{"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/assistq-affordance-centric-question-driven","title":"AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","arxiv_id":"2203.04203","date":"2022-03-08","proceeding":null,"authors":["Benita Wong","Joya Chen","You Wu","Stan Weixian Lei","Dongxing Mao","Difei Gao","Mike Zheng Shou"],"abstract":"A long-standing goal of intelligent assistants such as AR glasses/robots has been to assist users in affordance-centric real-world scenarios, such as \"how can I run the microwave for 1 minute?\". However, there is still no clear task definition and suitable benchmarks. In this paper, we define a new task called Affordance-centric Question-driven Task Completion, where the AI assistant should learn from instructional videos to provide step-by-step help in the user's view. To support the task, we constructed AssistQ, a new dataset comprising 531 question-answer samples from 100 newly filmed instructional videos. We also developed a novel Question-to-Actions (Q2A) model to address the AQTC task and validate it on the AssistQ dataset. The results show that our model significantly outperforms several VQA-related baselines while still having large room for improvement. We expect our task and dataset to advance Egocentric AI Assistant's development. Our project page is available at: https://showlab.github.io/assistq/.","url_abs":"https://arxiv.org/abs/2203.04203v5","url_pdf":"https://arxiv.org/pdf/2203.04203v5.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":"assistq-affordance-centric-question-driven","repo_url":"https://github.com/showlab/Q2A","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"assistq-affordance-centric-question-driven","repo_url":"https://github.com/jaykim9870/cvpr-22_loveu_unipyler","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"assistq-affordance-centric-question-driven","repo_url":"https://github.com/starsholic/loveu-cvpr22-aqtc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"assistq-affordance-centric-question-driven","repo_url":"https://github.com/zcfinal/loveu-cvpr23-aqtc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.04203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04203"}},"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/showlab/Q2A","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zcfinal/loveu-cvpr23-aqtc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/starsholic/loveu-cvpr22-aqtc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaykim9870/cvpr-22_loveu_unipyler","reach":null}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":6,"ran":5,"repositories":3}},"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":7,"samples":[{"code_sha256_prefix":"ff3991000b2e8faa","entry":"MLP","repo":"zcfinal/loveu-cvpr23-aqtc","repo_kind":"listed","path":"model.py","file_url":"https://github.com/zcfinal/loveu-cvpr23-aqtc/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff3991000b2e8faa"}},{"code_sha256_prefix":"3083c7f1d18ee9ac","entry":"MLP","repo":"jaykim9870/cvpr-22_loveu_unipyler","repo_kind":"listed","path":"model.py","file_url":"https://github.com/jaykim9870/cvpr-22_loveu_unipyler/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3083c7f1d18ee9ac"}},{"code_sha256_prefix":"7b1020baba6b54b4","entry":"MLP","repo":"starsholic/loveu-cvpr22-aqtc","repo_kind":"listed","path":"model.py","file_url":"https://github.com/starsholic/loveu-cvpr22-aqtc/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b1020baba6b54b4"}},{"code_sha256_prefix":"e8eff251bc5e6afc","entry":"Q2A","repo":"jaykim9870/cvpr-22_loveu_unipyler","repo_kind":"listed","path":"model.py","file_url":"https://github.com/jaykim9870/cvpr-22_loveu_unipyler/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8eff251bc5e6afc"}},{"code_sha256_prefix":"a8817f10023c6d40","entry":"Q2A","repo":"starsholic/loveu-cvpr22-aqtc","repo_kind":"listed","path":"model.py","file_url":"https://github.com/starsholic/loveu-cvpr22-aqtc/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8817f10023c6d40"}},{"code_sha256_prefix":"2dfd2ef830e4c6ee","entry":"Q2A","repo":"zcfinal/loveu-cvpr23-aqtc","repo_kind":"listed","path":"model.py","file_url":"https://github.com/zcfinal/loveu-cvpr23-aqtc/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2dfd2ef830e4c6ee"}},{"code_sha256_prefix":"fcdfdb8885527903","entry":"Q2A","repo":"showlab/Q2A","repo_kind":"official","path":"model.py","file_url":"https://github.com/showlab/Q2A/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fcdfdb8885527903"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}