{"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/tvqa-localized-compositional-video-question","title":"TVQA: Localized, Compositional Video Question Answering","arxiv_id":"1809.01696","date":"2018-09-05","proceeding":"EMNLP 2018 10","authors":["Jie Lei","Licheng Yu","Mohit Bansal","Tamara L. Berg"],"abstract":"Recent years have witnessed an increasing interest in image-based question-answering (QA) tasks. However, due to data limitations, there has been much less work on video-based QA. In this paper, we present TVQA, a large-scale video QA dataset based on 6 popular TV shows. TVQA consists of 152,545 QA pairs from 21,793 clips, spanning over 460 hours of video. Questions are designed to be compositional in nature, requiring systems to jointly localize relevant moments within a clip, comprehend subtitle-based dialogue, and recognize relevant visual concepts. We provide analyses of this new dataset as well as several baselines and a multi-stream end-to-end trainable neural network framework for the TVQA task. The dataset is publicly available at http://tvqa.cs.unc.edu.","url_abs":"https://arxiv.org/abs/1809.01696v2","url_pdf":"https://arxiv.org/pdf/1809.01696v2.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":"tvqa-localized-compositional-video-question","repo_url":"https://github.com/BM-K/Question-Difficulty-Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"tvqa-localized-compositional-video-question","repo_url":"https://github.com/h19920918/quiz_for_day06","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"tvqa-localized-compositional-video-question","repo_url":"https://github.com/jayleicn/TVQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tvqa-localized-compositional-video-question","repo_url":"https://github.com/mansigoel/TVQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"video-question-answering","task_name":"Video Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"tvqa","name":"TVQA","full_name":"TVQA"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-sutd-trafficqa","task":"Video Question Answering","dataset":"SUTD-TrafficQA","model":"TVQA","rank_in_archive_order":5,"of":6,"metrics":{"1/2":"63.15","1/4":"35.16"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.01696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.01696"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mansigoel/TVQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/h19920918/quiz_for_day06","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BM-K/Question-Difficulty-Estimation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jayleicn/TVQA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"listed":{"samples":8,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1b30465bb758c4b8","entry":"get_vidname2cnt_per_show","repo":"mansigoel/TVQA","repo_kind":"listed","path":"preprocessing.py","file_url":"https://github.com/mansigoel/TVQA/blob/HEAD/preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b30465bb758c4b8"}},{"code_sha256_prefix":"53d425eb1278ddda","entry":"load_json","repo":"jayleicn/TVQA","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/jayleicn/TVQA/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53d425eb1278ddda"}},{"code_sha256_prefix":"13141c69e7fed551","entry":"merge_list_dicts","repo":"mansigoel/TVQA","repo_kind":"listed","path":"preprocessing.py","file_url":"https://github.com/mansigoel/TVQA/blob/HEAD/preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13141c69e7fed551"}},{"code_sha256_prefix":"4e8b207ee04445f8","entry":"max_along_time","repo":"jayleicn/TVQA","repo_kind":"listed","path":"model/rnn.py","file_url":"https://github.com/jayleicn/TVQA/blob/HEAD/model/rnn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e8b207ee04445f8"}},{"code_sha256_prefix":"8ec050fe9cabe7f9","entry":"mean_along_time","repo":"jayleicn/TVQA","repo_kind":"listed","path":"model/rnn.py","file_url":"https://github.com/jayleicn/TVQA/blob/HEAD/model/rnn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ec050fe9cabe7f9"}},{"code_sha256_prefix":"d10981a16ea4b3bc","entry":"pad_collate","repo":"jayleicn/TVQA","repo_kind":"listed","path":"tvqa_dataset.py","file_url":"https://github.com/jayleicn/TVQA/blob/HEAD/tvqa_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d10981a16ea4b3bc"}},{"code_sha256_prefix":"1dc3bf82cc77e497","entry":"preprocess_inputs","repo":"jayleicn/TVQA","repo_kind":"listed","path":"tvqa_dataset.py","file_url":"https://github.com/jayleicn/TVQA/blob/HEAD/tvqa_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1dc3bf82cc77e497"}},{"code_sha256_prefix":"62891394278900f5","entry":"read_json_lines","repo":"jayleicn/TVQA","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/jayleicn/TVQA/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62891394278900f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}