{"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/heterogeneous-memory-enhanced-multimodal","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","arxiv_id":"1904.04357","date":"2019-04-08","proceeding":"CVPR 2019 6","authors":["Chenyou Fan","Xiaofan Zhang","Shu Zhang","Wensheng Wang","Chi Zhang","Heng Huang"],"abstract":"In this paper, we propose a novel end-to-end trainable Video Question\nAnswering (VideoQA) framework with three major components: 1) a new\nheterogeneous memory which can effectively learn global context information\nfrom appearance and motion features; 2) a redesigned question memory which\nhelps understand the complex semantics of question and highlights queried\nsubjects; and 3) a new multimodal fusion layer which performs multi-step\nreasoning by attending to relevant visual and textual hints with self-updated\nattention. Our VideoQA model firstly generates the global context-aware visual\nand textual features respectively by interacting current inputs with memory\ncontents. After that, it makes the attentional fusion of the multimodal visual\nand textual representations to infer the correct answer. Multiple cycles of\nreasoning can be made to iteratively refine attention weights of the multimodal\ndata and improve the final representation of the QA pair. Experimental results\ndemonstrate our approach achieves state-of-the-art performance on four VideoQA\nbenchmark datasets.","url_abs":"http://arxiv.org/abs/1904.04357v1","url_pdf":"http://arxiv.org/pdf/1904.04357v1.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":"heterogeneous-memory-enhanced-multimodal","repo_url":"https://github.com/fanchenyou/HME-VideoQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSRVTT-QA","model":"HMEMA","rank_in_archive_order":30,"of":34,"metrics":{"Accuracy":"0.33"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"HMEMA","rank_in_archive_order":34,"of":36,"metrics":{"Accuracy":"0.337"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.04357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04357"}},"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/fanchenyou/HME-VideoQA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"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":"9448865c9a0dac2c","entry":"clean_blank","repo":"fanchenyou/HME-VideoQA","repo_kind":"official","path":"gif-qa/data_util/data_util.py","file_url":"https://github.com/fanchenyou/HME-VideoQA/blob/HEAD/gif-qa/data_util/data_util.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":"9448865c9a0dac2c"}},{"code_sha256_prefix":"5cac0af93add604d","entry":"clean_str","repo":"fanchenyou/HME-VideoQA","repo_kind":"official","path":"gif-qa/data_util/data_util.py","file_url":"https://github.com/fanchenyou/HME-VideoQA/blob/HEAD/gif-qa/data_util/data_util.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":"5cac0af93add604d"}},{"code_sha256_prefix":"32af6c6131d67e09","entry":"recover_word","repo":"fanchenyou/HME-VideoQA","repo_kind":"official","path":"gif-qa/data_util/data_util.py","file_url":"https://github.com/fanchenyou/HME-VideoQA/blob/HEAD/gif-qa/data_util/data_util.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":"32af6c6131d67e09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}