{"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/motion-appearance-co-memory-networks-for","title":"Motion-Appearance Co-Memory Networks for Video Question Answering","arxiv_id":"1803.10906","date":"2018-03-29","proceeding":"CVPR 2018 6","authors":["Jiyang Gao","Runzhou Ge","Kan Chen","Ram Nevatia"],"abstract":"Video Question Answering (QA) is an important task in understanding video\ntemporal structure. We observe that there are three unique attributes of video\nQA compared with image QA: (1) it deals with long sequences of images\ncontaining richer information not only in quantity but also in variety; (2)\nmotion and appearance information are usually correlated with each other and\nable to provide useful attention cues to the other; (3) different questions\nrequire different number of frames to infer the answer. Based these\nobservations, we propose a motion-appearance comemory network for video QA. Our\nnetworks are built on concepts from Dynamic Memory Network (DMN) and introduces\nnew mechanisms for video QA. Specifically, there are three salient aspects: (1)\na co-memory attention mechanism that utilizes cues from both motion and\nappearance to generate attention; (2) a temporal conv-deconv network to\ngenerate multi-level contextual facts; (3) a dynamic fact ensemble method to\nconstruct temporal representation dynamically for different questions. We\nevaluate our method on TGIF-QA dataset, and the results outperform\nstate-of-the-art significantly on all four tasks of TGIF-QA.","url_abs":"http://arxiv.org/abs/1803.10906v1","url_pdf":"http://arxiv.org/pdf/1803.10906v1.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":[{"method_slug":"dynamic-memory-network","method_name":"Dynamic Memory Network"},{"method_slug":"gru","method_name":"GRU"},{"method_slug":"memory-network","method_name":"Memory Network"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSRVTT-QA","model":"Co-Mem","rank_in_archive_order":31,"of":34,"metrics":{"Accuracy":"0.32"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"Co-Mem","rank_in_archive_order":35,"of":36,"metrics":{"Accuracy":"0.317"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.10906","atlas_url":"https://app.syntology.ai/?focus=1803.10906","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":"1803.10906"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1803.10906\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1803.10906"},"call":"get_concepts_for_paper(arxiv_id=\"1803.10906\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"592b49af5efa8e78f2a547d7bf6c367c065f2c09603e663b2f57e830542c072e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}