{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:24Z","timestamp":1778048544963,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00790","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8188-8198","source":"Crossref","is-referenced-by-count":0,"title":["SurgXBench: Explainable Vision-Language Model Benchmark for Surgery"],"prefix":"10.1109","author":[{"given":"Jiajun","family":"Cheng","sequence":"first","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianwu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sainan","family":"Liu","sequence":"additional","affiliation":[{"name":"Intel Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofan","family":"Yu","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi","family":"Prakash","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick J.","family":"Codd","sequence":"additional","affiliation":[{"name":"Duke University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan Elliott","family":"Katz","sequence":"additional","affiliation":[{"name":"University of Miami"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Lin","sequence":"additional","affiliation":[{"name":"Arizona State University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10331-5_41"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/data10010007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.09.003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s44222-025-00294-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abi8017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206462"},{"key":"ref12","first-page":"2376","article-title":"Counterfactual visual explanations","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Goyal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.473"},{"key":"ref15","author":"Jin","year":"2024","journal-title":"Surgical-llava: Toward surgical scenario understanding via large language and vision models"},{"key":"ref16","author":"Li","year":"2024","journal-title":"Llava-surg: towards multimodal surgical assistant via structured surgical video learning"},{"key":"ref17","first-page":"12888","article-title":"Blip: Bootstrapping language-image pretraining for unified vision-language understanding and generation","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341556"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3096156"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197425"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433"},{"key":"ref23","author":"Powers","year":"2020","journal-title":"Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation"},{"key":"ref24","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref25","author":"Rau","year":"2025","journal-title":"Systematic evaluation of large vision-language models for surgical artificial intelligence"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1366"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101920"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref29","author":"Stan","year":"2024","journal-title":"Lvlm-interpret: An interpretability tool for large vision-language models"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref32","author":"Twinanda","year":"2022","journal-title":"Cholect50: A benchmark for surgical action triplet recognition"},{"key":"ref33","author":"Wang","year":"2025","journal-title":"Surgvidlm: Towards multi-grained surgical video understanding with large language model"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611898"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adt0684"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_29"},{"key":"ref38","article-title":"Procedure-aware surgical video-language pretraining with hierarchical knowledge augmentation","volume-title":"Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS)","author":"Yuan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103644"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01657-x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.115"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12020237"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492238.pdf?arnumber=11492238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:09:45Z","timestamp":1778047785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00790","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}