{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/tgif-qa-toward-spatio-temporal-reasoning-in","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","arxiv_id":"1704.04497","date":"2017-04-14","proceeding":"CVPR 2017 7","authors":["Yunseok Jang","Yale Song","Youngjae Yu","Youngjin Kim","Gunhee Kim"],"abstract":"Vision and language understanding has emerged as a subject undergoing intense\nstudy in Artificial Intelligence. Among many tasks in this line of research,\nvisual question answering (VQA) has been one of the most successful ones, where\nthe goal is to learn a model that understands visual content at region-level\ndetails and finds their associations with pairs of questions and answers in the\nnatural language form. Despite the rapid progress in the past few years, most\nexisting work in VQA have focused primarily on images. In this paper, we focus\non extending VQA to the video domain and contribute to the literature in three\nimportant ways. First, we propose three new tasks designed specifically for\nvideo VQA, which require spatio-temporal reasoning from videos to answer\nquestions correctly. Next, we introduce a new large-scale dataset for video VQA\nnamed TGIF-QA that extends existing VQA work with our new tasks. Finally, we\npropose a dual-LSTM based approach with both spatial and temporal attention,\nand show its effectiveness over conventional VQA techniques through empirical\nevaluations.","url_abs":"http://arxiv.org/abs/1704.04497v3","url_pdf":"http://arxiv.org/pdf/1704.04497v3.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":"tgif-qa-toward-spatio-temporal-reasoning-in","repo_url":"https://github.com/ahjeongseo/MASN-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tgif-qa-toward-spatio-temporal-reasoning-in","repo_url":"https://github.com/chaitanyadwivedii/3D-Attention-is-All-You-Need","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"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)"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[{"slug":"tgif-qa","name":"TGIF-QA","full_name":"TGIF-QA"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSRVTT-QA","model":"ST-VQA","rank_in_archive_order":33,"of":34,"metrics":{"Accuracy":"0.309"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"ST-VQA","rank_in_archive_order":36,"of":36,"metrics":{"Accuracy":"0.313"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.04497","atlas_url":"https://app.syntology.ai/?focus=1704.04497","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1704.04497"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1704.04497\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1704.04497"},"call":"get_concepts_for_paper(arxiv_id=\"1704.04497\")"}],"by_repo":[{"repo":"ahjeongseo/MASN-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.10446"],"harvested_for_calls":[{"arxiv_id":"2106.10446","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.10446"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.10446\")"}]},{"repo":"chaitanyadwivedii/3D-Attention-is-All-You-Need","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"482a9c22df0c0321b7e00ed891dec60a7648e7ae5bf6a9923812bb62425513ab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}