{"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/on-semantic-similarity-in-video-retrieval","title":"On Semantic Similarity in Video Retrieval","arxiv_id":"2103.10095","date":"2021-03-18","proceeding":"CVPR 2021 1","authors":["Michael Wray","Hazel Doughty","Dima Damen"],"abstract":"Current video retrieval efforts all found their evaluation on an instance-based assumption, that only a single caption is relevant to a query video and vice versa. We demonstrate that this assumption results in performance comparisons often not indicative of models' retrieval capabilities. We propose a move to semantic similarity video retrieval, where (i) multiple videos/captions can be deemed equally relevant, and their relative ranking does not affect a method's reported performance and (ii) retrieved videos/captions are ranked by their similarity to a query. We propose several proxies to estimate semantic similarities in large-scale retrieval datasets, without additional annotations. Our analysis is performed on three commonly used video retrieval datasets (MSR-VTT, YouCook2 and EPIC-KITCHENS).","url_abs":"https://arxiv.org/abs/2103.10095v1","url_pdf":"https://arxiv.org/pdf/2103.10095v1.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":"on-semantic-similarity-in-video-retrieval","repo_url":"https://github.com/mwray/Semantic-Video-Retrieval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"on-semantic-similarity-in-video-retrieval","repo_url":"https://github.com/aranciokov/fsmmda_videoretrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"on-semantic-similarity-in-video-retrieval","repo_url":"https://github.com/aranciokov/ranp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.10095","atlas_url":"https://app.syntology.ai/?focus=2103.10095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10095"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/mwray/Semantic-Video-Retrieval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aranciokov/ranp","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aranciokov/fsmmda_videoretrieval","reach":{"status":"unanswered"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"a3d83cec1646b646","entry":"create_iou","repo":"mwray/Semantic-Video-Retrieval","repo_kind":"official","path":"src/scripts/create_relevancy_matrix.py","file_url":"https://github.com/mwray/Semantic-Video-Retrieval/blob/HEAD/src/scripts/create_relevancy_matrix.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a3d83cec1646b646"}},{"code_sha256_prefix":"58dd367646b6a0b2","entry":"get_col_name","repo":"mwray/Semantic-Video-Retrieval","repo_kind":"official","path":"src/scripts/create_relevancy_matrix.py","file_url":"https://github.com/mwray/Semantic-Video-Retrieval/blob/HEAD/src/scripts/create_relevancy_matrix.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58dd367646b6a0b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}