{"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/simple-baselines-for-interactive-video","title":"Simple Baselines for Interactive Video Retrieval with Questions and Answers","arxiv_id":"2308.10402","date":"2023-08-21","proceeding":"ICCV 2023 1","authors":["Kaiqu Liang","Samuel Albanie"],"abstract":"To date, the majority of video retrieval systems have been optimized for a \"single-shot\" scenario in which the user submits a query in isolation, ignoring previous interactions with the system. Recently, there has been renewed interest in interactive systems to enhance retrieval, but existing approaches are complex and deliver limited gains in performance. In this work, we revisit this topic and propose several simple yet effective baselines for interactive video retrieval via question-answering. We employ a VideoQA model to simulate user interactions and show that this enables the productive study of the interactive retrieval task without access to ground truth dialogue data. Experiments on MSR-VTT, MSVD, and AVSD show that our framework using question-based interaction significantly improves the performance of text-based video retrieval systems.","url_abs":"https://arxiv.org/abs/2308.10402v1","url_pdf":"https://arxiv.org/pdf/2308.10402v1.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":"simple-baselines-for-interactive-video","repo_url":"https://github.com/kevinliang888/ivr-qa-baselines","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.10402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10402"}},"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/kevinliang888/ivr-qa-baselines","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/kevinliang888/IVR-QA-baselines","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"kevinliang888/IVR-QA-baselines","repo_kind":"official","path":"models/vit.py","file_url":"https://github.com/kevinliang888/IVR-QA-baselines/blob/HEAD/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"e19e22cd7641eb82","entry":"itm_eval","repo":"kevinliang888/IVR-QA-baselines","repo_kind":"official","path":"eval_retrieval_video.py","file_url":"https://github.com/kevinliang888/IVR-QA-baselines/blob/HEAD/eval_retrieval_video.py","link_basis":"harvester_set","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":"e19e22cd7641eb82"}},{"code_sha256_prefix":"aa5a91226269bf75","entry":"tile","repo":"kevinliang888/IVR-QA-baselines","repo_kind":"official","path":"models/blip_vqa.py","file_url":"https://github.com/kevinliang888/IVR-QA-baselines/blob/HEAD/models/blip_vqa.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5a91226269bf75"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"kevinliang888/IVR-QA-baselines","repo_kind":"official","path":"models/blip_retrieval.py","file_url":"https://github.com/kevinliang888/IVR-QA-baselines/blob/HEAD/models/blip_retrieval.py","link_basis":"harvester_set","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":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"kevinliang888/IVR-QA-baselines","repo_kind":"official","path":"models/blip_pretrain.py","file_url":"https://github.com/kevinliang888/IVR-QA-baselines/blob/HEAD/models/blip_pretrain.py","link_basis":"harvester_set","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":"73cecca9f3575f09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}