Computer Vision - ECCV 2022

The 39-volume set, comprising the LNCS books 13661 until 13699, constitutes the refereed proceedings of the 17th European Conference on Computer Vision, ECCV 2022, held in Tel Aviv, Israel, during October 2327, 2022.

The 1645 papers presented in these proceedings were carefully reviewed and selected from a total of 5804 submissions. The papers deal with topics such as computer vision; machine learning; deep neural networks; reinforcement learning; object recognition; image classification; image processing; object detection; semantic segmentation; human pose estimation; 3d reconstruction; stereo vision; computational photography; neural networks; image coding; image reconstruction; object recognition; motion estimation.

Inhalt
Interpretable Open-Set Domain Adaptation via Angular Margin Separation.- TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation.- Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation.- RBC: Rectifying the Biased Context in Continual Semantic Segmentation.- Factorizing Knowledge in Neural Networks.- Contrastive Vicinal Space for Unsupervised Domain Adaptation.- Cross-Modal Knowledge Transfer without Task-Relevant Source Data.- Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions.- Source-Free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition.- BMD: A General Class-Balanced Multicentric Dynamic Prototype Strategy for Source-Free Domain Adaptation.- Generalized Brain Image Synthesis with Transferable Convolutional Sparse Coding Networks.- Incomplete Multi-View Domain Adaptation via Channel Enhancement and Knowledge Transfer.- DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization.- ML-BPM: Multi-Teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation.- PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks.- Personalized Education: Blind Knowledge Distillation.- Not All Models Are Equal: Predicting Model Transferability in a Self-Challenging Fisher Space.- How Stable Are Transferability Metrics Evaluations?.- Attention Diversification for Domain Generalization.- ESS: Learning Event-Based Semantic Segmentation from Still Images.- An Efficient Spatio-Temporal Pyramid Transformer for Action Detection.- Human Trajectory Prediction via Neural Social Physics.- Towards Open Set Video Anomaly Detection.- ECLIPSE: Efficient Long-Range Video Retrieval Using Sight and Sound.- Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing.- Less than Few: Self-Shot Video Instance Segmentation.- Adaptive Face Forgery Detection in Cross Domain.- Real-Time Online Video Detection with Temporal Smoothing Transformers.- TALLFormer: Temporal Action Localization with a Long-Memory Transformer.- Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation.- TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency.- Rethinking Learning Approaches for Long-Term Action Anticipation.- DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition.- Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation.- PAC-Net: Highlight Your Video via History Preference Modeling.- How Severe Is Benchmark-Sensitivity in Video Self-Supervised Learning?.- A Sliding Window Scheme for Online Temporal Action Localization.- ERA: Expert Retrieval and Assembly for Early Action Prediction.- DualPerspective Network for Audio-Visual Event Localization.- NSNet: Non-Saliency Suppression Sampler for Efficient Video Recognition.- Video Activity Localisation with Uncertainties in Temporal Boundary.- Temporal Saliency Query Network for Efficient Video Recognition.