{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T07:32:48Z","timestamp":1782631968530,"version":"3.54.5"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T00:00:00Z","timestamp":1687392000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T00:00:00Z","timestamp":1687392000000},"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":["Int J CARS"],"DOI":"10.1007\/s11548-023-02971-6","type":"journal-article","created":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T10:14:52Z","timestamp":1687428892000},"page":"375-382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A spatio-temporal network for video semantic segmentation in surgical videos"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8345-0850","authenticated-orcid":false,"given":"Maria","family":"Grammatikopoulou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricardo","family":"Sanchez-Matilla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Bragman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Owen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucy","family":"Culshaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen","family":"Kerr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imanol","family":"Luengo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,22]]},"reference":[{"key":"2971_CR1","unstructured":"Hong W-Y, Kao C-L, Kuo Y-H, Wang J-R, Chang W-L, Shih C-S (2021) Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. In: 12th international conference on information processing in computer-assisted interventions"},{"issue":"1","key":"2971_CR2","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/00031348221101503","volume":"89","author":"DT Guerrero","year":"2022","unstructured":"Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE (2022) Advancing surgical education: the use of artificial intelligence in surgical training. Am Surg 89(1):49\u201354","journal-title":"Am Surg"},{"issue":"1","key":"2971_CR3","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1097\/SLA.0000000000002693","volume":"268","author":"DA Hashimoto","year":"2018","unstructured":"Hashimoto DA, Rosman G, Rus D, Meireles OR (2018) Artificial intelligence in surgery: promises and perils. Ann Surg 268(1):70\u201376","journal-title":"Ann Surg"},{"issue":"10","key":"2971_CR4","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, Liu D, Mu Y, Tan M, Wang X et al (2020) Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell 43(10):3349\u20133364","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2971_CR5","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2971_CR6","unstructured":"Zhou T, Porikli F, Crandall DJ, Gool LV, Wang W (2022) A survey on deep learning technique for video segmentation. IEEE Trans Pattern Anal Mach Intell 1\u201320"},{"key":"2971_CR7","doi-asserted-by":"crossref","unstructured":"Cheng B, Misra I, Schwing AG, Kirillov A, Girdhar R (2022) Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1290\u20131299","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2971_CR8","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez C, Bravo-S\u00e1nchez L, Arbelaez P (2020) Isinet: an instance-based approach for surgical instrument segmentation. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 595\u2013605","DOI":"10.1007\/978-3-030-59716-0_57"},{"key":"2971_CR9","doi-asserted-by":"crossref","unstructured":"Zhao Z, Jin Y, Gao X, Dou Q, Heng P-A (2020) Learning motion flows for semi-supervised instrument segmentation from robotic surgical video. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 679\u2013689","DOI":"10.1007\/978-3-030-59716-0_65"},{"key":"2971_CR10","doi-asserted-by":"crossref","unstructured":"Lea C, Flynn MD, Vidal R, Reiter A, Hager GD (2017) Temporal convolutional networks for action segmentation and detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.113"},{"key":"2971_CR11","doi-asserted-by":"crossref","unstructured":"Varghese S, Bayzidi Y, Bar A, Kapoor N, Lahiri S, Schneider JD, Schmidt NM, Schlicht P, Huger F, Fingscheidt T (2020) Unsupervised temporal consistency metric for video segmentation in highly-automated driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 336\u2013337","DOI":"10.1109\/CVPRW50498.2020.00176"},{"key":"2971_CR12","doi-asserted-by":"crossref","unstructured":"Puyal JG-B, Bhatia KK, Brandao P, Ahmad OF, Toth D, Kader R, Lovat L, Mountney P, Stoyanov D (2020) Endoscopic polyp segmentation using a hybrid 2D\/3D CNN. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 295\u2013305","DOI":"10.1007\/978-3-030-59725-2_29"},{"key":"2971_CR13","doi-asserted-by":"publisher","first-page":"46810","DOI":"10.1109\/ACCESS.2021.3067928","volume":"9","author":"B Wang","year":"2021","unstructured":"Wang B, Li L, Nakashima Y, Kawasaki R, Nagahara H, Yagi Y (2021) Noisy-lstm: improving temporal awareness for video semantic segmentation. IEEE Access 9:46810\u201346820","journal-title":"IEEE Access"},{"key":"2971_CR14","doi-asserted-by":"crossref","unstructured":"Liu Y, Shen C, Yu C, Wang J (2020) Efficient semantic video segmentation with per-frame inference. In: European conference on computer vision, Springer, pp 352\u2013368","DOI":"10.1007\/978-3-030-58607-2_21"},{"key":"2971_CR15","doi-asserted-by":"crossref","unstructured":"Jain S, Wang X, Gonzalez JE (2019) Accel: a corrective fusion network for efficient semantic segmentation on video. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8866\u20138875","DOI":"10.1109\/CVPR.2019.00907"},{"key":"2971_CR16","doi-asserted-by":"crossref","unstructured":"Farha YA, Gall J (2019) 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","DOI":"10.1109\/CVPR.2019.00369"},{"key":"2971_CR17","doi-asserted-by":"crossref","unstructured":"Hou J, Wang G, Chen X, Xue J-H, Zhu R, Yang H (2018) Spatial-temporal attention RES-TCN for skeleton-based dynamic hand gesture recognition. In: Proceedings of the European conference on computer vision (ECCV) workshops","DOI":"10.1007\/978-3-030-11024-6_18"},{"key":"2971_CR18","doi-asserted-by":"crossref","unstructured":"Teed Z, Deng J (2020) Raft: recurrent all-pairs field transforms for optical flow. In: European conference on computer vision, Springer, pp 402\u2013419","DOI":"10.1007\/978-3-030-58536-5_24"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02971-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-023-02971-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02971-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,4]],"date-time":"2024-02-04T12:03:09Z","timestamp":1707048189000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-023-02971-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,22]]},"references-count":18,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["2971"],"URL":"https:\/\/doi.org\/10.1007\/s11548-023-02971-6","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,22]]},"assertion":[{"value":"7 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Drs. Grammatikopoulou, Sanchez-Matilla, Bragman, Owen, Culshaw, Kerr, Luengo and Prof. Stoyanov are employees of Medtronic plc. Prof. Stoyanov is a co-founder and share- holder in Odin Vision, Ltd.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Medtronic plc maintains all necessary rights and consents to process, analyze and display the private data referenced in this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}