{"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/epic-kitchens-visor-benchmark-video","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","arxiv_id":"2209.13064","date":"2022-09-26","proceeding":null,"authors":["Ahmad Darkhalil","Dandan Shan","Bin Zhu","Jian Ma","Amlan Kar","Richard Higgins","Sanja Fidler","David Fouhey","Dima Damen"],"abstract":"We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, for scalability and quality. In total, we publicly release 272K manual semantic masks of 257 object classes, 9.9M interpolated dense masks, 67K hand-object relations, covering 36 hours of 179 untrimmed videos. Along with the annotations, we introduce three challenges in video object segmentation, interaction understanding and long-term reasoning. For data, code and leaderboards: http://epic-kitchens.github.io/VISOR","url_abs":"https://arxiv.org/abs/2209.13064v1","url_pdf":"https://arxiv.org/pdf/2209.13064v1.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":"epic-kitchens-visor-benchmark-video","repo_url":"https://github.com/epic-kitchens/visor-hos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"epic-kitchens-visor-benchmark-video","repo_url":"https://github.com/epic-kitchens/visor-vos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"epic-kitchens-visor-benchmark-video","repo_url":"https://github.com/epic-kitchens/visor-wdtcf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"visor","name":"VISOR - Semi supervised video object segmentation","full_name":"val"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.13064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.13064"}},"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":"deterministic:regex_extraction","url":"https://github.com/epic-kitchens/VISOR-HOS","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/epic-kitchens/VISOR-WDTCF","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/epic-kitchens/visor-hos","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/epic-kitchens/visor-vos","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/epic-kitchens/visor-wdtcf","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":5,"ran_violates":1},"by_repo_kind":{"official":{"samples":7,"ran":7,"repositories":2}},"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":"3a8c99d4a48e21e9","entry":"adjust_learning_rate","repo":"epic-kitchens/visor-vos","repo_kind":"official","path":"train_stm_baseline.py","file_url":"https://github.com/epic-kitchens/visor-vos/blob/HEAD/train_stm_baseline.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a8c99d4a48e21e9"}},{"code_sha256_prefix":"8307701e7f9f0c74","entry":"filter_sequences_with_less_than_k","repo":"epic-kitchens/visor-vos","repo_kind":"official","path":"visor_to_davis.py","file_url":"https://github.com/epic-kitchens/visor-vos/blob/HEAD/visor_to_davis.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8307701e7f9f0c74"}},{"code_sha256_prefix":"7066bcdcb77acc81","entry":"find_number_of_images_per_seq","repo":"epic-kitchens/visor-vos","repo_kind":"official","path":"visor_to_davis.py","file_url":"https://github.com/epic-kitchens/visor-vos/blob/HEAD/visor_to_davis.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7066bcdcb77acc81"}},{"code_sha256_prefix":"629e67d3ca344b17","entry":"get_category","repo":"epic-kitchens/VISOR-WDTCF","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/epic-kitchens/VISOR-WDTCF/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"629e67d3ca344b17"}},{"code_sha256_prefix":"08706bf9aeab566d","entry":"get_cats","repo":"epic-kitchens/VISOR-WDTCF","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/epic-kitchens/VISOR-WDTCF/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"08706bf9aeab566d"}},{"code_sha256_prefix":"1c95c0ea4660b5e1","entry":"get_sequence_objects","repo":"epic-kitchens/visor-vos","repo_kind":"official","path":"visor_to_davis.py","file_url":"https://github.com/epic-kitchens/visor-vos/blob/HEAD/visor_to_davis.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c95c0ea4660b5e1"}},{"code_sha256_prefix":"999140d26e677bf7","entry":"transfer_noun","repo":"epic-kitchens/VISOR-WDTCF","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/epic-kitchens/VISOR-WDTCF/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"999140d26e677bf7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}