{"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/next-qa-next-phase-of-question-answering-to","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","arxiv_id":"2105.08276","date":"2021-05-18","proceeding":null,"authors":["Junbin Xiao","Xindi Shang","Angela Yao","Tat-Seng Chua"],"abstract":"We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks targeting causal action reasoning, temporal action reasoning, and common scene comprehension. Through extensive analysis of baselines and established VideoQA techniques, we find that top-performing methods excel at shallow scene descriptions but are weak in causal and temporal action reasoning. Furthermore, the models that are effective on multi-choice QA, when adapted to open-ended QA, still struggle in generalizing the answers. This raises doubt on the ability of these models to reason and highlights possibilities for improvement. With detailed results for different question types and heuristic observations for future works, we hope NExT-QA will guide the next generation of VQA research to go beyond superficial scene description towards a deeper understanding of videos. (The dataset and related resources are available at https://github.com/doc-doc/NExT-QA.git)","url_abs":"https://arxiv.org/abs/2105.08276v2","url_pdf":"https://arxiv.org/pdf/2105.08276v2.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":"next-qa-next-phase-of-question-answering-to","repo_url":"https://github.com/doc-doc/NExT-QA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"next-qa-next-phase-of-question-answering-to","repo_url":"https://github.com/doc-doc/NExT-OE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[{"slug":"next-qa-open-ended-videoqa","name":"NExT-QA (Open-ended VideoQA)","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08276"}},"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/doc-doc/NExT-OE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/doc-doc/NExT-QA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":"784d83b86ef3420a","entry":"padding_mask_k","repo":"doc-doc/NExT-QA","repo_kind":"official","path":"networks/gcn.py","file_url":"https://github.com/doc-doc/NExT-QA/blob/HEAD/networks/gcn.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"784d83b86ef3420a"}},{"code_sha256_prefix":"1d75807b764af41c","entry":"padding_mask_q","repo":"doc-doc/NExT-QA","repo_kind":"official","path":"networks/gcn.py","file_url":"https://github.com/doc-doc/NExT-QA/blob/HEAD/networks/gcn.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d75807b764af41c"}},{"code_sha256_prefix":"e649c25c10f968ce","entry":"load_file","repo":"doc-doc/NExT-QA","repo_kind":"official","path":"utils.py","file_url":"https://github.com/doc-doc/NExT-QA/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":"e649c25c10f968ce"}},{"code_sha256_prefix":"5e25b5dfb19e34d9","entry":"padding_mask","repo":"doc-doc/NExT-QA","repo_kind":"official","path":"networks/q_v_transformer.py","file_url":"https://github.com/doc-doc/NExT-QA/blob/HEAD/networks/q_v_transformer.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":"5e25b5dfb19e34d9"}},{"code_sha256_prefix":"591a68fc919f3dda","entry":"padding_mask_embedded","repo":"doc-doc/NExT-QA","repo_kind":"official","path":"networks/q_v_transformer.py","file_url":"https://github.com/doc-doc/NExT-QA/blob/HEAD/networks/q_v_transformer.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":"591a68fc919f3dda"}},{"code_sha256_prefix":"18dee9c987b1ddb8","entry":"padding_mask_transformer","repo":"doc-doc/NExT-QA","repo_kind":"official","path":"networks/q_v_transformer.py","file_url":"https://github.com/doc-doc/NExT-QA/blob/HEAD/networks/q_v_transformer.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":"18dee9c987b1ddb8"}},{"code_sha256_prefix":"d90d68789e4723ae","entry":"pkload","repo":"doc-doc/NExT-QA","repo_kind":"official","path":"utils.py","file_url":"https://github.com/doc-doc/NExT-QA/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":"d90d68789e4723ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}