 Experiment
4.1 Implement Details
4.2 Domain Adaptation for Detection
5 Ablation Study
6 Conclusion
References
Two Stream Active Query Suggestion for Active Learning in Connectomics
1 Introduction
2 Related Work

3 Active Learning Framework Overview
4 Two-Stream Active Query Suggestion
4.1 Two-Stream Clustering
4.2 Active Clustering
4.3 Learning Strategy
5 EM-R50 Connectomics Dataset
6 Experiments on Connectomics Datasets
6.1 Comparing with State-of-the-Art Methods
6.2 Ablation Analysis of Two-Stream Active Query Suggestion
6.3 Ablation Analysis of Active Learning Pipeline
7 Application to Natural Image Classification
8 Conclusion
References
Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
1 Introduction
2 Related Work
3 Preliminaries