{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:05:48Z","timestamp":1784279148377,"version":"3.55.0"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100019065","name":"Tianjin Science and Technology Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113675","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:16:18Z","timestamp":1776442578000},"page":"113675","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Instance-level geometric prompting for visual object tracking"],"prefix":"10.1016","volume":"179","author":[{"given":"Qinghua","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6031-9334","authenticated-orcid":false,"given":"Wanli","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huayu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangcan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengyong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.patcog.2026.113675_b1","doi-asserted-by":"crossref","first-page":"5872","DOI":"10.1109\/TCSVT.2025.3531375","article-title":"SIEVL-track: Exploring semantic information enhancement for visual-language object tracking","volume":"35","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113675_b2","series-title":"European Conference on Computer Vision","first-page":"146","article-title":"Aiatrack: Attention in attention for transformer visual tracking","author":"Gao","year":"2022"},{"key":"10.1016\/j.patcog.2026.113675_b3","doi-asserted-by":"crossref","unstructured":"Y. Cui, C. Jiang, L. Wang, G. Wu, Mixformer: End-to-end tracking with iterative mixed attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13608\u201313618.","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"10.1016\/j.patcog.2026.113675_b4","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.patcog.2026.113675_b5","doi-asserted-by":"crossref","unstructured":"D. Yang, J. He, Y. Ma, Q. Yu, T. Zhang, Foreground-background distribution modeling transformer for visual object tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 10117\u201310127.","DOI":"10.1109\/ICCV51070.2023.00928"},{"key":"10.1016\/j.patcog.2026.113675_b6","series-title":"European Conference on Computer Vision","first-page":"341","article-title":"Joint feature learning and relation modeling for tracking: A one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.patcog.2026.113675_b7","series-title":"European Conference on Computer Vision","first-page":"375","article-title":"Backbone is all your need: A simplified architecture for visual object tracking","author":"Chen","year":"2022"},{"key":"10.1016\/j.patcog.2026.113675_b8","doi-asserted-by":"crossref","unstructured":"X. Chen, B. Yan, J. Zhu, D. Wang, X. Yang, H. Lu, Transformer tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8126\u20138135.","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10.1016\/j.patcog.2026.113675_b9","doi-asserted-by":"crossref","unstructured":"Z. Cao, C. Fu, J. Ye, B. Li, Y. Li, Hift: Hierarchical feature transformer for aerial tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 15457\u201315466.","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"10.1016\/j.patcog.2026.113675_b10","article-title":"Robust multi-stage tracking via multi-scale and multi-level representation learning","author":"Li","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113675_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109964","article-title":"Transformer-based visual object tracking via fine\u2013coarse concatenated attention and cross concatenated MLP","volume":"146","author":"Gao","year":"2024","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.patcog.2026.113675_b12","doi-asserted-by":"crossref","first-page":"2705","DOI":"10.1109\/TII.2022.3159648","article-title":"Visual object tracking based on light-field imaging in the presence of similar distractors","volume":"19","author":"Wang","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.patcog.2026.113675_b13","doi-asserted-by":"crossref","first-page":"4057","DOI":"10.1109\/TIP.2019.2956143","article-title":"Region attention networks for pose and occlusion robust facial expression recognition","volume":"29","author":"Wang","year":"2020","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"10.1016\/j.patcog.2026.113675_b14","doi-asserted-by":"crossref","first-page":"3848","DOI":"10.1109\/TCSVT.2023.3234312","article-title":"Multi-relations aware network for in-the-wild facial expression recognition","volume":"33","author":"Chen","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113675_b15","doi-asserted-by":"crossref","first-page":"8101","DOI":"10.1109\/TIP.2025.3637715","article-title":"A perception CNN for facial expression recognition","volume":"34","author":"Tian","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113675_b16","doi-asserted-by":"crossref","unstructured":"N. Wang, W. Zhou, J. Wang, H. Li, Transformer meets tracker: Exploiting temporal context for robust visual tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 1571\u20131580.","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"10.1016\/j.patcog.2026.113675_b17","doi-asserted-by":"crossref","unstructured":"B. Yan, H. Peng, J. Fu, D. Wang, H. Lu, Learning spatio-temporal transformer for visual tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10448\u201310457.","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"10.1016\/j.patcog.2026.113675_b18","doi-asserted-by":"crossref","unstructured":"C. Mayer, M. Danelljan, G. Bhat, M. Paul, D.P. Paudel, F. Yu, L. Van Gool, Transforming model prediction for tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8731\u20138740.","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"10.1016\/j.patcog.2026.113675_b19","doi-asserted-by":"crossref","first-page":"10055","DOI":"10.1109\/TMM.2024.3405654","article-title":"Visual object tracking with mutual affinity aligned to human intuition","volume":"26","author":"Zeng","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113675_b20","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113675_b21","doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.patcog.2026.113675_b22","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, et al., Segment anything, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.patcog.2026.113675_b23","doi-asserted-by":"crossref","unstructured":"Q. Wu, T. Yang, Z. Liu, B. Wu, Y. Shan, A.B. Chan, DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14561\u201314571.","DOI":"10.1109\/CVPR52729.2023.01399"},{"issue":"9","key":"10.1016\/j.patcog.2026.113675_b24","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":"TPAMI"},{"key":"10.1016\/j.patcog.2026.113675_b25","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.patcog.2026.113675_b26","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"},{"issue":"5","key":"10.1016\/j.patcog.2026.113675_b27","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":"TPAMI"},{"key":"10.1016\/j.patcog.2026.113675_b28","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXI 16","first-page":"771","article-title":"Ocean: Object-aware anchor-free tracking","author":"Zhang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113675_b29","doi-asserted-by":"crossref","unstructured":"X. Chen, H. Peng, D. Wang, H. Lu, H. Hu, SeqTrack: Sequence to Sequence Learning for Visual Object Tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14572\u201314581.","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"10.1016\/j.patcog.2026.113675_b30","doi-asserted-by":"crossref","unstructured":"J. Xie, B. Zhong, Z. Mo, S. Zhang, L. Shi, S. Song, R. Ji, Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19300\u201319309.","DOI":"10.1109\/CVPR52733.2024.01826"},{"key":"10.1016\/j.patcog.2026.113675_b31","article-title":"DSTrack: Diffusion-based sequence learning for visual object tracking","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113675_b32","doi-asserted-by":"crossref","unstructured":"K. He, X. Chen, S. Xie, Y. Li, P. Doll\u00e1r, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.patcog.2026.113675_b33","series-title":"ECCV","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.113675_b34","doi-asserted-by":"crossref","unstructured":"H. Law, J. Deng, Cornernet: Detecting objects as paired keypoints, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"10.1016\/j.patcog.2026.113675_b35","doi-asserted-by":"crossref","unstructured":"H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, S. Savarese, Generalized intersection over union: A metric and a loss for bounding box regression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 658\u2013666.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"10.1016\/j.patcog.2026.113675_b36","series-title":"ECCV","first-page":"547","article-title":"The eighth visual object tracking VOT2020 challenge results","author":"Kristan","year":"2020"},{"key":"10.1016\/j.patcog.2026.113675_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111128","article-title":"FocTrack: Focus attention for visual tracking","volume":"160","author":"Tao","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113675_b38","doi-asserted-by":"crossref","unstructured":"B. Yan, X. Zhang, D. Wang, H. Lu, X. Yang, Alpha-refine: Boosting tracking performance by precise bounding box estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5289\u20135298.","DOI":"10.1109\/CVPR46437.2021.00525"},{"issue":"11","key":"10.1016\/j.patcog.2026.113675_b39","doi-asserted-by":"crossref","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","article-title":"Detection and tracking meet drones challenge","volume":"44","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006400?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006400?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:29:24Z","timestamp":1784276964000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":39,"alternative-id":["S0031320326006400"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113675","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Instance-level geometric prompting for visual object tracking","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113675","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113675"}}