{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:12:58Z","timestamp":1783437178429,"version":"3.54.6"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Hong Kong Research Grants Council (RGC)","doi-asserted-by":"publisher","award":["CRF C4026-21GF,CRF C4063-18G"],"award-info":[{"award-number":["CRF C4026-21GF,CRF C4063-18G"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006355","name":"Shun Hing Institute of Advanced Engineering","doi-asserted-by":"publisher","award":["BME-pl-21\/8115064"],"award-info":[{"award-number":["BME-pl-21\/8115064"]}],"id":[{"id":"10.13039\/501100006355","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160403","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"6859-6865","source":"Crossref","is-referenced-by-count":27,"title":["Surgical-VQLA:Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery"],"prefix":"10.1109","author":[{"given":"Long","family":"Bai","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong (CUHK),Dept. of Electronic Engineering,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mobarakol","family":"Islam","sequence":"additional","affiliation":[{"name":"University College,Wellcome\/EPSRC Centre for Interventional and Surgical Sciences (WEISS),London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalithkumar","family":"Seenivasan","sequence":"additional","affiliation":[{"name":"National University of Singapore,Dept. of Biomedical Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong (CUHK),Dept. of Electronic Engineering,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-98390-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_4"},{"issue":"6","key":"ref3","first-page":"12","article-title":"Vr and ar applications in medical practice and education","volume":"64","author":"Hsieh","year":"2017","journal-title":"Hu Li Za Zhi"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/0142159X.2017.1391373"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3109\/10929080600989189"},{"key":"ref6","article-title":"Visu- albert: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Human-adversarial visual question answering","volume":"34","author":"Sheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11276-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.09.008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104165"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146544"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3206148"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","article-title":"Multimodal learning with deep boltzmann machines","volume":"25","author":"Srivastava","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Gated multimodal units for information fusion","author":"Arevalo","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"2018 robotic scene segmentation challenge","author":"Allan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_60"},{"key":"ref26","article-title":"2017 robotic instrument segmentation challenge","author":"Allan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Faster r-cnn: Towards real- time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160403.pdf?arnumber=10160403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:24:52Z","timestamp":1710368692000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160403","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}