{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T09:15:49Z","timestamp":1726218949580},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"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":["Image and Vision Computing"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1016\/j.imavis.2022.104374","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T01:17:19Z","timestamp":1642123039000},"page":"104374","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["LTST: Long-term segmentation tracker with memory attention network"],"prefix":"10.1016","volume":"119","author":[{"given":"Lang","family":"Yu","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6797-2240","authenticated-orcid":false,"given":"Baojun","family":"Qiao","sequence":"additional","affiliation":[]},{"given":"Huanlong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Junyang","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xin","family":"He","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2022.104374_bib0005","series-title":"Deep Learning for Visual Tracking: A Comprehensive Survey","author":"Marvasti-Zadeh","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0010","series-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","article-title":"The sixth visual object tracking vot2018 challenge results","author":"Kristan","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0015","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops","article-title":"The seventh visual object tracking vot2019 challenge results","author":"Kristan","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4660","article-title":"Atom: accurate tracking by overlap maximization","author":"Danelljan","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0025","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6182","article-title":"Learning discriminative model prediction for tracking","author":"Bhat","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4282","article-title":"Siamrpn++: evolution of siamese visual tracking with very deep networks","author":"Li","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0035","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"101","article-title":"Distractor-aware siamese networks for visual object tracking","author":"Zhu","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0040","series-title":"Computer Vision-ECCV 2020 16th European Conference","first-page":"378","article-title":"Clnet: a compact latent network for fast adjusting siamese trackers","author":"Dong","year":"2020"},{"key":"10.1016\/j.imavis.2022.104374_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16570","article-title":"Learning to fuse asymmetric feature maps in siamese trackers","author":"Han","year":"2021"},{"key":"10.1016\/j.imavis.2022.104374_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7133","article-title":"D3s-a discriminative single shot segmentation tracker","author":"Lukezic","year":"2020"},{"key":"10.1016\/j.imavis.2022.104374_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3623","article-title":"See more, know more: unsupervised video object segmentation with co-attention siamese networks","author":"Lu","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0060","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2020.3040258","article-title":"Zero-shot video object segmentation with co-attention siamese networks","author":"Lu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/j.imavis.2022.104374_bib0065","series-title":"Proceedings Of The IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2663","article-title":"Learning video object segmentation from static images","author":"Perazzi","year":"2017"},{"key":"10.1016\/j.imavis.2022.104374_bib0070","series-title":"Proceedings of the IEEE Conference on Computer Vision And Pattern Recognition","first-page":"221","article-title":"One-shot video object segmentation","author":"Caelles","year":"2017"},{"key":"10.1016\/j.imavis.2022.104374_bib0075","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6499","article-title":"Efficient video object segmentation via network modulation","author":"Yang","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0080","series-title":"Proceedings of the IEEE conference On Computer Vision and Pattern Recognition","first-page":"7376","article-title":"Fast video object segmentation by reference-guided mask propagation","author":"Oh","year":"2018"},{"issue":"6","key":"10.1016\/j.imavis.2022.104374_bib0085","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1109\/TCSVT.2018.2848358","article-title":"Semantics-aware visual object tracking","volume":"29","author":"Yao","year":"2018","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"10.1016\/j.imavis.2022.104374_bib0090","series-title":"Proceedings of the 26th ACM International Conference on Multimedia","first-page":"941","article-title":"Tracking-assisted weakly supervised online visual object segmentation in unconstrained videos","author":"Zhang","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0095","series-title":"Fast Visual Object Tracking With Rotated Bounding Boxes","author":"Chen","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0100","series-title":"Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition","first-page":"724","article-title":"A benchmark dataset and evaluation methodology for video object segmentation","author":"Perazzi","year":"2016"},{"key":"10.1016\/j.imavis.2022.104374_bib0105","series-title":"The 2017 Davis Challenge On Video Object Segmentation","author":"Pont-Tuset","year":"2017"},{"key":"10.1016\/j.imavis.2022.104374_bib0110","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5374","article-title":"Lasot: a high-quality benchmark for large-scale single object tracking","author":"Fan","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0115","series-title":"Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition","first-page":"4293","article-title":"Learning multi-domain convolutional neural networks for visual tracking","author":"Nam","year":"2016"},{"key":"10.1016\/j.imavis.2022.104374_bib0120","series-title":"Fully Convolutional Online Tracking","author":"Cui","year":"2020"},{"key":"10.1016\/j.imavis.2022.104374_bib0125","series-title":"The 2017 Davis Challenge on Video Object Segmentation-CVPR Workshops,Vol. 5","article-title":"Online adaptation of convolutional neural networks for the 2017 Davis challenge on video object segmentation","author":"Voigtlaender","year":"2017"},{"key":"10.1016\/j.imavis.2022.104374_bib0130","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6298","article-title":"High-performance long-term tracking with meta-updater","author":"Dai","year":"2020"},{"key":"10.1016\/j.imavis.2022.104374_bib0135","series-title":"Proceedings of the European Conference On Computer Vision (ECCV)","first-page":"54","article-title":"Videomatch: matching based video object segmentation","author":"Hu","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0140","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8934","article-title":"Pwc-net: cnns for optical flow using pyramid, warping, and cost volume","author":"Sun","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0145","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2758","article-title":"Flownet: learning optical flow with convolutional networks","author":"Dosovitskiy","year":"2015"},{"key":"10.1016\/j.imavis.2022.104374_bib0150","series-title":"Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition","first-page":"2462","article-title":"Flownet 2.0: evolution of optical flow estimation with deep networks","author":"Ilg","year":"2017"},{"key":"10.1016\/j.imavis.2022.104374_bib0155","doi-asserted-by":"crossref","first-page":"104181","DOI":"10.1016\/j.imavis.2021.104181","article-title":"Online-adaptive classification and regression network with sample-efficient meta learning for long-term tracking","volume":"112","author":"Yu","year":"2021","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.imavis.2022.104374_bib0160","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"749","article-title":"Multi-store tracker (muster): a cognitive psychology inspired approach to object tracking","author":"Hong","year":"2015"},{"key":"10.1016\/j.imavis.2022.104374_bib0165","doi-asserted-by":"crossref","first-page":"1268","DOI":"10.1109\/TCSVT.2019.2944654","article-title":"Adaptive region proposal with channel regularization for robust object tracking","volume":"31","author":"Lu","year":"2019","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"10.1016\/j.imavis.2022.104374_bib0170","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34","first-page":"11037","article-title":"Globaltrack: a simple and strong baseline for long-term tracking","author":"Huang","year":"2020"},{"key":"10.1016\/j.imavis.2022.104374_bib0175","series-title":"Proceedings of the Asian Conference on Computer Vision","article-title":"Visual tracking by tridentalign and context embedding","author":"Choi","year":"2020"},{"key":"10.1016\/j.imavis.2022.104374_bib0180","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2385","article-title":"'skimming-perusal\u2019tracking: a framework for real-time and robust long-term tracking","author":"Yan","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0185","series-title":"Asian Conference on Computer Vision","first-page":"595","article-title":"Fucolot-a fully-correlational long-term tracker","author":"Luke\u017ei\u010d","year":"2018"},{"issue":"7","key":"10.1016\/j.imavis.2022.104374_bib0190","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1109\/TPAMI.2011.239","article-title":"Tracking-learning-detection","volume":"34","author":"Kalal","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"issue":"3","key":"10.1016\/j.imavis.2022.104374_bib0195","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","article-title":"High-speed tracking with kernelized correlation filters","volume":"37","author":"Henriques","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/j.imavis.2022.104374_bib0200","series-title":"Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition","first-page":"2805","article-title":"End-to-end representation learning for correlation filter based tracking","author":"Valmadre","year":"2017"},{"key":"10.1016\/j.imavis.2022.104374_bib0205","series-title":"Proceedings of the IEEE Conference on Computer Vision And Pattern Recognition","first-page":"221","article-title":"One-shot video object segmentation","author":"Caelles","year":"2017"},{"key":"10.1016\/j.imavis.2022.104374_bib0210","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9481","article-title":"Feelvos: fast end-to-end embedding learning for video object segmentation","author":"Voigtlaender","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0215","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2020.3041332","article-title":"Deep object tracking with shrinkage loss","author":"Lu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/j.imavis.2022.104374_bib0220","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"459","article-title":"Triplet loss in siamese network for object tracking","author":"Dong","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0225","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1109\/TPAMI.2019.2956703","article-title":"Dynamical hyperparameter optimization via deep reinforcement learning in tracking","volume":"43","author":"Dong","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/j.imavis.2022.104374_bib0230","first-page":"1","article-title":"A survey on online learning for visual tracking","volume":"37","author":"Abbass","year":"2020","journal-title":"Visual Comput."},{"key":"10.1016\/j.imavis.2022.104374_bib0235","series-title":"End-to-End Memory Networks","author":"Sukhbaatar","year":"2015"},{"key":"10.1016\/j.imavis.2022.104374_bib0240","series-title":"Key-value memory networks for directly reading documents","author":"Miller","year":"2016"},{"key":"10.1016\/j.imavis.2022.104374_bib0245","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9226","article-title":"Video object segmentation using space-time memory networks","author":"Oh","year":"2019"},{"key":"10.1016\/j.imavis.2022.104374_bib0250","series-title":"Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.imavis.2022.104374_bib0255","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"issue":"7","key":"10.1016\/j.imavis.2022.104374_bib0260","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.1016\/j.patcog.2006.08.003","article-title":"A simple method for fitting of bounding rectangle to closed regions","volume":"40","author":"Chaudhuri","year":"2007","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2022.104374_bib0265","series-title":"Youtube-Vos: A Large-Scale Video Object Segmentation Benchmark","author":"Xu","year":"2018"},{"key":"10.1016\/j.imavis.2022.104374_bib0270","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision And Pattern Recognition","first-page":"6269","article-title":"Siamcar: siamese fully convolutional classification and regression for visual tracking","author":"Guo","year":"2020"},{"key":"10.1016\/j.imavis.2022.104374_bib0275","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6668","article-title":"Siamese box adaptive network for visual tracking","author":"Chen","year":"2020"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885622000038?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885622000038?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T22:06:11Z","timestamp":1674252371000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885622000038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":55,"alternative-id":["S0262885622000038"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2022.104374","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2022,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LTST: Long-term segmentation tracker with memory attention network","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2022.104374","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"104374"}}