{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T09:25:58Z","timestamp":1787217958701,"version":"build-2736575974"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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":["62576264"],"award-info":[{"award-number":["62576264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2025ZD0551500"],"award-info":[{"award-number":["2025ZD0551500"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2025ZD0551502"],"award-info":[{"award-number":["2025ZD0551502"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["62431020,62231027"],"award-info":[{"award-number":["62431020,62231027"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B07048"],"award-info":[{"award-number":["B07048"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018621","name":"Program for Changjiang Scholars and Innovative Research Team in University","doi-asserted-by":"publisher","award":["IRT 15R53"],"award-info":[{"award-number":["IRT 15R53"]}],"id":[{"id":"10.13039\/501100018621","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["GZC20232033"],"award-info":[{"award-number":["GZC20232033"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015009","name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015009","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012659","name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005320","name":"Xidian University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005320","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031935","name":"Xi'an Jiaotong University","doi-asserted-by":"publisher","award":["HMHAI-202405"],"award-info":[{"award-number":["HMHAI-202405"]}],"id":[{"id":"10.13039\/100031935","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031935","name":"Xi'an Jiaotong University","doi-asserted-by":"publisher","award":["HMHAI-202404"],"award-info":[{"award-number":["HMHAI-202404"]}],"id":[{"id":"10.13039\/100031935","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":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114273","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T15:49:25Z","timestamp":1781711365000},"page":"114273","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["TFBTrack: Target-Aware Foreground\u2013Background Modeling for vision\u2013language tracking"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0375-9253","authenticated-orcid":false,"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingling","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114273_b1","doi-asserted-by":"crossref","unstructured":"Q. Feng, V. Ablavsky, Q. Bai, G. Li, S. Sclaroff, Real-time visual object tracking with natural language description, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2020, pp. 700\u2013709.","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"10.1016\/j.patcog.2026.114273_b2","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.2026.114273_b3","doi-asserted-by":"crossref","first-page":"4446","DOI":"10.52202\/068431-0321","article-title":"Divert more attention to vision-language tracking","volume":"35","author":"Guo","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114273_b4","article-title":"Text generation and multi-modal knowledge transfer for few-shot object detection","author":"Du","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114273_b5","doi-asserted-by":"crossref","unstructured":"Z. Li, R. Tao, E. Gavves, C.G. Snoek, A.W. Smeulders, Tracking by natural language specification, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6495\u20136503.","DOI":"10.1109\/CVPR.2017.777"},{"key":"10.1016\/j.patcog.2026.114273_b6","doi-asserted-by":"crossref","unstructured":"X. Li, Y. Huang, Z. He, Y. Wang, H. Lu, M.-H. Yang, Citetracker: Correlating image and text for visual tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 9974\u20139983.","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"10.1016\/j.patcog.2026.114273_b7","doi-asserted-by":"crossref","unstructured":"B. Li, H. Dong, D. Zhang, Z. Zhao, H. Sun, J. Gao, Exploring efficient open-vocabulary segmentation in the remote sensing, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 40, 2026, pp. 5982\u20135991.","DOI":"10.1609\/aaai.v40i8.37521"},{"key":"10.1016\/j.patcog.2026.114273_b8","doi-asserted-by":"crossref","unstructured":"D. Zhang, F. Wang, B. Li, Z. Zhao, J. Gao, X. Li, KAID: Knowledge-Aware Interactive Distillation for Vision-Language Models, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 3212\u20133221.","DOI":"10.1145\/3746027.3755008"},{"key":"10.1016\/j.patcog.2026.114273_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111801","article-title":"U3M: Unbiased multiscale modal fusion model for multimodal semantic segmentation","volume":"168","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114273_b10","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.patcog.2017.11.007","article-title":"Deep visual tracking: Review and experimental comparison","volume":"76","author":"Li","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114273_b11","article-title":"Adaptive visual prompting for effective satellite video tracking","author":"Wang","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114273_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107233","article-title":"Online tracking of ants based on deep association metrics: method, dataset and evaluation","volume":"103","author":"Cao","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114273_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107796","article-title":"Deep mutual learning for visual object tracking","volume":"112","author":"Zhao","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114273_b14","doi-asserted-by":"crossref","unstructured":"Z. Zhang, H. Peng, Deeper and wider siamese networks for real-time visual tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4591\u20134600.","DOI":"10.1109\/CVPR.2019.00472"},{"key":"10.1016\/j.patcog.2026.114273_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107157","article-title":"Transfer learning-based discriminative correlation filter for visual tracking","volume":"100","author":"Huang","year":"2020","journal-title":"Pattern Recognit."},{"issue":"7","key":"10.1016\/j.patcog.2026.114273_b16","doi-asserted-by":"crossref","first-page":"6253","DOI":"10.1109\/TCSVT.2024.3358549","article-title":"Satellite video object tracking based on location prompts","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114273_b17","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-97-5208-9","article-title":"Multi-modal visual tracking based on textual generation","author":"Wang","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.patcog.2026.114273_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109652","article-title":"Knowledge transduction for cross-domain few-shot learning","volume":"141","author":"Li","year":"2023","journal-title":"Pattern Recognit."},{"issue":"12","key":"10.1016\/j.patcog.2026.114273_b19","doi-asserted-by":"crossref","first-page":"12770","DOI":"10.1109\/TCSVT.2024.3436878","article-title":"Visual and language collaborative learning for RGBT object tracking","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114273_b20","doi-asserted-by":"crossref","unstructured":"X. Wang, X. Shu, Z. Zhang, B. Jiang, Y. Wang, Y. Tian, F. Wu, Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13763\u201313773.","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"10.1016\/j.patcog.2026.114273_b21","doi-asserted-by":"crossref","unstructured":"L. Zhou, Z. Zhou, K. Mao, Z. He, Joint visual grounding and tracking with natural language specification, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 23151\u201323160.","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"10.1016\/j.patcog.2026.114273_b22","doi-asserted-by":"crossref","unstructured":"Y. Shao, S. He, Q. Ye, Y. Feng, W. Luo, J. Chen, Context-Aware Integration of Language and Visual References for Natural Language Tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19208\u201319217.","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"10.1016\/j.patcog.2026.114273_b23","doi-asserted-by":"crossref","unstructured":"Z. Zhang, Y. Liu, X. Wang, B. Li, W. Hu, Learn to match: Automatic matching network design for visual tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13339\u201313348.","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"10.1016\/j.patcog.2026.114273_b24","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.2026.114273_b25","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.2026.114273_b26","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.2026.114273_b27","doi-asserted-by":"crossref","unstructured":"X. Wei, Y. Bai, Y. Zheng, D. Shi, Y. Gong, Autoregressive visual tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9697\u20139706.","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"10.1016\/j.patcog.2026.114273_b28","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.2026.114273_b29","article-title":"Adaptively bypassing vision transformer blocks for efficient visual tracking","author":"Yang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114273_b30","doi-asserted-by":"crossref","unstructured":"Q. Feng, V. Ablavsky, Q. Bai, S. Sclaroff, Siamese natural language tracker: Tracking by natural language descriptions with siamese trackers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5851\u20135860.","DOI":"10.1109\/CVPR46437.2021.00579"},{"issue":"4","key":"10.1016\/j.patcog.2026.114273_b31","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/TCSVT.2023.3301933","article-title":"Toward unified token learning for vision-language tracking","volume":"34","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114273_b32","doi-asserted-by":"crossref","unstructured":"D. Ma, X. Wu, Tracking by Natural Language Specification with Long Short-term Context Decoupling, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 14012\u201314021.","DOI":"10.1109\/ICCV51070.2023.01288"},{"key":"10.1016\/j.patcog.2026.114273_b33","doi-asserted-by":"crossref","unstructured":"Z. Mo, G. Zhang, J. Nong, B. Zhong, Z. Li, Dual-stream Multi-modal Interactive Vision-language Tracking, in: Proceedings of the 6th ACM International Conference on Multimedia in Asia, 2024, pp. 1\u20137.","DOI":"10.1145\/3696409.3700220"},{"key":"10.1016\/j.patcog.2026.114273_b34","doi-asserted-by":"crossref","unstructured":"J. Ge, J. Cao, X. Zhu, X. Zhang, C. Liu, K. Wang, B. Liu, Consistencies are all you need for semi-supervised vision-language tracking, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 1895\u20131904.","DOI":"10.1145\/3664647.3680657"},{"key":"10.1016\/j.patcog.2026.114273_b35","first-page":"14903","article-title":"MemVLT: Vision-language tracking with adaptive memory-based prompts","volume":"37","author":"Feng","year":"2025","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"9","key":"10.1016\/j.patcog.2026.114273_b36","doi-asserted-by":"crossref","first-page":"9287","DOI":"10.1109\/TCSVT.2025.3557053","article-title":"Learning language prompt for vision-language tracking","volume":"35","author":"Zong","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114273_b37","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.patcog.2026.114273_b38","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.2026.114273_b39","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.2026.114273_b40","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.2026.114273_b41","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.114273_b42","doi-asserted-by":"crossref","unstructured":"H. Fan, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, H. Bai, Y. Xu, C. Liao, H. Ling, Lasot: A high-quality benchmark for large-scale single object tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5374\u20135383.","DOI":"10.1109\/CVPR.2019.00552"},{"key":"10.1016\/j.patcog.2026.114273_b43","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.114273_b44","series-title":"Towards efficient visual adaption via structural re-parameterization","author":"Luo","year":"2023"},{"key":"10.1016\/j.patcog.2026.114273_b45","series-title":"Exploring the underwater world segmentation without extra training","author":"Li","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012380?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012380?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:52:28Z","timestamp":1787215948000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":45,"alternative-id":["S0031320326012380"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114273","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TFBTrack: Target-Aware Foreground\u2013Background Modeling for vision\u2013language tracking","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114273","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":"114273"}}