{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T01:02:41Z","timestamp":1790038961032,"version":"4.0.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030872014","type":"print"},{"value":"9783030872021","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-87202-1_33","type":"book-chapter","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T15:03:23Z","timestamp":1632323003000},"page":"341-351","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Efficient Global-Local Memory for Real-Time Instrument Segmentation of Robotic Surgical Video"],"prefix":"10.1007","author":[{"given":"Jiacheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liansheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuntian","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"33_CR1","unstructured":"Allan, M., et al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"33_CR2","unstructured":"Allan, M., et al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"van Amsterdam, B., Clarkson, M.J., Stoyanov, D.: Multi-task recurrent neural network for surgical gesture recognition and progress prediction. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 1380\u20131386. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197301"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10337\u201310346 (2020)","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"33_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-030-59716-0_33","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"T Czempiel","year":"2020","unstructured":"Czempiel, T., et al.: TeCNO: surgical phase recognition with multi-stage temporal convolutional networks. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 343\u2013352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_33"},{"key":"33_CR6","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: CVPR 2009 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Garcia-Peraza-Herrera, L.C., et al.: ToolNet: holistically-nested real-time segmentation of robotic surgical tools. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5717\u20135722. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206462"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Hu, P., Caba, F., Wang, O., Lin, Z., Sclaroff, S., Perazzi, F.: Temporally distributed networks for fast video semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8818\u20138827 (2020)","DOI":"10.1109\/CVPR42600.2020.00884"},{"key":"33_CR10","unstructured":"Iglovikov, V., Shvets, A.: TernausNet: U-net with vgg11 encoder pre-trained on ImageNet for image segmentation. arXiv preprint arXiv:1801.05746 (2018)"},{"key":"33_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1007\/978-3-030-32254-0_49","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"Y Jin","year":"2019","unstructured":"Jin, Y., Cheng, K., Dou, Q., Heng, P.-A.: Incorporating temporal prior from motion flow for instrument segmentation in minimally invasive surgery video. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11768, pp. 440\u2013448. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32254-0_49"},{"issue":"5","key":"33_CR12","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/TMI.2017.2787657","volume":"37","author":"Y Jin","year":"2018","unstructured":"Jin, Y., et al.: SV-RCNet: workflow recognition from surgical videos using recurrent convolutional network. IEEE Trans. Med. Imaging 37(5), 1114\u20131126 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Jin, Y., Long, Y., Chen, C., Zhao, Z., Dou, Q., Heng, P.A.: Temporal memory relation network for workflow recognition from surgical video. IEEE Trans. Med. Imaging (2021)","DOI":"10.1109\/TMI.2021.3069471"},{"key":"33_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Liu, M., Zhu, M.: Mobile video object detection with temporally-aware feature maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5686\u20135695 (2018)","DOI":"10.1109\/CVPR.2018.00596"},{"key":"33_CR16","unstructured":"Nekrasov, V., Shen, C., Reid, I.: Light-weight RefineNet for real-time semantic segmentation. arXiv preprint arXiv:1810.03272 (2018)"},{"key":"33_CR17","doi-asserted-by":"crossref","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. arXiv preprint arXiv:1910.11109 (2019)","DOI":"10.1109\/ICRA40945.2020.9197425"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Ni, Z.L., et al.: Pyramid attention aggregation network for semantic segmentation of surgical instruments. In: AAAI, pp. 11782\u201311790 (2020)","DOI":"10.1609\/aaai.v34i07.6850"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Video object segmentation using space-time memory networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 9226\u20139235 (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Peng, C., et al.: MegDet: a large mini-batch object detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00647"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00474"},{"key":"33_CR22","doi-asserted-by":"crossref","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. IEEE (2018)","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Chai, Y., Schroff, F., Adam, H., Leibe, B., Chen, L.C.: FEELVOS: fast end-to-end embedding learning for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9481\u20139490 (2019)","DOI":"10.1109\/CVPR.2019.00971"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"33_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-030-32254-0_50","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"F Yi","year":"2019","unstructured":"Yi, F., Jiang, T.: Hard frame detection and online mapping for surgical phase recognition. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11768, pp. 449\u2013457. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32254-0_50"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Yi, P., Wang, Z., Jiang, K., Jiang, J., Ma, J.: Progressive fusion video super-resolution network via exploiting non-local spatio-temporal correlations. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3106\u20133115 (2019)","DOI":"10.1109\/ICCV.2019.00320"},{"key":"33_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/978-3-030-59716-0_39","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"J Zhang","year":"2020","unstructured":"Zhang, J., et al.: Symmetric dilated convolution for surgical gesture recognition. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 409\u2013418. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_39"},{"key":"33_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-030-59716-0_65","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"Z Zhao","year":"2020","unstructured":"Zhao, Z., Jin, Y., Gao, X., Dou, Q., Heng, P.-A.: Learning motion flows for\u00a0semi-supervised instrument segmentation from robotic surgical video. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 679\u2013689. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_65"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87202-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:14:47Z","timestamp":1790036087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87202-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030872014","9783030872021"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87202-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 September 2021","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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccai2021.org\/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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1622","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":"531","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":"33% - 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":"4","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}