{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:31:06Z","timestamp":1767310266990,"version":"3.48.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032097835","type":"print"},{"value":"9783032097842","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-09784-2_13","type":"book-chapter","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:28:19Z","timestamp":1767310099000},"page":"126-136","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Video Grounded Conversation Generation for\u00a0Reference Surgical Instrument Segmentation"],"prefix":"10.1007","author":[{"given":"Yihan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"13_CR1","unstructured":"Abdin, M., et\u00a0al.: Phi-3 technical report: a highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)"},{"key":"13_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Ayobi, N., P\u00e9rez-Rond\u00f3n, A., Rodr\u00edguez, S., Arbel\u00e1ez, P.: MATIS: masked-attention transformers for surgical instrument segmentation. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ISBI53787.2023.10230819"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Baby, B., et al.: From forks to forceps: a new framework for instance segmentation of surgical instruments. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6191\u20136201 (2023)","DOI":"10.1109\/WACV56688.2023.00613"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Bai, Z., et al.: One token to seg them all: language instructed reasoning segmentation in videos. arXiv preprint arXiv:2409.19603 (2024)","DOI":"10.52202\/079017-0219"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Botach, A., Zheltonozhskii, E., Baskin, C.: End-to-end referring video object segmentation with multimodal transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Liu, L., Wang, S., Jin, Y., Sch\u00f6nlieb, C.B., Aviles-Rivero, A.I.: Why deep surgical models fail?: Revisiting surgical action triplet recognition through the lens of robustness. In: International Workshop on Trustworthy Machine Learning for Healthcare, pp. 177\u2013189. Springer (2023)","DOI":"10.1007\/978-3-031-39539-0_15"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Z., Hui, T., Huang, J., Wei, X., Han, J., Liu, S.: Language-bridged spatial-temporal interaction for referring video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4964\u20134973 (2022)","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez, C., Bravo-S\u00e1nchez, L., Arbelaez, P.: ISINet: an instance-based approach for surgical instrument segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 595\u2013605. Springer (2020)","DOI":"10.1007\/978-3-030-59716-0_57"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Huang, D.A., et al.: Lita: Language instructed temporal-localization assistant. In: European Conference on Computer Vision, pp. 202\u2013218. Springer (2024)","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"13_CR11","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, L., Sch\u00f6nlieb, C.B., Aviles-Rivero, A.I.: Optimised propainter for video diminished reality inpainting. arXiv preprint arXiv:2406.02287 (2024)","DOI":"10.1109\/ISBI56570.2024.10635380"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-ChatGPT: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Ni, Z.L., Bian, G.B., Hou, Z.G., Zhou, X.H., Xie, X.L., Li, Z.: Attention-guided lightweight network for real-time segmentation of robotic surgical instruments. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 9939\u20139945 (2020). https:\/\/doi.org\/10.1109\/ICRA40945.2020.9197425","DOI":"10.1109\/ICRA40945.2020.9197425"},{"issue":"2","key":"13_CR15","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1109\/TASE.2017.2676018","volume":"15","author":"T Osa","year":"2018","unstructured":"Osa, T., Sugita, N., Mitsuishi, M.: Online trajectory planning and force control for automation of surgical tasks. IEEE Trans. Autom. Sci. Eng. 15(2), 675\u2013691 (2018). https:\/\/doi.org\/10.1109\/TASE.2017.2676018","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"13_CR16","unstructured":"Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: LLaVA++: extending visual capabilities with LLaMA-3 and Phi-3 (2024). https:\/\/github.com\/mbzuai-oryx\/LLaVA-pp"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: GLaMM: pixel grounding large multimodal model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13009\u201313018 (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"issue":"7","key":"13_CR19","doi-asserted-by":"publisher","first-page":"1542","DOI":"10.1109\/TMI.2017.2665671","volume":"36","author":"D Sarikaya","year":"2017","unstructured":"Sarikaya, D., Corso, J.J., Guru, K.A.: Detection and localization of robotic tools in robot-assisted surgery videos using deep neural networks for region proposal and detection. IEEE Trans. Med. Imaging 36(7), 1542\u20131549 (2017). https:\/\/doi.org\/10.1109\/TMI.2017.2665671","journal-title":"IEEE Trans. Med. Imaging"},{"key":"13_CR20","doi-asserted-by":"publisher","unstructured":"Shvets, A.A., Rakhlin, A., Kalinin, A.A., Iglovikov, V.I.: Automatic instrument segmentation in robot-assisted surgery using deep learning. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 624\u2013628 (2018). https:\/\/doi.org\/10.1109\/ICMLA.2018.00100","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Video-instrument synergistic network for referring video instrument segmentation in robotic surgery. IEEE Trans. Med. Imaging (2024)","DOI":"10.1109\/TMI.2024.3426953"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Yue, W., Zhang, J., Hu, K., Xia, Y., Luo, J., Wang, Z.: SurgicalSAM: efficient class promptable surgical instrument segmentation (2024)","DOI":"10.1609\/aaai.v38i7.28514"},{"key":"13_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-030-32254-0_7","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"D Zang","year":"2019","unstructured":"Zang, D., Bian, G.-B., Wang, Y., Li, Z.: An extremely fast and precise convolutional neural network for recognition and localization of cataract surgical tools. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11768, pp. 56\u201364. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32254-0_7"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Jin, Y., Gao, X., Dou, Q., Heng, P.A.: Learning motion flows for semi-supervised instrument segmentation from robotic surgical video. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23, pp. 679\u2013689. Springer (2020)","DOI":"10.1007\/978-3-030-59716-0_65"}],"container-title":["Lecture Notes in Computer Science","Collaborative Intelligence and Autonomy in Image-Guided Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09784-2_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:28:21Z","timestamp":1767310101000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09784-2_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032097835","9783032097842"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09784-2_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"COLAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Collaborative Intelligence and Autonomy in Image-Guided Surgery","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"colas2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/sites.google.com\/view\/miccai-2025-colas\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}