{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T05:12:18Z","timestamp":1741324338961,"version":"3.38.0"},"reference-count":48,"publisher":"Tech Science Press","issue":"1","license":[{"start":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T00:00:00Z","timestamp":1721347200000},"content-version":"vor","delay-in-days":200,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2024]]},"DOI":"10.32604\/cmc.2024.050959","type":"journal-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T09:09:09Z","timestamp":1720429749000},"page":"605-623","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["SMSTracker: A Self-Calibration Multi-Head Self-Attention Transformer for Visual Object Tracking"],"prefix":"10.32604","volume":"80","author":[{"given":"Zhongyang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"17807","published-online":{"date-parts":[[2024]]},"reference":[{"key":"ref1","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. CVPR 2000 (Cat. No.PR00662)","first-page":"142","article-title":"Real-time tracking of non-rigid objects using mean shift","volume":"2","author":"Comaniciu","year":"2000"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2259","DOI":"10.1109\/TPAMI.2011.66","article-title":"Robust visual tracking and vehicle classification via sparse representation","volume":"33","author":"Mei","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref3","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1145\/212094.212141","article-title":"The computation of optical flow","volume":"27","author":"Beauchemin","year":"1995","journal-title":"ACM Comput. Surv."},{"key":"ref4","series-title":"2010 IEEE Comput. Society Conf. Comput. Vis. Pattern Recognit.","first-page":"2544","article-title":"Visual object tracking using adaptive correlation filters","author":"Bolme","year":"2010"},{"key":"ref5","series-title":"Proc. Int. Conf. Comput. Vis. Workshops","first-page":"587","article-title":"Exploiting the circulant ` structure of tracking-by-detection with kernels","author":"Montero","year":"2015"},{"key":"ref6","series-title":"Br. Mach. Vis. Conf.","article-title":"Accurate scale estimation for robust visual tracking","author":"Danelljan","year":"Sep. 1\u20135, 2014"},{"key":"ref7","series-title":"Comput. Vis.\u2013ECCV 2014 Workshops, Zurich, Switzerland, Sep. 6\u20137, 2014","first-page":"254","article-title":"A scale adaptive kernel correlation filter tracker with feature integration","author":"Li"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"104468","DOI":"10.1016\/j.imavis.2022.104468","article-title":"Multi-feature fusion tracking algorithm based on peak-context learning","volume":"123","author":"Bouraffa","year":"2022","journal-title":"Image Vis. Comput."},{"key":"ref9","series-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","first-page":"3074","article-title":"Hierarchical convolutional features for visual tracking","author":"Ma","year":"2015"},{"key":"ref10","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit (CVPR)","first-page":"5000","article-title":"End-to-end representation learning for correlation filter based tracking","author":"Valmadre","year":"2017"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1109\/TIP.2018.2806280","article-title":"Good features to correlate for visual tracking","volume":"27","author":"Gundogdu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref12","unstructured":"Q. Wang, J. Gao, J. Xing, M. Zhang, and W. Hu, \u201cDCFNet: Discriminant correlation filters network for visual tracking,\u201d arXiv preprint arXiv:1704.04057, 2017."},{"key":"ref13","doi-asserted-by":"crossref","first-page":"4291","DOI":"10.1007\/s00371-021-02296-y","article-title":"MP-LN: Motion state prediction and localization network for visual object tracking","volume":"38","author":"Fan","year":"2022","journal-title":"Vis. Comput."},{"key":"ref14","unstructured":"P. Sun et al., \u201cTranstrack: Multiple object tracking with transformer,\u201d arXiv preprint arXiv:2012, 2012."},{"key":"ref15","series-title":"European Conf. Comput. Vis.","first-page":"375","article-title":"Backbone is all your need: A simplified architecture for visual object tracking","author":"Chen","year":"2022"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.3390\/e22121358","article-title":"Aerial video trackers review","volume":"22","author":"Jia","year":"2020","journal-title":"Entropy"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.patrec.2014.03.025","article-title":"Robust scale-adaptive mean-shift for tracking","volume":"49","author":"Vojir","year":"2014","journal-title":"Pattern Recognit. Lett."},{"key":"ref18","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/S0262-8856(02)00129-4","article-title":"An adaptive color-based particle filter","volume":"21","author":"Nummiaro","year":"2003","journal-title":"Image Vis. Comput."},{"key":"ref19","series-title":"Proc. Br. Mach.Vis. Conf. (BMVC)","first-page":"185.1","article-title":"Enable scale and aspect ratio adaptability in visual tracking with detection proposals","author":"Huang","year":"Sep. 2015"},{"key":"ref20","first-page":"809","article-title":"Learning a deep compact image representation for visual tracking","volume":"1","author":"Wang","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref21","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","first-page":"4293","article-title":"Learning multi-domain convolutional neural networks for visual tracking","author":"Nam","year":"2016"},{"key":"ref22","unstructured":"M. Zhao, K. Okada, and M. Inaba, \u201cTrTr: Visual tracking with transformer,\u201d arXiv preprint arXiv:2105.03817, 2021."},{"key":"ref23","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"9543","article-title":"Graph attention tracking","author":"Guo","year":"2021"},{"key":"ref24","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognition","first-page":"8126","article-title":"Transformer tracking","author":"Chen","year":"2021"},{"key":"ref25","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"13608","article-title":"MixFormer: End-to-end tracking with iterative mixed attention","author":"Cui","year":"2022"},{"key":"ref26","series-title":"Eur. Conf. Comput. Vis.","first-page":"612","article-title":"Weakly supervised object localization via transformer with implicit spatial calibration","author":"Bai","year":"2022"},{"key":"ref27","unstructured":"K. Islam, \u201cRecent advances in vision transformer: A survey and outlook of recent work,\u201d arXiv preprint arXiv:2203.01536, 2022."},{"key":"ref28","unstructured":"F. Wu, A. Fan, A. Baevski, Y. N. Dauphin, and M. Auli, \u201cPay less attention with lightweight and dynamic convolutions,\u201d arXiv preprint arXiv:1901.10430, 2019."},{"key":"ref29","unstructured":"A. Stotsky, \u201cSystematic review of newton-schulz iterations with unified factorizations: Integration in the richardson method and application to robust failure detection in electrical networks,\u201d arXiv preprint arXiv:2208.04068, 2022."},{"key":"ref30","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"658","article-title":"Generalized intersection over union: A metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"ref31","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","first-page":"2411","article-title":"Online object tracking: A benchmark","author":"Wu","year":"2013"},{"key":"ref32","series-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","first-page":"300","article-title":"TrackingNet: A large-scale dataset and benchmark for object tracking in the wild","author":"Muller","year":"2018"},{"key":"ref33","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"5374","article-title":"LaSOT: A high-quality benchmark for large-scale single object tracking","author":"Fan","year":"2019"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","article-title":"GOT-10k: A large high-diversity benchmark for generic object tracking in the wild","volume":"43","author":"Huang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref35","unstructured":"I. Loshchilov and F. Hutter, \u201cDecoupled weight decay regularization,\u201d arXiv preprint arXiv:1711.05101, 2017."},{"key":"ref36","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"10448","article-title":"Learning spatio-temporal transformer for visual tracking","author":"Yan","year":"2021"},{"key":"ref37","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"13774","article-title":"STMTrack: Template-free visual tracking with space-time memory networks","author":"Fu","year":"2021"},{"key":"ref38","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"8731","article-title":"Transforming model prediction for tracking","author":"Mayer","year":"2022"},{"key":"ref39","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"13444","article-title":"Learning target candidate association to keep track of what not to track","author":"Mayer","year":"2021"},{"key":"ref40","series-title":"Comput. Vis.\u2013ECCV 2020: 16th Eur. Conf., Proc.","first-page":"205","article-title":"Know your surroundings: Exploiting scene information for object tracking","author":"Bhat","year":"Aug. 23\u201328, 2020"},{"key":"ref41","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"6578","article-title":"Siam R-CNN: Visual tracking by re-detection","author":"Voigtlaender","year":"2020"},{"key":"ref42","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"1571","article-title":"Transformer meets tracker: Exploiting temporal context for robust visual tracking","author":"Wang","year":"2021"},{"key":"ref43","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"7183","article-title":"Probabilistic regression for visual tracking","author":"Danelljan","year":"2020"},{"key":"ref44","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"14572","article-title":"SeqTrack: Sequence to sequence learning for visual object tracking","author":"Chen","year":"2023"},{"key":"ref45","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"8791","article-title":"Transformer tracking with cyclic shifting window attention","author":"Song","year":"2022"},{"key":"ref46","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"2688","article-title":"Learning tracking representations via dual-branch fully transformer networks","author":"Xie","year":"2021"},{"key":"ref47","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","first-page":"8751","article-title":"Correlationaware deep tracking","author":"Xie","year":"2022"},{"key":"ref48","unstructured":"Y. Cui, C. Jiang, L. Wang, and G. Wu, \u201cTarget transformed regression for accurate tracking,\u201d arXiv preprint arXiv:2104.00403, 2021."}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.techscience.com\/files\/cmc\/2024\/TSP_CMC-80-1\/TSP_CMC_50959\/TSP_CMC_50959.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T11:34:33Z","timestamp":1741260873000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v80n1\/57378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024]]},"published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2024.050959","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2024-02-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-23","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-18","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}