{"url":"/dataset/grasp","name":"GraSP","full_name":"Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies","description_markdown":"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 enables a multi-level comprehension of surgical activities, encompassing long-term tasks such as surgical phases and steps 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, we demonstrate the impact of including segmentation annotations in short-term recognition tasks, highlight the varying granularity requirements of each task, and establish TAPIS's superiority over previously proposed baselines and conventional CNN-based models. Additionally, we validate the robustness of our method across multiple public benchmarks, confirming the reliability and applicability of our dataset. This work represents a significant step forward in Endoscopic Vision, offering a novel and comprehensive framework for future research towards a holistic understanding of surgical procedures.","description_withheld":null,"homepage":"https://github.com/BCV-Uniandes/GraSP/tree/main","introduced_date":"2024-01-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/pixel-wise-recognition-for-holistic-surgical","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","first_author":"Nicolás Ayobi","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Action Localization","url":"/task/action-localization","datasets_with_task":"/datasets/task/action-localization"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"Surgical phase recognition","url":"/task/surgical-phase-recognition","datasets_with_task":"/datasets/task/surgical-phase-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GraSP"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/surgical-phase-recognition-on-grasp","task":"Surgical phase recognition","dataset_variant":"GraSP","rows":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MuST","paper":"/paper/must-multi-scale-transformers-for-surgical","metrics":{"mAP":"79.14"},"code_links":[{"title":"BCV-Uniandes/MuST","url":"https://github.com/BCV-Uniandes/MuST"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/must-multi-scale-transformers-for-surgical","title":"MuST: Multi-Scale Transformers for Surgical Phase Recognition","date":"2024-07-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pixel-wise-recognition-for-holistic-surgical","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","date":"2024-01-20","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":7,"samples_unverified":6,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":13,"samples_ran":7,"samples_unverified":6,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}