Computer Vision – ACCV 2022

Table of Contents

1. Altmetric Badge
   Book Overview
2. Altmetric Badge
   Chapter 1 Confidence-Calibrated Face Image Forgery Detection with Contrastive Representation Distillation
3. Altmetric Badge
   Chapter 2 Exposing Face Forgery Clues via Retinex-Based Image Enhancement
4. Altmetric Badge
   Chapter 3 GB-CosFace: Rethinking Softmax-Based Face Recognition from the Perspective of Open Set Classification
5. Altmetric Badge
   Chapter 4 Learning Video-Independent Eye Contact Segmentation from In-the-Wild Videos
6. Altmetric Badge
   Chapter 5 Exemplar Free Class Agnostic Counting
7. Altmetric Badge
   Chapter 6 Emphasizing Closeness and Diversity Simultaneously for Deep Face Representation
8. Altmetric Badge
   Chapter 7 KinStyle: A Strong Baseline Photorealistic Kinship Face Synthesis with an Optimized StyleGAN Encoder
9. Altmetric Badge
   Chapter 8 Occluded Facial Expression Recognition Using Self-supervised Learning
10. Altmetric Badge
    Chapter 9 Heterogeneous Avatar Synthesis Based on Disentanglement of Topology and Rendering
11. Altmetric Badge
    Chapter 10 Focal and Global Spatial-Temporal Transformer for Skeleton-Based Action Recognition
12. Altmetric Badge
    Chapter 11 Spatial-Temporal Adaptive Graph Convolutional Network for Skeleton-Based Action Recognition
13. Altmetric Badge
    Chapter 12 3D Pose Based Feedback for Physical Exercises
14. Altmetric Badge
    Chapter 13 Generating Multiple Hypotheses for 3D Human Mesh and Pose Using Conditional Generative Adversarial Nets
15. Altmetric Badge
    Chapter 14 SCOAD: Single-Frame Click Supervision for Online Action Detection
16. Altmetric Badge
    Chapter 15 Neural Puppeteer: Keypoint-Based Neural Rendering of Dynamic Shapes
17. Altmetric Badge
    Chapter 16 Decanus to Legatus: Synthetic Training for 2D-3D Human Pose Lifting
18. Altmetric Badge
    Chapter 17 Social Aware Multi-modal Pedestrian Crossing Behavior Prediction
19. Altmetric Badge
    Chapter 18 Action Representing by Constrained Conditional Mutual Information
20. Altmetric Badge
    Chapter 19 Temporal-Viewpoint Transportation Plan for Skeletal Few-Shot Action Recognition
21. Altmetric Badge
    Chapter 20 Spatial Temporal Network for Image and Skeleton Based Group Activity Recognition
22. Altmetric Badge
    Chapter 21 Learning Using Privileged Information for Zero-Shot Action Recognition
23. Altmetric Badge
    Chapter 22 MGTR: End-to-End Mutual Gaze Detection with Transformer
24. Altmetric Badge
    Chapter 23 Is an Object-Centric Video Representation Beneficial for Transfer?
25. Altmetric Badge
    Chapter 24 DCVQE: A Hierarchical Transformer for Video Quality Assessment
26. Altmetric Badge
    Chapter 25 Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition
27. Altmetric Badge
    Chapter 26 FunnyNet: Audiovisual Learning of Funny Moments in Videos
28. Altmetric Badge
    Chapter 27 ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval
29. Altmetric Badge
    Chapter 28 A Compressive Prior Guided Mask Predictive Coding Approach for Video Analysis
30. Altmetric Badge
    Chapter 29 BaSSL: Boundary-aware Self-Supervised Learning for Video Scene Segmentation
31. Altmetric Badge
    Chapter 30 HaViT: Hybrid-Attention Based Vision Transformer for Video Classification
32. Altmetric Badge
    Chapter 31 From Sparse to Dense: Semantic Graph Evolutionary Hashing for Unsupervised Cross-Modal Retrieval
33. Altmetric Badge
    Chapter 32 SST-VLM: Sparse Sampling-Twice Inspired Video-Language Model
34. Altmetric Badge
    Chapter 33 PromptLearner-CLIP: Contrastive Multi-Modal Action Representation Learning with Context Optimization
35. Altmetric Badge
    Chapter 34 Causal Property Based Anti-conflict Modeling with Hybrid Data Augmentation for Unbiased Scene Graph Generation
36. Altmetric Badge
    Chapter 35 gScoreCAM: What Objects Is CLIP Looking At?
37. Altmetric Badge
    Chapter 36 From Within to Between: Knowledge Distillation for Cross Modality Retrieval
38. Altmetric Badge
    Chapter 37 Thinking Hallucination for Video Captioning
39. Altmetric Badge
    Chapter 38 Boundary-Aware Temporal Sentence Grounding with Adaptive Proposal Refinement
40. Altmetric Badge
    Chapter 39 Two-Stage Multimodality Fusion for High-Performance Text-Based Visual Question Answering
41. Altmetric Badge
    Chapter 40 Bright as the Sun: In-depth Analysis of Imagination-Driven Image Captioning
42. Altmetric Badge
    Chapter 41 Heterogeneous Interactive Learning Network for Unsupervised Cross-Modal Retrieval
43. Altmetric Badge
    Chapter 42 GaitStrip: Gait Recognition via Effective Strip-Based Feature Representations and Multi-level Framework
44. Altmetric Badge
    Chapter 43 Soft Label Mining and Average Expression Anchoring for Facial Expression Recognition
45. Altmetric Badge
    Chapter 44 ‘Labelling the Gaps’: A Weakly Supervised Automatic Eye Gaze Estimation