{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:21:23Z","timestamp":1773246083857,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1109\/bibm62325.2024.10821976","type":"proceedings-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:12:45Z","timestamp":1736539965000},"page":"3076-3081","source":"Crossref","is-referenced-by-count":4,"title":["SurgFC: Multimodal Surgical Function Calling Framework on the Demand of Surgeons"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Chen","sequence":"first","affiliation":[{"name":"CAIR, HKISI, CAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjian","family":"Luo","sequence":"additional","affiliation":[{"name":"CAIR, HKISI, CAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlin","family":"Wu","sequence":"additional","affiliation":[{"name":"CAIR, HKISI, CAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danny T.M.","family":"Chan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Surgery"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"CAIR, HKISI, CAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastien","family":"Ourselin","sequence":"additional","affiliation":[{"name":"King’s College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Liu","sequence":"additional","affiliation":[{"name":"CAIR, HKISI, CAS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102306"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_44"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00566-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635466"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801703"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3069471"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12553-021-00547-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMRB.2020.3040002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_66"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM58861.2023.10385308"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_45"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_27"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_38"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Llama 2: Open foundation and fine-tuned chat models, 2023","author":"Touvron","year":"2023"},{"key":"ref17","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref19","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref20","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"},{"key":"ref21","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref22","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref23","first-page":"23 716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"key":"ref24","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"issue":"6","key":"ref25","first-page":"7","article-title":"Alpaca: A strong, replicable instruction-following model","volume-title":"Stanford Center for Research on Foundation Models","volume":"3","author":"Taori","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102888"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102803"},{"key":"ref29","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref30","article-title":"mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023"},{"key":"ref31","article-title":"Llava-plus: Learning to use tools for creating multimodal agents","author":"Liu","year":"2023"},{"key":"ref32","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref34","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"}],"event":{"name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","location":"Lisbon, Portugal","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10821710\/10821711\/10821976.pdf?arnumber=10821976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:32Z","timestamp":1736883632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10821976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/bibm62325.2024.10821976","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}