{"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/wildqa-in-the-wild-video-question-answering","title":"WildQA: In-the-Wild Video Question Answering","arxiv_id":"2209.06650","date":"2022-09-14","proceeding":null,"authors":["Santiago Castro","Naihao Deng","Pingxuan Huang","Mihai Burzo","Rada Mihalcea"],"abstract":"Existing video understanding datasets mostly focus on human interactions, with little attention being paid to the \"in the wild\" settings, where the videos are recorded outdoors. We propose WILDQA, a video understanding dataset of videos recorded in outside settings. In addition to video question answering (Video QA), we also introduce the new task of identifying visual support for a given question and answer (Video Evidence Selection). Through evaluations using a wide range of baseline models, we show that WILDQA poses new challenges to the vision and language research communities. The dataset is available at https://lit.eecs.umich.edu/wildqa/.","url_abs":"https://arxiv.org/abs/2209.06650v1","url_pdf":"https://arxiv.org/pdf/2209.06650v1.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":"evidence-selection","task_name":"Evidence Selection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[{"slug":"wildqa","name":"WildQA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-wildqa","task":"Video Question Answering","dataset":"WildQA","model":"Multi (text + video, IO)","rank_in_archive_order":1,"of":5,"metrics":{"ROUGE-1":"34.0 ± 0.5","ROUGE-2":"18.8 ± 0.7","ROUGE-L":"32.8 ± 0.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-wildqa","task":"Video Question Answering","dataset":"WildQA","model":"Multi (text + video, SE)","rank_in_archive_order":2,"of":5,"metrics":{"ROUGE-1":"33.8 ± 0.8","ROUGE-2":"18.5 ± 0.7","ROUGE-L":"32.5 ± 0.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-wildqa","task":"Video Question Answering","dataset":"WildQA","model":"T5 (text)","rank_in_archive_order":3,"of":5,"metrics":{"ROUGE-1":"33.8 ± 0.2","ROUGE-2":"17.7 ± 0.1","ROUGE-L":" 32.4 ± 0.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-wildqa","task":"Video Question Answering","dataset":"WildQA","model":"T5 (text + video)","rank_in_archive_order":4,"of":5,"metrics":{"ROUGE-1":"33.1 ± 0.3","ROUGE-2":"17.3 ± 0.4","ROUGE-L":"31.9 ± 0.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-wildqa","task":"Video Question Answering","dataset":"WildQA","model":"T5 (text, zero-shot)","rank_in_archive_order":5,"of":5,"metrics":{"ROUGE-1":"0.8 ± 0.0","ROUGE-2":"0.0 ± 0.0","ROUGE-L":"0.8 ± 0.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.06650","atlas_url":"https://app.syntology.ai/?focus=2209.06650","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}