{"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/video-question-answering-with-iterative-video","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","arxiv_id":"2208.00934","date":"2022-08-01","proceeding":null,"authors":["AJ Piergiovanni","Kairo Morton","Weicheng Kuo","Michael S. Ryoo","Anelia Angelova"],"abstract":"Video question answering is a challenging task that requires understanding jointly the language input, the visual information in individual video frames, as well as the temporal information about the events occurring in the video. In this paper, we propose a novel multi-stream video encoder for video question answering that uses multiple video inputs and a new video-text iterative co-tokenization approach to answer a variety of questions related to videos. We experimentally evaluate the model on several datasets, such as MSRVTT-QA, MSVD-QA, IVQA, outperforming the previous state-of-the-art by large margins. Simultaneously, our model reduces the required GFLOPs from 150-360 to only 67, producing a highly efficient video question answering model.","url_abs":"https://arxiv.org/abs/2208.00934v1","url_pdf":"https://arxiv.org/pdf/2208.00934v1.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":[],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-ivqa","task":"Video Question Answering","dataset":"iVQA","model":"Co-Tokenization","rank_in_archive_order":4,"of":7,"metrics":{"Accuracy":"38.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSRVTT-QA","model":"Co-Tokenization","rank_in_archive_order":14,"of":34,"metrics":{"Accuracy":".457"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"Co-Tokenization","rank_in_archive_order":23,"of":36,"metrics":{"Accuracy":".486"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2208.00934","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}