Computer Vision – ECCV 2022 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXVII

Most and Least Retrievable Images in Visual-Language Query Systems.- Sports Video Analysis on Large-Scale Data.- Grounding Visual Representations with Texts for Domain Generalization.- Bridging the Visual Semantic Gap in VLN via Semantically Richer Instructions.- StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation.- VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance.- Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation.- End-to-End Active Speaker Detection.- Emotion Recognition for Multiple Context Awareness.- Adaptive Fine-Grained Sketch-Based Image Retrieval.- Quantized GAN for Complex Music Generation from Dance Videos.- Uncertainty-Aware Multi-modal Learning via Cross-Modal Random Network Prediction.- Localizing Visual Sounds the Easy Way.- Learning Visual Styles from Audio-Visual Associations.- Remote Respiration Monitoring of Moving Person Using Radio Signals.- Camera Pose Estimation and Localization with Active Audio Sensing.- PACS: A Dataset for Physical Audiovisual Commonsense Reasoning.- VoViT: Low Latency Graph-Based Audio-Visual Voice Separation Transformer.- Telepresence Video Quality Assessment.- MultiMAE: Multi-modal Multi-task Masked Autoencoders.- AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation.- Audio—Visual Segmentation.- Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression.- Relationformer: A Unified Framework for Image-to-Graph Generation.- GAMa: Cross-view Video Geo-localization.- Revisiting a kNN-based Image Classification System with High-capacity Storage.- Geometric Representation Learning for Document Image Rectification.- S2-VER: Semi-Supervised Visual Emotion Recognition.- Image Coding for Machines with Omnipotent Feature Learning.- Feature Representation Learning for Unsupervised Cross-Domain Image Retrieval.- Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition.- Semantic-Guided Multi-Mask Image Harmonization.- Learning an Isometric Surface Parameterization for Texture Unwrapping.- Towards Regression-Free Neural Networks for Diverse Compute Platforms.- Relationship Spatialization for Depth Estimation.- Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models.- FAR: Fourier Aerial Video Recognition.- Translating a Visual LEGO Manual to a Machine-Executable Plan.- Fabric Material Recovery from Video Using Multi-Scale Geometric Auto-Encoder.- MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment.- The One Where They Reconstructed 3D Humans and Environments in TV Shows.