Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXVIII(13698 Lecture Notes in Computer Science)

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 23–27, 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.

Table of Contents:
TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices Using Submodular Mutual Information.- An Efficient Person Clustering Algorithm for Open Checkout-Free Groceries.- POP: Mining POtential Performance of New Fashion Products via Webly Cross-Modal Query Expansion.- Pose Forecasting in Industrial Human-Robot Collaboration.- Actor-Centered Representations for Action Localization in Streaming Videos.- Bandwidth-Aware Adaptive Codec for DNN Inference Offloading in IoT.- Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment.- Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics.- TIPS: Text-Induced Pose Synthesis.- Addressing Heterogeneity in Federated Learning via Distributional Transformation.- Where in the World Is This Image? Transformer-Based Geo-Localization in the Wild.- Colorization for In Situ Marine Plankton Images.- Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection.-  A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch.- A Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D.- AutoTransition: Learning to Recommend Video Transition Effects.- Online Segmentation of LiDAR Sequences: Dataset and Algorithm.- Open-World Semantic Segmentation for LIDAR Point Clouds.- KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients.- Differentiable Raycasting for Self-Supervised Occupancy Forecasting.- InAction: Interpretable Action Decision Making for Autonomous Driving.- CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection.- CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving.- Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving.- StretchBEV: Stretching Future Instance Prediction Spatially and Temporally.- RCLane: Relay Chain Prediction for Lane Detection.- Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation.- CenterFormer: Center-based Transformer for 3D Object Detection.- Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches.- ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning.- PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark.- PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation.- BRNet: Exploring Comprehensive Features for Monocular Depth Estimation.- SiamDoGe: Domain Generalizable Semantic Segmentation Using Siamese Network.- Context-Aware Streaming Perception in Dynamic Environments.- Context-Aware Streaming Perception in Dynamic Environments.- MultimodalTransformer for Automatic 3D Annotation and Object Detection.- Dynamic 3D Scene Analysis by Point Cloud Accumulation.- Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection.- JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes.- Semi-Supervised 3D Object Detection with Proficient Teachers.- Point Cloud Compression with Sibling Context and Surface Priors.