{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T15:41:03Z","timestamp":1791819663174,"version":"4.3.4"},"reference-count":51,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"US National Institutes of Health","doi-asserted-by":"crossref","award":["R01 CA240808"],"award-info":[{"award-number":["R01 CA240808"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Health"],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1088\/3049-477x\/ae291a","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:47:23Z","timestamp":1765234043000},"page":"015003","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["TSMS-SAM2: multi-scale temporal sampling augmentation and memory-splitting pruning for promptable video object segmentation and tracking in surgical scenarios"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1431-7191","authenticated-orcid":true,"given":"Guoping","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7664-7257","authenticated-orcid":true,"given":"Hua-Chieh","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"mlhealthae291abib1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3391743","type":"journal-article","article-title":"Video object segmentation and tracking: a survey","volume":"11","author":"Yao","year":"2020","journal-title":"ACM Trans. Intell. Sys. Technol."},{"key":"mlhealthae291abib2","article-title":"Segment anything for video: a comprehensive review of video object segmentation and tracking from past to future","author":"Xu","year":"2025","type":"preprint"},{"key":"mlhealthae291abib3","first-page":"4015","type":"conference-proceedings","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"mlhealthae291abib4","article-title":"SAM 2: segment anything in images and videos","author":"Ravi","year":"2024","type":"preprint"},{"key":"mlhealthae291abib5","article-title":"MedSAM2: segment Anything in 3D Medical Images and Videos","author":"Ma","year":"2025","type":"preprint"},{"key":"mlhealthae291abib6","article-title":"Medical SAM 2: segment medical images as video via segment anything model 2","author":"Zhu","year":"2024","type":"preprint"},{"key":"mlhealthae291abib7","first-page":"11302","type":"conference-proceedings","article-title":"One-prompt to segment all medical images","author":"Wu","year":"2024"},{"key":"mlhealthae291abib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109347","type":"journal-article","article-title":"A comprehensive survey of image augmentation techniques for deep learning","volume":"137","author":"Xu","year":"2023","journal-title":"Pattern Recogn."},{"key":"mlhealthae291abib9","first-page":"2918","type":"conference-proceedings","article-title":"Simple copy-paste is a strong data augmentation method for instance segmentation","author":"Ghiasi","year":"2021"},{"key":"mlhealthae291abib10","doi-asserted-by":"publisher","first-page":"81039","DOI":"10.1007\/s11042-024-18829-1","type":"journal-article","article-title":"Fast-SegNet: fast semantic segmentation network for small objects","volume":"83","author":"Zhang","year":"2024","journal-title":"Multimedia Tools Appl."},{"key":"mlhealthae291abib11","first-page":"702","type":"conference-proceedings","article-title":"Randaugment: Practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"mlhealthae291abib12","article-title":"mixup: beyond empirical risk minimization","author":"Zhang","year":"2017","type":"preprint"},{"key":"mlhealthae291abib13","first-page":"6023","type":"conference-proceedings","article-title":"Cutmix: regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"mlhealthae291abib14","first-page":"15323","type":"conference-proceedings","article-title":"Continuous copy-paste for one-stage multi-object tracking and segmentation","author":"Xu","year":"2021"},{"key":"mlhealthae291abib15","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1007\/s11263-023-01807-9","type":"journal-article","article-title":"Instaboost++: visual coherence principles for unified 2d\/3d instance level data augmentation","volume":"131","author":"Sun","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"mlhealthae291abib16","first-page":"230","type":"conference-proceedings","article-title":"Large scale labelled video data augmentation for semantic segmentation in driving scenarios","author":"Budvytis","year":"2017"},{"key":"mlhealthae291abib17","first-page":"6202","type":"conference-proceedings","article-title":"Slowfast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"key":"mlhealthae291abib18","article-title":"Surgical SAM 2: real-time segment anything in surgical video by efficient frame pruning","author":"Liu","year":"2024","type":"preprint"},{"key":"mlhealthae291abib19","first-page":"3417","type":"conference-proceedings","article-title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","author":"Mei","year":"2025"},{"key":"mlhealthae291abib20","article-title":"Videomix: rethinking data augmentation for video classification","author":"Yun","year":"2020","type":"preprint"},{"key":"mlhealthae291abib21","first-page":"242","type":"conference-proceedings","article-title":"Learn2augment: learning to composite videos for data augmentation in action recognition","author":"Gowda","year":"2022"},{"key":"mlhealthae291abib22","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.1109\/TKDE.2019.2947442","type":"journal-article","article-title":"Feature re-learning with data augmentation for video relevance prediction","volume":"33","author":"Dong","year":"2019","journal-title":"IEEE Trans. Knowledge Data Eng."},{"key":"mlhealthae291abib23","doi-asserted-by":"publisher","first-page":"93","DOI":"10.3390\/fi14030093","type":"journal-article","article-title":"Survey on videos data augmentation for deep learning models","volume":"14","author":"Cauli","year":"2022","journal-title":"Future Internet"},{"key":"mlhealthae291abib24","article-title":"Pathformer: multi-scale transformers with adaptive pathways for time series forecasting","author":"Chen","year":"2024","type":"preprint"},{"key":"mlhealthae291abib25","doi-asserted-by":"publisher","first-page":"10466","DOI":"10.1109\/TPAMI.2024.3443141","type":"journal-article","article-title":"A survey on graph neural networks for time series: forecasting, classification, imputation, and anomaly detection","volume":"46","author":"Jin","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlhealthae291abib26","first-page":"1933","type":"conference-proceedings","article-title":"Convolutional two-stream network fusion for video action recognition","author":"Feichtenhofer","year":"2016"},{"key":"mlhealthae291abib27","first-page":"27","type":"conference-proceedings","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014"},{"key":"mlhealthae291abib28","article-title":"MSPred: video prediction at multiple spatio-temporal scales with hierarchical recurrent networks","author":"Villar-Corrales","type":"preprint"},{"key":"mlhealthae291abib29","first-page":"4554","type":"conference-proceedings","article-title":"Exploring spatial-temporal multi-frequency analysis for high-fidelity and temporal-consistency video prediction","author":"Jin","year":"2020"},{"key":"mlhealthae291abib30","first-page":"803","type":"conference-proceedings","article-title":"Temporal relational reasoning in videos","author":"Zhou","year":"2018"},{"key":"mlhealthae291abib31","first-page":"29441","type":"conference-proceedings","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","author":"Ryali","year":"2023"},{"key":"mlhealthae291abib32","first-page":"16000","type":"conference-proceedings","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"mlhealthae291abib33","first-page":"89","author":"Atkinson","year":"1968","type":"book"},{"key":"mlhealthae291abib34","article-title":"2017 robotic instrument segmentation challenge","author":"Allan","year":"2019","type":"preprint"},{"key":"mlhealthae291abib35","article-title":"2018 robotic scene segmentation challenge","author":"Allan","year":"2020","type":"preprint"},{"key":"mlhealthae291abib36","first-page":"595","type":"conference-proceedings","article-title":"Isinet: an instance-based approach for surgical instrument segmentation","author":"Gonz\u00e1lez","year":"2020"},{"key":"mlhealthae291abib37","article-title":"Ternausnet: u-net with vgg11 encoder pre-trained on imagenet for image segmentation","author":"Iglovikov","year":"2018","type":"preprint"},{"key":"mlhealthae291abib38","first-page":"440","type":"book","article-title":"Incorporating temporal prior from motion flow for instrument segmentation in minimally invasive surgery video","author":"Jin","year":"2019"},{"key":"mlhealthae291abib39","first-page":"6191","type":"conference-proceedings","article-title":"From forks to forceps: a new framework for instance segmentation of surgical instruments","author":"Baby","year":"2023"},{"key":"mlhealthae291abib40","first-page":"1","type":"conference-proceedings","article-title":"Matis: masked-attention transformers for surgical instrument segmentation","author":"Ayobi","year":"2023"},{"key":"mlhealthae291abib41","article-title":"Track anything: segment anything meets videos","author":"Yang","year":"2023","type":"preprint"},{"key":"mlhealthae291abib42","article-title":"Personalize segment anything model with one shot","author":"Zhang","year":"2023","type":"preprint"},{"key":"mlhealthae291abib43","first-page":"5188","type":"conference-proceedings","article-title":"Video instance segmentation","author":"Yang","year":"2019"},{"key":"mlhealthae291abib44","first-page":"1290","type":"conference-proceedings","article-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng","year":"2022"},{"key":"mlhealthae291abib45","first-page":"6890","type":"conference-proceedings","article-title":"Surgicalsam: efficient class promptable surgical instrument segmentation","author":"Yue","year":"2024"},{"key":"mlhealthae291abib46","first-page":"640","type":"conference-proceedings","article-title":"Xmem: long-term video object segmentation with an Atkinson-Shiffrin memory model","author":"Cheng","year":"2022"},{"key":"mlhealthae291abib47","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","type":"journal-article","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"mlhealthae291abib48","first-page":"430","type":"conference-proceedings","article-title":"Machine learning for high-speed corner detection","author":"Rosten","year":"2006"},{"key":"mlhealthae291abib49","first-page":"2564","type":"conference-proceedings","article-title":"ORB: an efficient alternative to SIFT or SURF","author":"Rublee","year":"2011"},{"key":"mlhealthae291abib50","first-page":"402","type":"conference-proceedings","article-title":"Raft: recurrent all-pairs field transforms for optical flow Book Raft: Recurrent All-pairs Field Transforms for Optical Flow","author":"Teed","year":"2020"},{"key":"mlhealthae291abib51","doi-asserted-by":"publisher","first-page":"2491","DOI":"10.1080\/14767058.2019.1668923","type":"conference-proceedings","article-title":"Associating objects with transformers for video object segmentation","volume":"vol 34","author":"Yang","year":"2021"}],"container-title":["Machine Learning: Health"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:35:43Z","timestamp":1768818943000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/3049-477X\/ae291a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,19]]},"published-print":{"date-parts":[[2026,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/3049-477x\/ae291a","relation":{},"ISSN":["3049-477X"],"issn-type":[{"value":"3049-477X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]},"assertion":[{"value":"TSMS-SAM2: multi-scale temporal sampling augmentation and memory-splitting pruning for promptable video object segmentation and tracking in surgical scenarios","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Health","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-08-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}