{"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","title":"Visual Semantic Role Labeling","arxiv_id":"1505.04474","date":"2015-05-17","proceeding":null,"authors":["Saurabh Gupta","Jitendra Malik"],"abstract":"In this paper we introduce the problem of Visual Semantic Role Labeling:\ngiven an image we want to detect people doing actions and localize the objects\nof interaction. Classical approaches to action recognition either study the\ntask of action classification at the image or video clip level or at best\nproduce a bounding box around the person doing the action. We believe such an\noutput is inadequate and a complete understanding can only come when we are\nable to associate objects in the scene to the different semantic roles of the\naction. To enable progress towards this goal, we annotate a dataset of 16K\npeople instances in 10K images with actions they are doing and associate\nobjects in the scene with different semantic roles for each action. Finally, we\nprovide a set of baseline algorithms for this task and analyze error modes\nproviding directions for future work.","url_abs":"http://arxiv.org/abs/1505.04474v1","url_pdf":"http://arxiv.org/pdf/1505.04474v1.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","repo_url":"https://github.com/dreamh1gh/awesome-srl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"visual-semantic-role-labeling","repo_url":"https://github.com/s-gupta/v-coco","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"16k","task_name":"16k"},{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[{"slug":"v-coco","name":"V-COCO","full_name":"Verbs in COCO"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1505.04474","atlas_url":"https://app.syntology.ai/?focus=1505.04474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.04474"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/s-gupta/v-coco","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dreamh1gh/awesome-srl","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"3dc1dc492dbbbf13","entry":"clip_xyxy_to_image","repo":"s-gupta/v-coco","repo_kind":"listed","path":"vsrl_eval.py","file_url":"https://github.com/s-gupta/v-coco/blob/HEAD/vsrl_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3dc1dc492dbbbf13"}},{"code_sha256_prefix":"d5a0b6aba0d66951","entry":"get_overlap","repo":"s-gupta/v-coco","repo_kind":"listed","path":"vsrl_eval.py","file_url":"https://github.com/s-gupta/v-coco/blob/HEAD/vsrl_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d5a0b6aba0d66951"}},{"code_sha256_prefix":"7c16bfea33d37328","entry":"voc_ap","repo":"s-gupta/v-coco","repo_kind":"listed","path":"vsrl_eval.py","file_url":"https://github.com/s-gupta/v-coco/blob/HEAD/vsrl_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c16bfea33d37328"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}