{"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/pixel-wise-recognition-for-holistic-surgical","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","arxiv_id":"2401.11174","date":"2024-01-20","proceeding":null,"authors":["Nicolás Ayobi","Santiago Rodríguez","Alejandra Pérez","Isabela Hernández","Nicolás Aparicio","Eugénie Dessevres","Sebastián Peña","Jessica Santander","Juan Ignacio Caicedo","Nicolás Fernández","Pablo Arbeláez"],"abstract":"This paper presents the Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies (GraSP) dataset, a curated benchmark that models surgical scene understanding as a hierarchy of complementary tasks with varying levels of granularity. Our approach encompasses long-term tasks, such as surgical phase and step recognition, and short-term tasks, including surgical instrument segmentation and atomic visual actions detection. To exploit our proposed benchmark, we introduce the Transformers for Actions, Phases, Steps, and Instrument Segmentation (TAPIS) model, a general architecture that combines a global video feature extractor with localized region proposals from an instrument segmentation model to tackle the multi-granularity of our benchmark. Through extensive experimentation in ours and alternative benchmarks, we demonstrate TAPIS's versatility and state-of-the-art performance across different tasks. This work represents a foundational step forward in Endoscopic Vision, offering a novel framework for future research towards holistic surgical scene understanding.","url_abs":"https://arxiv.org/abs/2401.11174v3","url_pdf":"https://arxiv.org/pdf/2401.11174v3.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":"pixel-wise-recognition-for-holistic-surgical","repo_url":"https://github.com/bcv-uniandes/grasp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pixel-wise-recognition-for-holistic-surgical","repo_url":"https://github.com/bcv-uniandes/matis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pixel-wise-recognition-for-holistic-surgical","repo_url":"https://github.com/bcv-uniandes/tapir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"surgical-phase-recognition","task_name":"Surgical phase recognition"}],"methods":[],"datasets_introduced":[{"slug":"grasp","name":"GraSP","full_name":"Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/surgical-phase-recognition-on-grasp","task":"Surgical phase recognition","dataset":"GraSP","model":"TAPIS","rank_in_archive_order":2,"of":2,"metrics":{"mAP":"76.72"},"uses_additional_data":false},{"leaderboard":"/sota/surgical-phase-recognition-on-misaw","task":"Surgical phase recognition","dataset":"MISAW","model":"TAPIS","rank_in_archive_order":2,"of":3,"metrics":{"mAP":"97.14"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.11174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11174"}},"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/bcv-uniandes/grasp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bcv-uniandes/matis","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bcv-uniandes/tapir","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":13,"ran":7,"repositories":3}},"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":1,"samples":[{"code_sha256_prefix":"e1053815b1f94169","entry":"compute_weighted_loss","repo":"bcv-uniandes/grasp","repo_kind":"official","path":"TAPIS/tapis/models/losses.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1053815b1f94169"}},{"code_sha256_prefix":"d97bc90017599f32","entry":"construct_optimizer","repo":"bcv-uniandes/tapir","repo_kind":"official","path":"slowfast/models/optimizer.py","file_url":"https://github.com/bcv-uniandes/tapir/blob/HEAD/slowfast/models/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d97bc90017599f32"}},{"code_sha256_prefix":"e1aeddec06db2326","entry":"eval_epoch","repo":"bcv-uniandes/matis","repo_kind":"official","path":"tools/train_net.py","file_url":"https://github.com/bcv-uniandes/matis/blob/HEAD/tools/train_net.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":"e1aeddec06db2326"}},{"code_sha256_prefix":"c90b5f606f54d4f7","entry":"get_loss_func","repo":"bcv-uniandes/grasp","repo_kind":"official","path":"TAPIS/tapis/models/losses.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c90b5f606f54d4f7"}},{"code_sha256_prefix":"aaac7c46cd146e47","entry":"get_loss_func","repo":"bcv-uniandes/tapir","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/bcv-uniandes/tapir/blob/HEAD/slowfast/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aaac7c46cd146e47"}},{"code_sha256_prefix":"cdefb159d0ccbc07","entry":"get_loss_type","repo":"bcv-uniandes/grasp","repo_kind":"official","path":"TAPIS/tapis/models/losses.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cdefb159d0ccbc07"}},{"code_sha256_prefix":"829565bab809c0f8","entry":"normalize_bbox","repo":"bcv-uniandes/tapir","repo_kind":"official","path":"slowfast/evaluate/convert_coco_anns_to_our_method.py","file_url":"https://github.com/bcv-uniandes/tapir/blob/HEAD/slowfast/evaluate/convert_coco_anns_to_our_method.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"829565bab809c0f8"}},{"code_sha256_prefix":"a4723eab8df61dbe","entry":"attention_pool","repo":"bcv-uniandes/tapir","repo_kind":"official","path":"slowfast/models/attention.py","file_url":"https://github.com/bcv-uniandes/tapir/blob/HEAD/slowfast/models/attention.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":"a4723eab8df61dbe"}},{"code_sha256_prefix":"5803e73c1b7f2a96","entry":"attention_pool","repo":"bcv-uniandes/grasp","repo_kind":"official","path":"TAPIS/tapis/models/attention.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/attention.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":"5803e73c1b7f2a96"}},{"code_sha256_prefix":"156d0bf08e703f3c","entry":"cal_rel_pos_spatial","repo":"bcv-uniandes/grasp","repo_kind":"official","path":"TAPIS/tapis/models/attention.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/attention.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":"156d0bf08e703f3c"}},{"code_sha256_prefix":"bcc1cdae3bb3212c","entry":"drop_path","repo":"bcv-uniandes/grasp","repo_kind":"official","path":"TAPIS/tapis/models/common.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/common.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":"bcc1cdae3bb3212c"}},{"code_sha256_prefix":"5fc6c9c916e0ebc7","entry":"get_rel_pos","repo":"bcv-uniandes/grasp","repo_kind":"official","path":"TAPIS/tapis/models/attention.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/models/attention.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":"5fc6c9c916e0ebc7"}},{"code_sha256_prefix":"d296e9fcbb9a1e04","entry":"get_stem_func","repo":"bcv-uniandes/tapir","repo_kind":"official","path":"slowfast/models/stem_helper.py","file_url":"https://github.com/bcv-uniandes/tapir/blob/HEAD/slowfast/models/stem_helper.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":"d296e9fcbb9a1e04"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}