{"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/visual-semantic-role-labeling-for-video","title":"Visual Semantic Role Labeling for Video Understanding","arxiv_id":"2104.00990","date":"2021-04-02","proceeding":"CVPR 2021 1","authors":["Arka Sadhu","Tanmay Gupta","Mark Yatskar","Ram Nevatia","Aniruddha Kembhavi"],"abstract":"We propose a new framework for understanding and representing related salient events in a video using visual semantic role labeling. We represent videos as a set of related events, wherein each event consists of a verb and multiple entities that fulfill various roles relevant to that event. To study the challenging task of semantic role labeling in videos or VidSRL, we introduce the VidSitu benchmark, a large-scale video understanding data source with $29K$ $10$-second movie clips richly annotated with a verb and semantic-roles every $2$ seconds. Entities are co-referenced across events within a movie clip and events are connected to each other via event-event relations. Clips in VidSitu are drawn from a large collection of movies (${\\sim}3K$) and have been chosen to be both complex (${\\sim}4.2$ unique verbs within a video) as well as diverse (${\\sim}200$ verbs have more than $100$ annotations each). We provide a comprehensive analysis of the dataset in comparison to other publicly available video understanding benchmarks, several illustrative baselines and evaluate a range of standard video recognition models. Our code and dataset is available at vidsitu.org.","url_abs":"https://arxiv.org/abs/2104.00990v1","url_pdf":"https://arxiv.org/pdf/2104.00990v1.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":"visual-semantic-role-labeling-for-video","repo_url":"https://github.com/TheShadow29/VidSitu","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"video-recognition","task_name":"Video Recognition"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[{"slug":"vidsitu","name":"VidSitu","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.00990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00990"}},"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/TheShadow29/VidSitu","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"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":"4d2f5f7e7d5fc1a1","entry":"get_name_from_inst","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"main_dist.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/main_dist.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d2f5f7e7d5fc1a1"}},{"code_sha256_prefix":"bb2ee2eda144860b","entry":"arg_mapper","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"vidsitu_code/evl_fns.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/vidsitu_code/evl_fns.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":"bb2ee2eda144860b"}},{"code_sha256_prefix":"783738a17e5778da","entry":"collate_dct_lst_naive","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"vidsitu_code/evl_fns.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/vidsitu_code/evl_fns.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":"783738a17e5778da"}},{"code_sha256_prefix":"0fd9228e4e9231e0","entry":"enclose_ag","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"vidsitu_code/dat_loader.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/vidsitu_code/dat_loader.py","link_basis":"harvester_set","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":"0fd9228e4e9231e0"}},{"code_sha256_prefix":"b32761c4fc18d6c4","entry":"end_ag","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"vidsitu_code/dat_loader.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/vidsitu_code/dat_loader.py","link_basis":"harvester_set","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":"b32761c4fc18d6c4"}},{"code_sha256_prefix":"b11ee0a6f802aabd","entry":"read_file_with_assertion","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"prep_data/dwn_yt.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/prep_data/dwn_yt.py","link_basis":"harvester_set","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":"b11ee0a6f802aabd"}},{"code_sha256_prefix":"3b568ae652a0217f","entry":"read_file_with_assertion","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"vidsitu_code/evl_fns.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/vidsitu_code/evl_fns.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":"3b568ae652a0217f"}},{"code_sha256_prefix":"ba87f2f7b1e31bc3","entry":"rem_mdl","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"vidsitu_code/feat_extractor.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/vidsitu_code/feat_extractor.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":"ba87f2f7b1e31bc3"}},{"code_sha256_prefix":"7425b7ac40dc3b30","entry":"st_ag","repo":"TheShadow29/VidSitu","repo_kind":"official","path":"vidsitu_code/dat_loader.py","file_url":"https://github.com/TheShadow29/VidSitu/blob/HEAD/vidsitu_code/dat_loader.py","link_basis":"harvester_set","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":"7425b7ac40dc3b30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}