{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:12:59Z","timestamp":1783437179120,"version":"3.54.6"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439957","type":"print"},{"value":"9783031439964","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-43996-4_38","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"397-407","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["CAT-ViL: Co-attention Gated Vision-Language Embedding for\u00a0Visual Question Localized-Answering in\u00a0Robotic Surgery"],"prefix":"10.1007","author":[{"given":"Long","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mobarakol","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"38_CR1","unstructured":"Allan, M., et al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"38_CR2","unstructured":"Allan, M., et al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"38_CR3","unstructured":"Arevalo, J., Solorio, T., Montes-y G\u00f3mez, M., Gonz\u00e1lez, F.A.: Gated multimodal units for information fusion. arXiv preprint arXiv:1702.01992 (2017)"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Seenivasan, L., Ren, H.: Surgical-VQLA: transformer with gated vision-language embedding for visual question localized-answering in robotic surgery. arXiv preprint arXiv:2305.11692 (2023)","DOI":"10.1109\/ICRA48891.2023.10160403"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Thome, N., Cord, M.: BLOCK: bilinear superdiagonal fusion for visual question answering and visual relationship detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8102\u20138109 (2019)","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"38_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"38_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Georgescu, M.I., et al.: Multimodal multi-head convolutional attention with various kernel sizes for medical image super-resolution. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2195\u20132205 (2023)","DOI":"10.1109\/WACV56688.2023.00223"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"38_CR12","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)"},{"issue":"6","key":"38_CR13","first-page":"12","volume":"64","author":"MC Hsieh","year":"2017","unstructured":"Hsieh, M.C., Lin, Y.H.: VR and AR applications in medical practice and education. Hu Li Za Zhi 64(6), 12\u201318 (2017)","journal-title":"Hu Li Za Zhi"},{"key":"38_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-3-030-59716-0_60","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"M Islam","year":"2020","unstructured":"Islam, M., Seenivasan, L., Ming, L.C., Ren, H.: Learning and reasoning with the graph structure representation in robotic surgery. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 627\u2013636. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_60"},{"key":"38_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Kuo, W., Bertsch, F., Li, W., Piergiovanni, A., Saffar, M., Angelova, A.: FindIt: generalized localization with natural language queries. arXiv preprint arXiv:2203.17273 (2022)","DOI":"10.1007\/978-3-031-20059-5_29"},{"key":"38_CR17","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"issue":"5","key":"38_CR18","doi-asserted-by":"publisher","first-page":"220","DOI":"10.3109\/10929080600989189","volume":"11","author":"HC Lin","year":"2006","unstructured":"Lin, H.C., Shafran, I., Yuh, D., Hager, G.D.: Towards automatic skill evaluation: detection and segmentation of robot-assisted surgical motions. Comput. Aided Surg. 11(5), 220\u2013230 (2006)","journal-title":"Comput. Aided Surg."},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Praveen, R.G., et al.: A joint cross-attention model for audio-visual fusion in dimensional emotion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2486\u20132495 (2022)","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"38_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"38_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-031-16449-1_4","volume-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2022","author":"L Seenivasan","year":"2022","unstructured":"Seenivasan, L., Islam, M., Krishna, A., Ren, H.: Surgical-VQA: visual question answering in surgical scenes using transformer. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13437, pp. 33\u201343. Springer, Cham (2022)"},{"key":"38_CR23","doi-asserted-by":"publisher","first-page":"3858","DOI":"10.1109\/LRA.2022.3146544","volume":"7","author":"L Seenivasan","year":"2022","unstructured":"Seenivasan, L., Mitheran, S., Islam, M., Ren, H.: Global-reasoned multi-task learning model for surgical scene understanding. IEEE Robot. Autom. Lett. 7, 3858\u20133865 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"1","key":"38_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-98390-1","volume":"11","author":"D Sharma","year":"2021","unstructured":"Sharma, D., Purushotham, S., Reddy, C.K.: MedFuseNet: an attention-based multimodal deep learning model for visual question answering in the medical domain. Sci. Rep. 11(1), 1\u201318 (2021)","journal-title":"Sci. Rep."},{"key":"38_CR25","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"38_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Wu, Z., Liu, L., Zhang, Y., Mao, M., Lin, L., Li, G.: Multimodal crowd counting with mutual attention transformers. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859777"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., Tao, D., Tian, Q.: Deep modular co-attention networks for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6281\u20136290 (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"issue":"12","key":"38_CR29","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","volume":"29","author":"Z Yu","year":"2018","unstructured":"Yu, Z., Yu, J., Xiang, C., Fan, J., Tao, D.: Generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. 29(12), 5947\u20135959 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43996-4_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T16:08:12Z","timestamp":1720109292000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43996-4_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439957","9783031439964"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43996-4_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"730","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}