{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T23:13:46Z","timestamp":1783725226610,"version":"3.55.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032241818","type":"print"},{"value":"9783032241825","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\/978-3-032-24182-5_13","type":"book-chapter","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T22:24:05Z","timestamp":1783722245000},"page":"135-144","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Memory-Enhanced Temporal Learning: Leveraging SAM2\u2019s Memory Modules for\u00a0Consistent Segmentation on\u00a0Surgical Video"],"prefix":"10.1007","author":[{"given":"Shunsuke","family":"Kikuchi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Kouno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroki","family":"Matsuzaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Oh, S.W., Price, B., et\u00a0al.: Putting the object back into video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3151\u20133161 (2024)","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Defazio, A., Yang, X., Mehta, H., et\u00a0al.: The road less scheduled (2024)","DOI":"10.52202\/079017-0320"},{"key":"13_CR4","unstructured":"Hong, W.Y., Kao, C.L., Kuo, Y.H., Wang, J.R., Chang, W.L., Shih, C.S.: Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80 (2020). https:\/\/arxiv.org\/abs\/2012.12453"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, W., Pang, J., et\u00a0al.: Video k-net: a simple, strong, and unified baseline for video segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18847\u201318857 (2022)","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et\u00a0al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"13_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1007\/978-3-030-58607-2_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Shen, C., Yu, C., Wang, J.: Efficient semantic video segmentation with per-frame inference. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 352\u2013368. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_21"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Miles, R., Yucel, M.K., Manganelli, B., et\u00a0al.: Mobilevos: real-time video object segmentation contrastive learning meets knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10480\u201310490 (2023)","DOI":"10.1109\/CVPR52729.2023.01010"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"M\u00fcller, S.G., Hutter, F.: Trivialaugment: tuning-free yet state-of-the-art data augmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 774\u2013782 (2021)","DOI":"10.1109\/ICCV48922.2021.00081"},{"key":"13_CR10","unstructured":"Psychogyios, D., Colleoni, E., Van\u00a0Amsterdam, B., et\u00a0al.: Sar-rarp50: segmentation of surgical instrumentation and action recognition on robot-assisted radical prostatectomy challenge (2024)"},{"key":"13_CR11","unstructured":"Ravi, N., Gabeur, V., Hu, Y.T., et\u00a0al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"13_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"13_CR13","unstructured":"Ross, T., Reinke, A., Full, P.M., et\u00a0al.: Robust medical instrument segmentation challenge 2019 (2020)"},{"key":"13_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-319-67558-9_28","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"CH Sudre","year":"2017","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA\/ML-CDS -2017. LNCS, vol. 10553, pp. 240\u2013248. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-67558-9_28"},{"key":"13_CR15","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a097, pp. 6105\u20136114. PMLR (2019)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Tu, Z., Talebi, H., Zhang, H., et\u00a0al.: Maxvit: multi-axis vision transformer. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lipson, L., Deng, J., et\u00a0al.: SEA-RAFt: simple, efficient, accurate RAFT for optical flow. In: Leonardis, A., Ricci, E., Roth, S., et\u00a0al. (eds.) Computer Vision \u2013 ECCV 2024, pp. 36\u201354. Springer (2025)","DOI":"10.1007\/978-3-031-72667-5_3"},{"key":"13_CR18","unstructured":"Zia, A., Bhattacharyya, K., Liu, X., et\u00a0al.: Surgical tool classification and localization: results and methods from the MICCAI 2022 surgtoolloc challenge (2023)"}],"container-title":["Lecture Notes in Computer Science","Empowering Medical Image Computing and Research Through Early-Career Expertise"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-24182-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T22:24:07Z","timestamp":1783722247000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-24182-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032241818","9783032241825"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-24182-5_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":"4 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A video used for validation with, TMAM inference, base model inference, and ground truth is available from github repository.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Supplementary Material"}},{"value":"Shunsuke Kikuchi received financial support for a research internship at Jmees Inc. Atsushi Kouno is an employee of Jmees Inc. Hiroki Matsuzaki is the co-founder and CEO of Jmees Inc.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"EMERGE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop on Empowering Medical Image Computing and Research through Early-Career Expertise","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":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"emerge2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccaimsb.github.io\/emerge\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}