{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T16:47:54Z","timestamp":1792860474952,"version":"4.5.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061160490"],"award-info":[{"award-number":["62061160490"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122029"],"award-info":[{"award-number":["62122029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2064"],"award-info":[{"award-number":["U20B2064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3277462","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T18:00:19Z","timestamp":1685037619000},"page":"4452-4461","source":"Crossref","is-referenced-by-count":66,"title":["Vision Transformer With Hybrid Shifted Windows for Gastrointestinal Endoscopy Image Classification"],"prefix":"10.1109","volume":"33","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Jiangsu, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6252-1061","authenticated-orcid":false,"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Hubei, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Jiangsu, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00622-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5940433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2017.8037242"},{"key":"ref53","article-title":"Effective light field de-occlusion network based on Swin transformer","author":"wang","year":"2022","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref52","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume":"34","author":"dai","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3083187.3083212"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2008.4649388"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212434"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2017.10.014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/2485934"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10120-018-0793-2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IST.2016.7738279"},{"key":"ref51","article-title":"LocalViT: Bringing locality to vision transformers","author":"li","year":"2021","journal-title":"arXiv 2104 05707"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref45","article-title":"DeepViT: Towards deeper vision transformer","author":"zhou","year":"2021","journal-title":"arXiv 2103 11886"},{"key":"ref48","first-page":"1","article-title":"CrossFormer: A versatile vision transformer hinging on cross-scale attention","author":"wang","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859720"},{"key":"ref42","first-page":"1","article-title":"An inception-like CNN architecture for GI disease and anatomical landmark classification","volume":"1984","author":"petscharnig","year":"2017","journal-title":"Proc CEUR Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593957"},{"key":"ref44","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/int.22815"},{"key":"ref49","first-page":"1","article-title":"RegionViT: Regional-to-local attention for vision transformers","author":"chen","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3892\/or.15.4.997"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2001.1019637"},{"key":"ref9","first-page":"55","article-title":"Neuro-fuzzy classification system for wireless-capsule endoscopic images","volume":"2","author":"kodogiannis","year":"2008","journal-title":"Int J Comput and Elect Engin"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","first-page":"1","article-title":"An image is worth 16 × 16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","first-page":"1","article-title":"Classification of abnormal endoscopic images using morphological watershed segmentation","author":"dhandra","year":"2005","journal-title":"Proc Int Conf Cognit Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.1998.745583"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1063\/5.0054161"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/9545920"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3010102"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2936645"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2015.7407907"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2015.7419037"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1751-2980.2007.00304.x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2008.12.015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-25842-6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2015.7252086"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1117\/12.2254333"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-017-0048-x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107568"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0185508"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS.2018.00073"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2635662"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref27","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020","journal-title":"arXiv 2004 10934"},{"key":"ref29","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10136531.pdf?arnumber=10136531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:42:22Z","timestamp":1695667342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10136531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":56,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3277462","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}