Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Weichao, Feng, Hao, Liu, Qi, Tang, Jingqun, Wei, Shu, Wu, Binghong, Liao, Lei, Ye, Yongjie, Liu, Hao, Zhou, Wengang, Li, Houqiang, Huang, Can
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2406.01326
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913541449056256
author Zhao, Weichao
Feng, Hao
Liu, Qi
Tang, Jingqun
Wei, Shu
Wu, Binghong
Liao, Lei
Ye, Yongjie
Liu, Hao
Zhou, Wengang
Li, Houqiang
Huang, Can
author_facet Zhao, Weichao
Feng, Hao
Liu, Qi
Tang, Jingqun
Wei, Shu
Wu, Binghong
Liao, Lei
Ye, Yongjie
Liu, Hao
Zhou, Wengang
Li, Houqiang
Huang, Can
contents Tables contain factual and quantitative data accompanied by various structures and contents that pose challenges for machine comprehension. Previous methods generally design task-specific architectures and objectives for individual tasks, resulting in modal isolation and intricate workflows. In this paper, we present a novel large vision-language model, TabPedia, equipped with a concept synergy mechanism. In this mechanism, all the involved diverse visual table understanding (VTU) tasks and multi-source visual embeddings are abstracted as concepts. This unified framework allows TabPedia to seamlessly integrate VTU tasks, such as table detection, table structure recognition, table querying, and table question answering, by leveraging the capabilities of large language models (LLMs). Moreover, the concept synergy mechanism enables table perception-related and comprehension-related tasks to work in harmony, as they can effectively leverage the needed clues from the corresponding source perception embeddings. Furthermore, to better evaluate the VTU task in real-world scenarios, we establish a new and comprehensive table VQA benchmark, ComTQA, featuring approximately 9,000 QA pairs. Extensive quantitative and qualitative experiments on both table perception and comprehension tasks, conducted across various public benchmarks, validate the effectiveness of our TabPedia. The superior performance further confirms the feasibility of using LLMs for understanding visual tables when all concepts work in synergy. The benchmark ComTQA has been open-sourced at https://huggingface.co/datasets/ByteDance/ComTQA. The source code and model also have been released athttps://github.com/zhaowc-ustc/TabPedia.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01326
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
Zhao, Weichao
Feng, Hao
Liu, Qi
Tang, Jingqun
Wei, Shu
Wu, Binghong
Liao, Lei
Ye, Yongjie
Liu, Hao
Zhou, Wengang
Li, Houqiang
Huang, Can
Computer Vision and Pattern Recognition
Tables contain factual and quantitative data accompanied by various structures and contents that pose challenges for machine comprehension. Previous methods generally design task-specific architectures and objectives for individual tasks, resulting in modal isolation and intricate workflows. In this paper, we present a novel large vision-language model, TabPedia, equipped with a concept synergy mechanism. In this mechanism, all the involved diverse visual table understanding (VTU) tasks and multi-source visual embeddings are abstracted as concepts. This unified framework allows TabPedia to seamlessly integrate VTU tasks, such as table detection, table structure recognition, table querying, and table question answering, by leveraging the capabilities of large language models (LLMs). Moreover, the concept synergy mechanism enables table perception-related and comprehension-related tasks to work in harmony, as they can effectively leverage the needed clues from the corresponding source perception embeddings. Furthermore, to better evaluate the VTU task in real-world scenarios, we establish a new and comprehensive table VQA benchmark, ComTQA, featuring approximately 9,000 QA pairs. Extensive quantitative and qualitative experiments on both table perception and comprehension tasks, conducted across various public benchmarks, validate the effectiveness of our TabPedia. The superior performance further confirms the feasibility of using LLMs for understanding visual tables when all concepts work in synergy. The benchmark ComTQA has been open-sourced at https://huggingface.co/datasets/ByteDance/ComTQA. The source code and model also have been released athttps://github.com/zhaowc-ustc/TabPedia.
title TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.01326