{"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-spatio-temporal-grounding-for-video","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","arxiv_id":"1904.11574","date":"2019-04-25","proceeding":"ACL 2020 6","authors":["Jie Lei","Licheng Yu","Tamara L. Berg","Mohit Bansal"],"abstract":"We present the task of Spatio-Temporal Video Question Answering, which requires intelligent systems to simultaneously retrieve relevant moments and detect referenced visual concepts (people and objects) to answer natural language questions about videos. We first augment the TVQA dataset with 310.8K bounding boxes, linking depicted objects to visual concepts in questions and answers. We name this augmented version as TVQA+. We then propose Spatio-Temporal Answerer with Grounded Evidence (STAGE), a unified framework that grounds evidence in both spatial and temporal domains to answer questions about videos. Comprehensive experiments and analyses demonstrate the effectiveness of our framework and how the rich annotations in our TVQA+ dataset can contribute to the question answering task. Moreover, by performing this joint task, our model is able to produce insightful and interpretable spatio-temporal attention visualizations. Dataset and code are publicly available at: http: //tvqa.cs.unc.edu, https://github.com/jayleicn/TVQAplus","url_abs":"https://arxiv.org/abs/1904.11574v2","url_pdf":"https://arxiv.org/pdf/1904.11574v2.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-spatio-temporal-grounding-for-video","repo_url":"https://github.com/jayleicn/TVQA-PLUS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tvqa-spatio-temporal-grounding-for-video","repo_url":"https://github.com/jayleicn/TVQAplus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tvqa-spatio-temporal-grounding-for-video","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"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"tvqa-1","name":"TVQA+","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-tvqa","task":"Video Question Answering","dataset":"TVQA","model":"STAGE (Lei et al., 2019)","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"70.50"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.11574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11574"}},"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/jayleicn/TVQA-PLUS","reach":{"status":"ok","spdx":"MIT"}},{"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/jayleicn/TVQAplus","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":2,"ran":1,"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":13,"ran":6,"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":"15a10d81f1798c24","entry":"clean_label","repo":"jayleicn/TVQAplus","repo_kind":"official","path":"eval/eval_tvqa_plus.py","file_url":"https://github.com/jayleicn/TVQAplus/blob/HEAD/eval/eval_tvqa_plus.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15a10d81f1798c24"}},{"code_sha256_prefix":"e6748ac2de40b82f","entry":"compute_temporal_iou","repo":"jayleicn/TVQAplus","repo_kind":"official","path":"eval/eval_tvqa_plus.py","file_url":"https://github.com/jayleicn/TVQAplus/blob/HEAD/eval/eval_tvqa_plus.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e6748ac2de40b82f"}},{"code_sha256_prefix":"ac298b19120de9b3","entry":"find_max_pair","repo":"jayleicn/TVQAplus","repo_kind":"official","path":"inference.py","file_url":"https://github.com/jayleicn/TVQAplus/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac298b19120de9b3"}},{"code_sha256_prefix":"cef10190a6f8f7e9","entry":"flat_list_of_lists","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/blob/HEAD/model/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cef10190a6f8f7e9"}},{"code_sha256_prefix":"53d425eb1278ddda","entry":"load_json","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/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":"1c17153fb5488283","entry":"mask_logits","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"model/model_utils.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/blob/HEAD/model/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c17153fb5488283"}},{"code_sha256_prefix":"3b1c10bbead1587d","entry":"clones","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"model/self_attention.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/blob/HEAD/model/self_attention.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":"3b1c10bbead1587d"}},{"code_sha256_prefix":"c5706ab8b1fb0d80","entry":"compute_temporal_metrics","repo":"jayleicn/TVQAplus","repo_kind":"official","path":"eval/eval_tvqa_plus.py","file_url":"https://github.com/jayleicn/TVQAplus/blob/HEAD/eval/eval_tvqa_plus.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":"c5706ab8b1fb0d80"}},{"code_sha256_prefix":"371c15cd94273e6d","entry":"filter_list_dicts","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"tvqa_dataset.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/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":"371c15cd94273e6d"}},{"code_sha256_prefix":"5c8b4d65ef6e0701","entry":"load_jsonl_as_dict","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/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":"5c8b4d65ef6e0701"}},{"code_sha256_prefix":"c9c5db64f027a226","entry":"pad_sequence_3d_label","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"tvqa_dataset.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/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":"c9c5db64f027a226"}},{"code_sha256_prefix":"4c3a3572441640fa","entry":"read_json_lines","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/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":"4c3a3572441640fa"}},{"code_sha256_prefix":"350e1afa784151b9","entry":"rm_empty_by_copy","repo":"jayleicn/TVQA-PLUS","repo_kind":"official","path":"tvqa_dataset.py","file_url":"https://github.com/jayleicn/TVQA-PLUS/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":"350e1afa784151b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}