{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:58:40Z","timestamp":1775627920932,"version":"3.50.1"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[[2025,12,3]]},"DOI":"10.1109\/icmla66185.2025.00031","type":"proceedings-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:54:58Z","timestamp":1775591698000},"page":"192-199","source":"Crossref","is-referenced-by-count":0,"title":["Accurate Polyp Sizing via Attention-Guided Parallel CNN-ViT Depth and Learned Scale"],"prefix":"10.1109","author":[{"given":"Alimire","family":"Nabijiang","sequence":"first","affiliation":[{"name":"University of Massachusetts Lowell,Miner School of Computer &amp; Information Sciences,USA"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University School of Medicine,Shanghai Tenth People&#x2019;s Hospital,China"}]},{"given":"Jiao","family":"Feng","sequence":"additional","affiliation":[{"name":"Tongji University School of Medicine,Shanghai Tenth People&#x2019;s Hospital,China"}]},{"given":"QiLei","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell,Miner School of Computer &amp; Information Sciences,USA"}]},{"given":"Yu","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell,Miner School of Computer &amp; Information Sciences,USA"}]},{"given":"BenYuan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Massachusetts Lowell,Miner School of Computer &amp; Information Sciences,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2022-327736"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00535-021-01776-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.14309\/ajg.0000000000000544"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2023.10.012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v21.i2.623"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2015.08.082"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00384-015-2203-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dld.2010.12.015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2014.01.053"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/den.14318"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1117\/1.JBO.26.9.096002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1111\/den.14351"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1055\/a-2502-9733"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2020.03.1787"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1055\/a-2077-7398"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1111\/den.14318"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635184"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1055\/a-2189-7036"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-05251-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_62"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34048-2_61"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/21681163.2021.2004445"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01962-w"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00077"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10121416"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_27"},{"key":"ref28","article-title":"Depth pro: Sharp monocular metric depth in less than a second","author":"Bochkovskii","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01945"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_27"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref35","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Bhat","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3352390"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_68"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1117\/12.2513093"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2021-324510"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.26599\/air.2023.9150015"},{"key":"ref42","article-title":"MAF-Net: Multi-branch anchor-free detector for polyp localization and classification in colonoscopy","volume-title":"International Conference on Medical Imaging with Deep Learning","author":"Sun","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00148"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3147686"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00056"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref49","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref52","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume":"27","author":"Eigen","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102956"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03359-0"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3628473"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1975.8"}],"event":{"name":"2025 International Conference on Machine Learning and Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Machine Learning and Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471302\/11471304\/11471332.pdf?arnumber=11471332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:18:59Z","timestamp":1775625539000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/icmla66185.2025.00031","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}