{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T07:04:13Z","timestamp":1779865453058,"version":"3.53.1"},"reference-count":29,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.bspc.2026.110494","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T16:48:38Z","timestamp":1777999718000},"page":"110494","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["SurgLSTRNet: A dual-timescale network for capturing long-term and short-term relationships in endoscopic surgery videos"],"prefix":"10.1016","volume":"123","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9498-8074","authenticated-orcid":false,"given":"Jingzhen","family":"Niu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicheng","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingbo","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guodong","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengbo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dazhi","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xujun","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.bspc.2026.110494_b1","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/JPROC.2019.2946993","article-title":"CAI4cai: The rise of contextual artificial intelligence in computer-assisted interventions","volume":"108","author":"Vercauteren","year":"2020","journal-title":"Proc. IEEE"},{"issue":"11","key":"10.1016\/j.bspc.2026.110494_b2","doi-asserted-by":"crossref","first-page":"5405","DOI":"10.1109\/JBHI.2023.3311628","article-title":"Deep learning in surgical workflow analysis: A review of phase and step recognition","volume":"27","author":"Demir","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.bspc.2026.110494_b3","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","first-page":"486","article-title":"AutoLaparo: A new dataset of integrated multi-tasks for image-guided surgical automation in laparoscopic hysterectomy","author":"Wang","year":"2022"},{"issue":"3","key":"10.1016\/j.bspc.2026.110494_b4","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1109\/TBME.2005.869771","article-title":"Generalized approach for modeling minimally invasive surgery as a stochastic process using a discrete Markov model","volume":"53","author":"Rosen","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.bspc.2026.110494_b5","series-title":"Proceedings of the 20th National Conference on Innovative Applications of Artificial Intelligence - Volume 3","first-page":"1718","article-title":"On-line recognition of surgical activity for monitoring in the operating room","author":"Padoy","year":"2008"},{"key":"10.1016\/j.bspc.2026.110494_b6","series-title":"MultiMedia Modeling","first-page":"241","article-title":"Frame-based classification of operation phases in cataract surgery videos","author":"Primus","year":"2018"},{"issue":"1","key":"10.1016\/j.bspc.2026.110494_b7","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","article-title":"EndoNet: A deep architecture for recognition tasks on laparoscopic videos","volume":"36","author":"Twinanda","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"5","key":"10.1016\/j.bspc.2026.110494_b8","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1109\/TMI.2017.2787657","article-title":"SV-RCNet: Workflow recognition from surgical videos using recurrent convolutional network","volume":"37","author":"Jin","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.bspc.2026.110494_b9","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","first-page":"449","article-title":"Hard frame detection and online mapping for surgical phase recognition","author":"Yi","year":"2019"},{"key":"10.1016\/j.bspc.2026.110494_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103366","article-title":"Lovit: Long video transformer for surgical phase recognition","volume":"99","author":"Liu","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.bspc.2026.110494_b11","doi-asserted-by":"crossref","unstructured":"Yang Liu, Jiayu Huo, Jingjing Peng, Rachel Sparks, Prokar Dasgupta, Alejandro Granados, S\u00e9bastien Ourselin, SKiT: a Fast Key Information Video Transformer for Online Surgical Phase Recognition, in: 2023 IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 21017\u201321027, URL https:\/\/api.semanticscholar.org\/CorpusID:267026014.","DOI":"10.1109\/ICCV51070.2023.01927"},{"key":"10.1016\/j.bspc.2026.110494_b12","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024","first-page":"606","article-title":"Surgformer: Surgical transformer with hierarchical temporal attention for surgical phase recognition","author":"Yang","year":"2024"},{"key":"10.1016\/j.bspc.2026.110494_b13","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume":"vol. 139","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.bspc.2026.110494_b14","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","first-page":"343","article-title":"TeCNO: Surgical phase recognition with multi-stage temporal convolutional networks","author":"Czempiel","year":"2020"},{"key":"10.1016\/j.bspc.2026.110494_b15","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","first-page":"593","article-title":"Trans-svnet: Accurate phase recognition from surgical videos via hybrid embedding aggregation transformer","author":"Gao","year":"2021"},{"key":"10.1016\/j.bspc.2026.110494_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103716","article-title":"PitVis-2023 challenge: Workflow recognition in videos of endoscopic pituitary surgery","volume":"106","author":"Das","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.bspc.2026.110494_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2025.110222","article-title":"Attention in surgical phase recognition for endoscopic pituitary surgery: Insights from real-world data","volume":"191","author":"Gonz\u00e1lez-Cebri\u00e1n","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.bspc.2026.110494_b18","series-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"issue":"7","key":"10.1016\/j.bspc.2026.110494_b19","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.1109\/TMI.2021.3069471","article-title":"Temporal memory relation network for workflow recognition from surgical video","volume":"40","author":"Jin","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"4","key":"10.1016\/j.bspc.2026.110494_b20","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/s11102-008-0087-5","article-title":"Endoscopic pituitary surgery","volume":"11","author":"Cappabianca","year":"2008","journal-title":"Pituitary"},{"issue":"6","key":"10.1016\/j.bspc.2026.110494_b21","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1007\/s11102-021-01162-3","article-title":"Pituitary society expert delphi consensus: operative workflow in endoscopic transsphenoidal pituitary adenoma resection","volume":"24","author":"Marcus","year":"2021","journal-title":"Pituitary"},{"issue":"9","key":"10.1016\/j.bspc.2026.110494_b22","doi-asserted-by":"crossref","first-page":"1673","DOI":"10.1007\/s11548-023-02923-0","article-title":"A methodology for the annotation of surgical videos for supervised machine learning applications","volume":"18","author":"Fischer","year":"2023","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"10.1016\/j.bspc.2026.110494_b23","doi-asserted-by":"crossref","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.bspc.2026.110494_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103646","article-title":"Stsanet: Spatial temporal-self-aggregation network for surgical phase recognition","volume":"126","author":"Li","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.bspc.2026.110494_b25","doi-asserted-by":"crossref","unstructured":"Rohit Girdhar, Kristen Grauman, Anticipative Video Transformer, in: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 13485\u201313495.","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"10.1016\/j.bspc.2026.110494_b26","series-title":"Advanced Intelligent Computing Technology and Applications","first-page":"228","article-title":"Osfenet: Object spatiotemporal feature enhanced network for surgical phase recognition","author":"You","year":"2024"},{"key":"10.1016\/j.bspc.2026.110494_b27","article-title":"EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training","volume":"vol. LNCS 15968","author":"Tian","year":"2025"},{"key":"10.1016\/j.bspc.2026.110494_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.105637","article-title":"Adaptive undersampling and short clip-based two-stream CNN-LSTM model for surgical phase recognition on cholecystectomy videos","volume":"88","author":"Lee","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"10.1016\/j.bspc.2026.110494_b29","doi-asserted-by":"crossref","unstructured":"Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q. Weinberger, Densely Connected Convolutional Networks, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 2261\u20132269.","DOI":"10.1109\/CVPR.2017.243"}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426010487?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426010487?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T06:24:44Z","timestamp":1779863084000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1746809426010487"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":29,"alternative-id":["S1746809426010487"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110494","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SurgLSTRNet: A dual-timescale network for capturing long-term and short-term relationships in endoscopic surgery videos","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110494","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"110494"}}