{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T04:47:09Z","timestamp":1782535629723,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3695410","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:45:04Z","timestamp":1779911104000},"page":"6744-6759","source":"Crossref","is-referenced-by-count":0,"title":["Neural Wave Propagation for Surgical Video Action Recognition: A New Dataset and Baseline"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7758-699X","authenticated-orcid":false,"given":"Tianxiang","family":"Chen","sequence":"first","affiliation":[{"name":"Terminal Intelligence Computing Division, Alibaba Cloud., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weibin","family":"Wang","sequence":"additional","affiliation":[{"name":"South China Normal University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhentao","family":"Tan","sequence":"additional","affiliation":[{"name":"reside, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9067-8920","authenticated-orcid":false,"given":"Ru","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Ruijin Hospital Luwan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wu","sequence":"additional","affiliation":[{"name":"reside, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1605-0873","authenticated-orcid":false,"given":"Ziyang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Digital Technologies, Aston University, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Lu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingliang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of General Surgery, Ruijin Hospital Luwan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1002-0315","authenticated-orcid":false,"given":"Zi","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Maynooth University, Maynooth, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4103\/2231-0746.200348"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2224-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9061964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2018.2813015"},{"key":"ref5","article-title":"m2caiseg: Semantic segmentation of laparoscopic images using convolutional neural networks","author":"Maqbool","year":"2020","journal-title":"arXiv:2008.10134"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-019-07281-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS58004.2023.00187"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-018-1791-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-019-06667-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref14","article-title":"TinyViM: Frequency decoupling for tiny hybrid vision mamba","author":"Ma","year":"2024","journal-title":"arXiv:2411.17473"},{"key":"ref15","article-title":"Building vision models upon heat conduction","author":"Wang","year":"2024","journal-title":"arXiv:2405.16555"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3208127"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102433","article-title":"Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videos","volume":"78","author":"Nwoye","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref19","article-title":"SAR-RARP50: Segmentation of surgical instrumentation and action recognition on robot-assisted radical prostatectomy challenge","author":"Psychogyios","year":"2023","journal-title":"arXiv:2401.00496"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758267"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-05093-7"},{"key":"ref22","first-page":"1","article-title":"JHU-ISI gesture and skill assessment working set (JIGSAWS): A surgical activity dataset for human motion modeling","volume-title":"Proc. MICCAI Workshop","volume":"3","author":"Gao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3147640"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106452"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102770"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_42"},{"key":"ref27","article-title":"Surg-3m: A dataset and foundation model for perception in surgical settings","author":"Che","year":"2025","journal-title":"arXiv:2503.19740"},{"key":"ref28","article-title":"Surgbench: A unified large-scale benchmark for surgical video analysis","author":"Wei","year":"2025","journal-title":"arXiv:2506.07603"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref34","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref35","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref36","volume-title":"Non-equilibrium Thermodynamics","author":"De Groot","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.12.002"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27882"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/66"},{"key":"ref40","first-page":"103031","article-title":"VMamba: Visual state space model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiao"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref42","first-page":"980","article-title":"Global filter networks for image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref43","article-title":"Adaptive Fourier neural operators: Efficient token mixers for transformers","author":"Guibas","year":"2021","journal-title":"arXiv:2111.13587"},{"key":"ref44","first-page":"54152","article-title":"Scattering vision transformer: Spectral mixing matters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Agneeswaran"},{"key":"ref45","article-title":"Rethinking spatiotemporal feature learning for video understanding","author":"Xie","year":"2017","journal-title":"arXiv:1712.04851"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.49"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_57"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_46"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref51","article-title":"Single- and multi-task architectures for surgical workflow challenge at M2CAI 2016","author":"Twinanda","year":"2016","journal-title":"arXiv:1610.08844"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2787657"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32254-0_50"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3069471"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103366"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01927"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586118"},{"key":"ref63","article-title":"Vision-centric token compression in large language model","author":"Xing","year":"2025","journal-title":"arXiv:2502.00791"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3629609"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/s44401-024-00010-3"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11536833.pdf?arnumber=11536833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T04:25:32Z","timestamp":1782534332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11536833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3695410","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}