{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/focal-visual-text-attention-for-visual","title":"Focal Visual-Text Attention for Visual Question Answering","arxiv_id":"1806.01873","date":"2018-06-05","proceeding":"CVPR 2018 6","authors":["Junwei Liang","Lu Jiang","Liangliang Cao","Li-Jia Li","Alexander Hauptmann"],"abstract":"Recent insights on language and vision with neural networks have been successfully applied to simple single-image visual question answering. However, to tackle real-life question answering problems on multimedia collections such as personal photos, we have to look at whole collections with sequences of photos or videos. When answering questions from a large collection, a natural problem is to identify snippets to support the answer. In this paper, we describe a novel neural network called Focal Visual-Text Attention network (FVTA) for collective reasoning in visual question answering, where both visual and text sequence information such as images and text metadata are presented. FVTA introduces an end-to-end approach that makes use of a hierarchical process to dynamically determine what media and what time to focus on in the sequential data to answer the question. FVTA can not only answer the questions well but also provides the justifications which the system results are based upon to get the answers. FVTA achieves state-of-the-art performance on the MemexQA dataset and competitive results on the MovieQA dataset.","url_abs":"https://arxiv.org/abs/1806.01873v2","url_pdf":"https://arxiv.org/pdf/1806.01873v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"focal-visual-text-attention-for-visual","repo_url":"https://github.com/JunweiLiang/FVTA_MemexQA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"focal-visual-text-attention-for-visual","repo_url":"https://github.com/JunweiLiang/FVTA_memoryqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"memex-question-answering","task_name":"Memex Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/memex-question-answering-on-memexqa","task":"Memex Question Answering","dataset":"MemexQA","model":"FVTA","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"0.357"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.01873","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}