{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T20:14:29Z","timestamp":1779308069403,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3692813","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:58:44Z","timestamp":1778788724000},"page":"74030-74047","source":"Crossref","is-referenced-by-count":0,"title":["EfficientEndoSeg: A Lightweight YOLOv5-Based Framework for Endoscopic Surgical Instrument Segmentation and Skill-Related Motion Analysis"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9060-4769","authenticated-orcid":false,"given":"Thai Dinh","family":"Kim","sequence":"first","affiliation":[{"name":"International School, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1353-3367","authenticated-orcid":false,"given":"Quang-Anh","family":"Nguyen-Duc","sequence":"additional","affiliation":[{"name":"International School, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh-Duc","family":"Pham","sequence":"additional","affiliation":[{"name":"Computer Vision and Robotics Laboratory, International School, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3511-5591","authenticated-orcid":false,"given":"Duy-Tung","family":"Doan","sequence":"additional","affiliation":[{"name":"School of Communication and Technology, Hanoi University of Science and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manh-Hung","family":"Nguyen","sequence":"additional","affiliation":[{"name":"International School, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5320-6975","authenticated-orcid":false,"given":"Xuan-Hai","family":"Le","sequence":"additional","affiliation":[{"name":"International School, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1055-2875","authenticated-orcid":false,"given":"Ngoc-Thanh","family":"Pham","sequence":"additional","affiliation":[{"name":"International School, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSSE58758.2023.10227217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40846-019-00503-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.09.003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103945"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2022.3214377"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9629914"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10979-w"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00081"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-84295-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197425"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3046258"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102569"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-025-07456-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/make5040083"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02404-2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_57"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2019.8856791"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101920"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2025.103227"},{"key":"ref23","article-title":"Ultralytics YOLOv8: Real-time object detection and segmentation","author":"Jocher","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0724"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref27","article-title":"Ultralytics\/YOLOv5: V7.0\u2014YOLOv5 SOTA realtime instance segmentation","author":"Jocher","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"ref29","article-title":"A2-Nets: Double attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"31","author":"Chen"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3365501"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2969885"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1515\/amcs-2016-0031"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2478\/v10006-010-0024-4"},{"key":"ref35","article-title":"Single- and multi-task architectures for surgical workflow challenge at M2CAI 2016","author":"Twinanda","year":"2016","journal-title":"arXiv:1610.08844"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref37","first-page":"13610","article-title":"Tap-vid: A benchmark for tracking any point in a video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Doersch"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_57"},{"key":"ref39","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021","journal-title":"arXiv:2105.15203"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3248089"},{"key":"ref41","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref43","article-title":"Ultralytics YOLOv11: Next-generation real-time object detection models","author":"Jocher","year":"2024"},{"key":"ref44","article-title":"YOLOv12: Attention-centric real-time object detectors","author":"Tian","year":"2025","journal-title":"arXiv:2502.12524"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11516624.pdf?arnumber=11516624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:54:08Z","timestamp":1779306848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11516624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3692813","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}