18. • オーラルセッション動画のカテゴリは, CVPRのセッション名に基づき定める
• 2019A: Architecture, Representation, Theory & Optimization
• Deep Learning・Scenes & Representation・Learning, Physics, Theory, & Datasets・Low-Level & Optimization
• 2019B: Recognition, Understanding, Segmentation & Retrieval
• Recognition・Segmentation & Grouping
• 2019C: Language, Reasoning, Body & Applications
• Motion & Biometrics・Language & Reasoning・Applications・Face & Body
• 2019D: Synthesis
• Synthesis
• 2019E: Video & 3D
• 3D Multiview・Action & Video・3D Single View & RGBD
• 除外したセッション
• Computational Photography & Graphics
オーラルセッション動画のカテゴリ
付録1 18
19. • オーラルセッション動画のカテゴリは, CVPRのセッション名に基づき定める
• 2020A: Architecture, Representation, Theory & Optimization
• Adversarial Learning・Efficient Training and Inference・Low-Level and Physics-Based Vision・Transfer/Low-
Shot/Semi/Unsupervised Learning・Representation Learning・Optimization and Learning Methods・Machine Learning
Architectures and Formulations
• 2020B: Recognition, Understanding, Segmentation & Retrieval
• Image Retrieval・Datasets and Evaluation・Scene Analysis and Understanding・Segmentation, Grouping and Shape・
Architecture, Representation, Theory & Optimization
• 2020C: Language, Reasoning, Body & Applications
• Medical, Biological and Cell Microscopy・Face, Gesture, and Body Pose・Motion and Tracking・Vision & Language・Vision for
Robotics and Autonomous Vehicles・Vision Applications and Systems・Vision & Other Modalities・Visual Reasoning and Logical
Representation
• 2020D: Synthesis
• Image and Video Synthesis
• 2020E: Video & 3D
• 3D From a Single Image and Shape-From-X・Action and Behavior・3D From Multiview and Sensors・Video Analysis and
Understanding
• 除外したセッション
• Computational Photography・Explainable AI・Fairness, Accountability, Transparency and Ethics in Vision
オーラルセッション動画のカテゴリ
付録1 19
20. • 2019A
• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope
• Lifting Vectorial Variational Problems: A Natural Formulation Based on Geometric Measure Theory and Discrete Exterior Calculus
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
• SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• Learning Video Representations From Correspondence Proposals
• A Generative Adversarial Density Estimator
• Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence
• 2020A
• Search to Distill: Pearls Are Everywhere but Not the Eyes
• Circle Loss: A Unified Perspective of Pair Similarity Optimization
• Learning Combinatorial Solver for Graph Matching
• Revisiting Knowledge Distillation via Label Smoothing Regularization
• Benchmarking Adversarial Robustness on Image Classification
• HyperSTAR: Task-Aware Hyperparameters for Deep Networks
• ActBERT: Learning Global-Local Video-Text Representations
• Hyperbolic Image Embeddings
• Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations
• How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework
サーベイしたオーラルセッション動画の論文名一覧
付録2 20
21. • 2019B
• Joint Discriminative and Generative Learning for Person Re-Identification
• Gradient Matching Generative Networks for Zero-Shot Learning
• Semantic Correlation Promoted Shape-Variant Context for Segmentation
• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
• Domain Generalization by Solving Jigsaw Puzzles
• Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble Network
• Deep Metric Learning Beyond Binary Supervision
• Panoptic Feature Pyramid Networks
• Learning to Cluster Faces on an Affinity Graph
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• 2020B
• Dynamic Graph Message Passing Networks
• Learning User Representations for Open Vocabulary Image Hashtag Prediction
• Momentum Contrast for Unsupervised Visual Representation Learning
• PointRend: Image Segmentation As Rendering
• Few-Shot Class-Incremental Learning
• ViBE: Dressing for Diverse Body Shapes
• Interactive Object Segmentation With Inside-Outside Guidance
• Detection in Crowded Scenes: One Proposal, Multiple Predictions
• Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
• Mapillary Street-Level Sequences: A Dataset for Lifelong Place Recognition
サーベイしたオーラルセッション動画の論文名一覧
付録2 21
22. • 2019C
• High-Quality Face Capture Using Anatomical Muscles
• 3D Hand Shape and Pose Estimation From a Single RGB Image
• Deeper and Wider Siamese Networks for Real-Time Visual Tracking
• GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching
• CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark
• Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
• Monocular Total Capture: Posing Face, Body, and Hands in the Wild
• Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in a Triadic Interaction
• Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields
• ATOM: Accurate Tracking by Overlap Maximization
• 2020C
• REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
• Say As You Wish: Fine-Grained Control of Image Caption Generation With Abstract Scene Graphs
• SAPIEN: A SimulAted Part-Based Interactive ENvironment
• LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
• TA-Student VQA: Multi-Agents Training by Self-Questioning
• P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
• Collaborative Motion Prediction via Neural Motion Message Passing
• Iterative Context-Aware Graph Inference for Visual Dialog
• Reciprocal Learning Networks for Human Trajectory Prediction
• Counterfactual Vision and Language Learning
サーベイしたオーラルセッション動画の論文名一覧
付録2 22
23. • 2019D
• Semantics Disentangling for Text-To-Image Generation
• Progressive Pose Attention Transfer for Person Image Generation
• Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translation
• Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translation
• DeepVoxels: Learning Persistent 3D Feature Embeddings
• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
• Animating Arbitrary Objects via Deep Motion Transfer
• Label-Noise Robust Generative Adversarial Networks
• DLOW: Domain Flow for Adaptation and Generalization
• CollaGAN: Collaborative GAN for Missing Image Data Imputation
• 2020D
• Attentive Normalization for Conditional Image Generation
• Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
• SynSin: End-to-End View Synthesis From a Single Image
• Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
• Blurry Video Frame Interpolation
• Disentangled Image Generation Through Structured Noise Injection
• Cross-Domain Correspondence Learning for Exemplar-Based Image Translation
• SketchyCOCO: Image Generation From Freehand Scene Sketches
• Single Image Reflection Removal With Physically-Based Training Images
• Semantic Pyramid for Image Generation
サーベイしたオーラルセッション動画の論文名一覧
付録2 23
24. • 2019E
• Which Way Are You Going? Imitative Decision Learning for Path Forecasting in Dynamic Scenes
• STEP: Spatio-Temporal Progressive Learning for Video Action Detection
• GA-Net: Guided Aggregation Net for End-To-End Stereo Matching
• Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image
• Revealing Scenes by Inverting Structure From Motion Reconstructions
• BAD SLAM: Bundle Adjusted Direct RGB-D SLAM
• Pushing the Boundaries of View Extrapolation With Multiplane Images
• What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
• NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences
• Gaussian Temporal Awareness Networks for Action Localization
• 2020E
• Extreme Relative Pose Network Under Hybrid Representations
• X3D: Expanding Architectures for Efficient Video Recognition
• Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve
• Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction
• BSP-Net: Generating Compact Meshes via Binary Space Partitioning
• Single-Shot Monocular RGB-D Imaging Using Uneven Double Refraction
• RoutedFusion: Learning Real-Time Depth Map Fusion
• OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
• Blur Aware Calibration of Multi-Focus Plenoptic Camera
• Information-Driven Direct RGB-D Odometry
サーベイしたオーラルセッション動画の論文名一覧
付録2 24