{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:27Z","timestamp":1766061687868,"version":"3.48.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247452","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"20912-20919","source":"Crossref","is-referenced-by-count":0,"title":["SurgiPose: Estimating Surgical Tool Kinematics from Monocular Video for Surgical Robot Learning"],"prefix":"10.1109","author":[{"given":"Juo-Tung","family":"Chen","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Dept. of Mechanical Engineering,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"XinHao","family":"Chen","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Dept. of Mechanical Engineering,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji Woong","family":"Kim","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Dept. of Mechanical Engineering,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul Maria","family":"Scheikl","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Dept. of Mechanical Engineering,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard Jaepyeong","family":"Cha","sequence":"additional","affiliation":[{"name":"Optosurgical,Columbia,USA,21046"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Axel","family":"Krieger","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Dept. of Mechanical Engineering,Baltimore,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s21165412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC202255925.2022.9922725"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00937-3_32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-019-07281-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544960"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR63436.2024.10585751"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3335693"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2022.3214439"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3410297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211032721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3382529"},{"article-title":"Openvla: An open-source vision-language-action model","year":"2024","author":"Kim","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref15","article-title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","volume-title":"CoRR","volume":"abs\/2403.05949","author":"Schmidgall","year":"2024"},{"article-title":"Fiducial marker design and detection for locating surgical instrument in images","year":"2016","author":"Zhao","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561249"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CACS50047.2020.9289718"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594471"},{"key":"ref20","first-page":"289","article-title":"3d pose estimation with depth camera for markerless computer assisted orthopaedic surgery","volume":"3","author":"Ogor","year":"2019","journal-title":"CAOS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913507796"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46720-7_45"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2794439"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/s24113355"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202200188"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_60"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00170"},{"article-title":"Differentiable robot rendering","volume-title":"8th Annual Conference on Robot Learning","author":"Liu","key":"ref28"},{"article-title":"Diff-dope: Differentiable deep object pose estimation","year":"2023","author":"Tremblay","key":"ref29"},{"key":"ref30","first-page":"715","article-title":"Megapose: 6d pose estimation of novel objects via render & compare","author":"Labb\u00e9","year":"2023"},{"article-title":"Sam 2: Segment anything in images and videos","year":"2024","author":"Ravi","key":"ref31"},{"issue":"4","key":"ref32","article-title":"3d gaussian splatting for real-time radiance field rendering","volume-title":"ACM Transactions on Graphics","volume":"42","author":"Kerbl","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907809"},{"article-title":"Surgical robot transformer (SRT): Imitation learning for surgical tasks","volume-title":"8th Annual Conference on Robot Learning","author":"Kim","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Tan","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103674"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247452.pdf?arnumber=11247452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:38:27Z","timestamp":1766061507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247452","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}