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
Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing.- Generative Negative Text Replay for Continual Vision-Language Pretraining.- Video Graph Transformer for Video Question Answering.- Trace Controlled Text to Image Generation.- Video Question Answering with Iterative Video-Text Co-Tokenization.- Rethinking Data Augmentation for Robust Visual Question Answering.- Explicit Image Caption Editing.- Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding.- Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly.- GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features.- Selective Query-Guided Debiasing for Video Corpus Moment Retrieval.- Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding.- Object-Centric Unsupervised Image Captioning.- Contrastive Vision-Language Pre-training with Limited Resources.- Learning Linguistic Association towards Efficient Text-Video Retrieval.- ASSISTER: Assistive Navigation via Conditional Instruction Generation.- X-DETR: A Versatile Architecture for Instance-Wise Vision-Language Tasks.- Learning Disentanglement with Decoupled Labels for Vision-Language Navigation.- Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input.- Word-Level Fine-Grained Story Visualization.- Unifying Event Detection and Captioning as Sequence Generation via Pre-training.- Multimodal Transformer with Variable-Length Memory for Vision-and-Language Navigation.- Fine-Grained Visual Entailment.- Bottom Up Top down Detection Transformers for Language Grounding in Images and Point Clouds.- New Datasets and Models for Contextual Reasoning in Visual Dialog.- VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage FeatureSelection.- Classification-Regression for Chart Comprehension.- AssistQ: Affordance-Centric Question-Driven Task Completion for Egocentric Assistant.- FindIt: Generalized Localization with Natural Language Queries.- UniTAB: Unifying Text and Box Outputs for Grounded VisionLanguage Modeling.- Scaling Open-Vocabulary Image Segmentation with Image-Level Labels.- The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning.- Speaker-Adaptive Lip Reading with User-Dependent Padding.- TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation.- SemAug: Semantically Meaningful Image Augmentations for Object Detection through Language Grounding.- Referring Object Manipulation of Natural Images with Conditional Classifier-Free Guidance.- NewsStories: Illustrating Articles with Visual Summaries.- Webly Supervised Concept Expansion for General Purpose Vision Models.- FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation.- CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval.- Language-Driven Artistic Style Transfer.- Single-Stream Multi-level Alignment for Vision-Language Pretraining.
