{"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/procedure-aware-surgical-video-language","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","arxiv_id":"2410.00263","date":"2024-09-30","proceeding":null,"authors":["Kun Yuan","Vinkle Srivastav","Nassir Navab","Nicolas Padoy"],"abstract":"Surgical video-language pretraining (VLP) faces unique challenges due to the knowledge domain gap and the scarcity of multi-modal data. This study aims to bridge the gap by addressing issues regarding textual information loss in surgical lecture videos and the spatial-temporal challenges of surgical VLP. We propose a hierarchical knowledge augmentation approach and a novel Procedure-Encoded Surgical Knowledge-Augmented Video-Language Pretraining (PeskaVLP) framework to tackle these issues. The knowledge augmentation uses large language models (LLM) for refining and enriching surgical concepts, thus providing comprehensive language supervision and reducing the risk of overfitting. PeskaVLP combines language supervision with visual self-supervision, constructing hard negative samples and employing a Dynamic Time Warping (DTW) based loss function to effectively comprehend the cross-modal procedural alignment. Extensive experiments on multiple public surgical scene understanding and cross-modal retrieval datasets show that our proposed method significantly improves zero-shot transferring performance and offers a generalist visual representation for further advancements in surgical scene understanding.","url_abs":"https://arxiv.org/abs/2410.00263v1","url_pdf":"https://arxiv.org/pdf/2410.00263v1.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":"procedure-aware-surgical-video-language","repo_url":"https://github.com/camma-public/peskavlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"procedure-aware-surgical-video-language","repo_url":"https://github.com/camma-public/surgvlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.00263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00263"}},"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/CAMMA-public/SurgVLP","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/camma-public/peskavlp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/camma-public/surgvlp","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_violates":1,"ran_fixture":1,"ran_honours":1,"unverified":6},"by_repo_kind":{"listed":{"samples":15,"ran":9,"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":15,"samples":[{"code_sha256_prefix":"8ca1275e7e3d3105","entry":"AllGather","repo":"camma-public/peskavlp","repo_kind":"listed","path":"codes/engines/engine_phase_video_hierarchy.py","file_url":"https://github.com/camma-public/peskavlp/blob/HEAD/codes/engines/engine_phase_video_hierarchy.py","link_basis":"first_harvest_node","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":"8ca1275e7e3d3105"}},{"code_sha256_prefix":"b00380055f8cdd09","entry":"bert_token_collate_fn","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/codes/datasets/utils.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/codes/datasets/utils.py","link_basis":"first_harvest_node","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":"b00380055f8cdd09"}},{"code_sha256_prefix":"157585dc6ae8a498","entry":"crop_boxes","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/codes/datasets/transform.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/codes/datasets/transform.py","link_basis":"first_harvest_node","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":"157585dc6ae8a498"}},{"code_sha256_prefix":"a6f06c2bfe4c6098","entry":"cumulative_sum","repo":"camma-public/peskavlp","repo_kind":"listed","path":"codes/engines/engine_phase_video_hierarchy.py","file_url":"https://github.com/camma-public/peskavlp/blob/HEAD/codes/engines/engine_phase_video_hierarchy.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6f06c2bfe4c6098"}},{"code_sha256_prefix":"45cc344e60f640a1","entry":"get_padding_shape","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/codes/models/utils.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/codes/models/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45cc344e60f640a1"}},{"code_sha256_prefix":"37cabfc73f71318b","entry":"get_sequence","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/codes/datasets/utils.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/codes/datasets/utils.py","link_basis":"first_harvest_node","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":"37cabfc73f71318b"}},{"code_sha256_prefix":"1df9a5ffd9b38c34","entry":"pil_loader","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/codes/datasets/recognition_frame.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/codes/datasets/recognition_frame.py","link_basis":"harvester_set","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":"1df9a5ffd9b38c34"}},{"code_sha256_prefix":"04ae3eaf0d9d9378","entry":"random_crop","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/codes/datasets/transform.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/codes/datasets/transform.py","link_basis":"first_harvest_node","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":"04ae3eaf0d9d9378"}},{"code_sha256_prefix":"8b52c4f275af3fc5","entry":"random_short_side_scale_jitter","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/codes/datasets/transform.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/codes/datasets/transform.py","link_basis":"first_harvest_node","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":"8b52c4f275af3fc5"}},{"code_sha256_prefix":"c19215ccf489bbf4","entry":"TrainOneBatch_phase_abstract","repo":"camma-public/peskavlp","repo_kind":"listed","path":"codes/engines/engine_phase_video_hierarchy.py","file_url":"https://github.com/camma-public/peskavlp/blob/HEAD/codes/engines/engine_phase_video_hierarchy.py","link_basis":"first_harvest_node","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":"c19215ccf489bbf4"}},{"code_sha256_prefix":"b6c6f8816d16c800","entry":"build_from_cfg","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/mmcv.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/mmcv.py","link_basis":"first_harvest_node","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":"b6c6f8816d16c800"}},{"code_sha256_prefix":"2ec9ac675733a9ac","entry":"get_model","repo":"camma-public/peskavlp","repo_kind":"listed","path":"codes/engines/engine_phase_video_hierarchy.py","file_url":"https://github.com/camma-public/peskavlp/blob/HEAD/codes/engines/engine_phase_video_hierarchy.py","link_basis":"first_harvest_node","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":"2ec9ac675733a9ac"}},{"code_sha256_prefix":"51ad490245c34c78","entry":"load","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/surgvlp.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/surgvlp.py","link_basis":"first_harvest_node","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":"51ad490245c34c78"}},{"code_sha256_prefix":"4dbe45bb21ca3839","entry":"load_dataset","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/surgvlp.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/surgvlp.py","link_basis":"plan_row","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":"4dbe45bb21ca3839"}},{"code_sha256_prefix":"2c5a6406461abcfa","entry":"tokenize","repo":"CAMMA-public/SurgVLP","repo_kind":"listed","path":"surgvlp/surgvlp.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/surgvlp.py","link_basis":"first_harvest_node","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":"2c5a6406461abcfa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}