Full Description
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.
Contents
ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-Verified Image-Caption Associations for MS-COCO.- MOTCOM: The Multi-Object Tracking Dataset Complexity Metric.- How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?.- A Real World Dataset for Multi-View 3D Reconstruction.- REALY: Rethinking the Evaluation of 3D Face Reconstruction.- Capturing, Reconstructing, and Simulating: The UrbanScene3D Dataset.- 3D CoMPaT: Composition of Materials on Parts of 3D Things.- PartImageNet: A Large, High-Quality Dataset of Parts.- A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge.- OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images.- Facial Depth and Normal Estimation Using Single Dual-Pixel Camera.- The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing.- StyleBabel: Artistic Style Tagging and Captioning.- PANDORA: A Panoramic Detection Dataset for Object with Orientation.- FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context.- Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset.- The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting.- A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility.- BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis.- Dress Code: High-Resolution Multi-Category Virtual Try-On.- A Data-Centric Approach for Improving Ambiguous Labels with Combined Semi-Supervised Classification and Clustering.- ClearPose: Large-Scale Transparent Object Dataset and Benchmark.- When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics.- AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment.- MUGEN: A Playground for Video-Audio-Text MultimodalUnderstanding and GENeration.- A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing.- MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis.- Delving into Universal Lesion Segmentation: Method, Dataset, andBenchmark.- Large Scale Real-World Multi-person Tracking.- D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights.- The Missing Link: Finding Label Relations across Datasets.- Learning Omnidirectional Flow in 360o Video via Siamese Representation.- VizWiz-FewShot: Locating Objects in Images Taken by People withVisual Impairments.- TRoVE: Transforming Road Scene Datasets into Photorealistic VirtualEnvironments.- Trapped in Texture Bias? A Large Scale Comparison of Deep InstanceSegmentation.- Deformable Feature Aggregationfor Dynamic Multi-modal 3D ObjectDetection.- WeLSA: Learning to Predict 6D Pose from Weakly Labeled Data UsingShape Alignment.- Graph R-CNN: Towards Accurate 3D Object Detection withSemantic-Decorated Local Graph.- MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection.- Long-Tail Detection with Effective Class-Margins.- Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency.- PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer towards Video Object Detection.
