{"id":3254,"date":"2025-08-04T12:50:03","date_gmt":"2025-08-04T12:50:03","guid":{"rendered":"http:\/\/www.labren.org\/mm\/?p=3254"},"modified":"2025-08-05T12:58:01","modified_gmt":"2025-08-05T12:58:01","slug":"%f0%9f%8e%89our-recent-work-surgical-vqla-adversarial-contrastive-learning-for-calibrated-robust-visual-question-localized-answering-in-robotic-surgery-has-been-accepted-by-information-fusion","status":"publish","type":"post","link":"http:\/\/www.labren.org\/mm\/news\/%f0%9f%8e%89our-recent-work-surgical-vqla-adversarial-contrastive-learning-for-calibrated-robust-visual-question-localized-answering-in-robotic-surgery-has-been-accepted-by-information-fusion\/","title":{"rendered":"\ud83c\udf89Our recent work “Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery” has been accepted by Information Fusion!"},"content":{"rendered":"\n

This paper is an extended version of our #ICRA2023<\/strong> Surgical-VQLA. Our method can serve as an effective and reliable tool to assist in surgical education and clinical decision-making by providing more insightful analyses of surgical scenes.<\/p>\n\n\n\n

\u2728 Key Contributions in the journal version:<\/p>\n\n\n\n

– A dual calibration module is proposed to align and normalize multimodal representations. <\/p>\n\n\n\n

– A contrastive training strategy with adversarial examples is employed to enhance robustness.<\/p>\n\n\n\n

– Various optimization function is widely explored.<\/p>\n\n\n\n

– The EndoVis-18-VQLA & EndoVis-17-VQLA datasets are further extended.<\/p>\n\n\n\n

– Our proposed solution presents superior performance and robustness against real-world image corruption.<\/p>\n\n\n\n

Conference Version (ICRA 2023): https:\/\/lnkd.in\/gHscT3eN<\/p>\n\n\n\n

Journal Version (Information Fusion): https:\/\/lnkd.in\/gQNWwHmt<\/p>\n\n\n\n

Code & Dataset: https:\/\/lnkd.in\/g7CTuyAH<\/p>\n\n\n\n

Thank all of the collaborators for their effort: Long Bai<\/a>, Guankun Wang, An Wang<\/a>, and Prof. Hongliang Ren<\/a> from CUHK, Dr. Mobarakol Islam<\/a> from WEISS, UCL, and Dr. Lalithkumar Seenivasan<\/a> from JHU.<\/p>\n\n\n\n

\"No<\/figure>\n\n\n\n
\"No<\/figure>\n\n\n\n
\"No<\/figure>\n","protected":false},"excerpt":{"rendered":"

This paper is an extended version of our #ICRA2023 Surgical-VQLA. Our method can serve as an effective and reliable tool to assist in surgical education and clinical decision-making by providing more insightful analyses of surgical scenes. \u2728 Key Contributions in the journal version: – A dual calibration module is proposed\u2026 Continue reading<\/a><\/p>\n","protected":false},"author":17,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[4],"tags":[126,140,146,142,11,145,118,127,141,144,143],"class_list":["post-3254","post","type-post","status-publish","format-standard","hentry","category-news","tag-cuhk","tag-informationfusion","tag-jhu","tag-multimodal","tag-robotics","tag-surgery","tag-surgicalai","tag-ucl","tag-visionlanguage","tag-visualgrounding","tag-vqa"],"_links":{"self":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3254","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/users\/17"}],"replies":[{"embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/comments?post=3254"}],"version-history":[{"count":1,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3254\/revisions"}],"predecessor-version":[{"id":3255,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/posts\/3254\/revisions\/3255"}],"wp:attachment":[{"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/media?parent=3254"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/categories?post=3254"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.labren.org\/mm\/wp-json\/wp\/v2\/tags?post=3254"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}