{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:19:53Z","timestamp":1775107193998,"version":"3.50.1"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472025"],"award-info":[{"award-number":["62472025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.imavis.2026.105922","type":"journal-article","created":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T15:42:06Z","timestamp":1770565326000},"page":"105922","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Non-target information also matters: InverseFormer tracker for single object tracking"],"prefix":"10.1016","volume":"168","author":[{"given":"Qiuhang","family":"Gu","sequence":"first","affiliation":[]},{"given":"Baopeng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhu","family":"Teng","sequence":"additional","affiliation":[]},{"given":"Hongwei","family":"Xu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.105922_bb0005","series-title":"ICLR","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.imavis.2026.105922_bb0010","series-title":"NIPS","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.imavis.2026.105922_bb0015","series-title":"IJCAI","article-title":"Sparsett: visual tracking with sparse transformers","author":"Fu","year":"2022"},{"key":"10.1016\/j.imavis.2026.105922_bb0020","series-title":"CVPR","first-page":"8126","article-title":"Transformer tracking","author":"Chen","year":"2021"},{"key":"10.1016\/j.imavis.2026.105922_bb0025","series-title":"ECCV","first-page":"300","article-title":"Trackingnet: a large-scale dataset and benchmark for object tracking in the wild","author":"Muller","year":"2018"},{"key":"10.1016\/j.imavis.2026.105922_bb0030","series-title":"ECCV","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.imavis.2026.105922_bb0035","series-title":"CVPR","first-page":"8971","article-title":"High performance visual tracking with siamese region proposal network","author":"Li","year":"2018"},{"key":"10.1016\/j.imavis.2026.105922_bb0040","series-title":"CVPR","first-page":"4282","article-title":"Siamrpn++: evolution of siamese visual tracking with very deep networks","author":"Li","year":"2019"},{"key":"10.1016\/j.imavis.2026.105922_bb0045","series-title":"CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.imavis.2026.105922_bb0050","series-title":"ECCV","first-page":"101","article-title":"Distractor-aware siamese networks for visual object tracking","author":"Zhu","year":"2018"},{"key":"10.1016\/j.imavis.2026.105922_bb0055","series-title":"CVPR","first-page":"1328","article-title":"Fast online object tracking and segmentation: a unifying approach","author":"Wang","year":"2019"},{"key":"10.1016\/j.imavis.2026.105922_bb0060","series-title":"CVPR","first-page":"10448","article-title":"Learning spatio-temporal transformer for visual tracking","author":"Yan","year":"2021"},{"key":"10.1016\/j.imavis.2026.105922_bb0065","series-title":"CVPR","first-page":"8791","article-title":"Transformer tracking with cyclic shifting window attention","author":"Song","year":"2022"},{"key":"10.1016\/j.imavis.2026.105922_bb0070","series-title":"ICCV","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.imavis.2026.105922_bb0075","series-title":"ECCV","first-page":"146","article-title":"Aiatrack: attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"issue":"11","key":"10.1016\/j.imavis.2026.105922_bb0080","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.1109\/TCSVT.2014.2317888","article-title":"Object tracking with only background cues","volume":"24","author":"Li","year":"2014","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.105922_bb0085","series-title":"ICCV","first-page":"1135","article-title":"Learning background aware correlation filters for visual tracking","author":"Kiani Galoogahi","year":"2017"},{"key":"10.1016\/j.imavis.2026.105922_bb0090","doi-asserted-by":"crossref","first-page":"2867","DOI":"10.1109\/TIP.2023.3269229","article-title":"Capsule-based regression tracking via background inpainting","volume":"32","author":"Ma","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.105922_bb0095","article-title":"Dynamic routing between capsules","volume":"30","author":"Sabour","year":"2017","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.imavis.2026.105922_bb0100","series-title":"Image and Vision Computing","article-title":"LTST: long-term segmentation tracker with memory attention network","volume":"Volume 119","author":"Yu","year":"2022"},{"key":"10.1016\/j.imavis.2026.105922_bb0105","first-page":"1562","article-title":"Got-10k: a large high-diversity benchmark for generic object tracking in the wild","author":"Huang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.105922_bb0110","series-title":"CVPR","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.2026.105922_bb0115","series-title":"ECCV","first-page":"740","article-title":"Microsoft coco: common objects in \u00b4context","author":"Lin","year":"2014"},{"key":"10.1016\/j.imavis.2026.105922_bb0120","series-title":"CVPR","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"issue":"9","key":"10.1016\/j.imavis.2026.105922_bb0125","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","article-title":"Object tracking benchmark","volume":"37","author":"Wu","year":"2015","journal-title":"IEEE TPAMI"},{"key":"10.1016\/j.imavis.2026.105922_bb0130","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14","first-page":"445","article-title":"A benchmark and simulator for uav tracking","author":"Mueller","year":"2016"},{"key":"10.1016\/j.imavis.2026.105922_bb0135","series-title":"CVPR","first-page":"1125","article-title":"Need for speed: a benchmark for higher frame rate object tracking","author":"Kiani Galoogahi","year":"2017"},{"key":"10.1016\/j.imavis.2026.105922_bb0140","series-title":"ECCV Workshops: Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16","first-page":"547","article-title":"The eighth visual object tracking vot2020 challenge results","author":"Kristan","year":"2020"},{"key":"10.1016\/j.imavis.2026.105922_bb0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2023.104760","article-title":"Visual tracking using transformer with a combination of convolution and attention","volume":"Volume 137","author":"Wang","year":"2023","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.105922_bb0150","series-title":"ICME","first-page":"624","article-title":"Multi-template tracker driven by cache manager algorithm, towards multi-distractor scenarios","author":"Lei","year":"2023"},{"key":"10.1016\/j.imavis.2026.105922_bb0155","series-title":"ICME","first-page":"1427","article-title":"Know who you are: learning target-aware transformer for object tracking","author":"Zou","year":"2023"},{"key":"10.1016\/j.imavis.2026.105922_bb0160","series-title":"CVPR","first-page":"8781","article-title":"Unified transformer tracker for object tracking","author":"Ma","year":"2022"},{"key":"10.1016\/j.imavis.2026.105922_bb0165","series-title":"Image and Vision Computing","article-title":"Exploiting spatial and temporal context for online tracking with improved transformer","volume":"Volume 133","author":"Zhang","year":"2023"},{"key":"10.1016\/j.imavis.2026.105922_bb0170","doi-asserted-by":"crossref","first-page":"3630","DOI":"10.1109\/TIP.2022.3166638","article-title":"Dual aligned siamese dense regression tracker","volume":"31","author":"Fan","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.105922_bb0175","series-title":"CVPR","first-page":"4660","article-title":"Atom: accurate tracking by overlap maximization","author":"Danelljan","year":"2019"},{"key":"10.1016\/j.imavis.2026.105922_bb0180","series-title":"ICCV","first-page":"6182","article-title":"Learning discriminative model prediction for tracking","author":"Bhat","year":"2019"},{"key":"10.1016\/j.imavis.2026.105922_bb0185","series-title":"ECCV","first-page":"483","article-title":"Unveiling the power of deep tracking","author":"Bhat","year":"2018"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626000284?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626000284?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T03:51:09Z","timestamp":1775101869000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626000284"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":37,"alternative-id":["S0262885626000284"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.105922","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Non-target information also matters: InverseFormer tracker for single object tracking","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.105922","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"105922"}}