{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:41:46Z","timestamp":1783968106964,"version":"3.55.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["62276054"],"award-info":[{"award-number":["62276054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019065","name":"Sichuan Science and Technology Program","doi-asserted-by":"publisher","award":["2023YFG0156"],"award-info":[{"award-number":["2023YFG0156"]}],"id":[{"id":"10.13039\/501100019065","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":[[2025,7]]},"DOI":"10.1109\/tcsvt.2025.3534204","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T14:08:24Z","timestamp":1737986904000},"page":"6424-6436","source":"Crossref","is-referenced-by-count":4,"title":["Flexible ViG: Learning the Self-Saliency for Flexible Object Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2739-8290","authenticated-orcid":false,"given":"Kunshan","family":"Yang","sequence":"first","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1598-1249","authenticated-orcid":false,"given":"Lin","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0693-2197","authenticated-orcid":false,"given":"Mengmeng","family":"Jing","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6594-8409","authenticated-orcid":false,"given":"Xianlong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunbin","family":"He","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9344-8506","authenticated-orcid":false,"given":"Yongqi","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-323-96104-2.00002-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2023.1178450"},{"key":"ref7","article-title":"Point cloud registration of non-rigid objects in sparse 3D scans with applications in mixed reality","author":"Jha","year":"2022","journal-title":"arXiv:2212.03856"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10694-019-00899-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1029\/2018GL077787"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00224"},{"key":"ref11","article-title":"FireNet: A specialized lightweight fire & smoke detection model for real-time IoT applications","author":"Jadon","year":"2019","journal-title":"arXiv:1905.11922"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2392531"},{"key":"ref13","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2005.1569195"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2003.1225549"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3258527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2013.12.009"},{"key":"ref19","article-title":"Graph neural networks: Methods, applications, and opportunities","author":"Waikhom","year":"2021","journal-title":"arXiv:2108.10733"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0069-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref22","article-title":"Graph attention networks","author":"Veli\u010d kovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-85826-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3238642"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.05.026"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75762-5_41"},{"key":"ref28","first-page":"8291","article-title":"Vision GNN: An image is worth graph of nodes","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Han"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/4652526"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.41"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5220\/0008968003070314"},{"key":"ref33","article-title":"Vit graph head attention for small sized datasets","volume-title":"Proc. Workshop Efficient Syst. Found. Models (ICML)","author":"Kim"},{"key":"ref34","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probab.","volume":"1","author":"MacQueen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32047-8_16"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/science.1136800"},{"key":"ref37","article-title":"Image as set of points","author":"Ma","year":"2023","journal-title":"arXiv:2303.01494"},{"key":"ref38","first-page":"1","article-title":"ImageNet-hard: The hardest images remaining from a study of the power of zoom and spatial biases in image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Taesiri"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref41","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref46","article-title":"ShuffleNet: An extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2017","journal-title":"arXiv:1707.01083"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref49","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. NeurIPS","author":"Tolstikhin"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00546"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11071401\/10854580.pdf?arnumber=10854580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:39Z","timestamp":1767638439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10854580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":51,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3534204","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}