{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T04:56:38Z","timestamp":1776142598295,"version":"3.50.1"},"reference-count":63,"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":["62272423"],"award-info":[{"award-number":["62272423"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203480"],"award-info":[{"award-number":["62203480"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["242300421055"],"award-info":[{"award-number":["242300421055"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Hunan Province of China","doi-asserted-by":"publisher","award":["241111222400"],"award-info":[{"award-number":["241111222400"]}],"id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011447","name":"Science and Technology Department of Henan Province","doi-asserted-by":"publisher","award":["241111210400"],"award-info":[{"award-number":["241111210400"]}],"id":[{"id":"10.13039\/501100011447","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011447","name":"Science and Technology Department of Henan Province","doi-asserted-by":"publisher","award":["235200810022"],"award-info":[{"award-number":["235200810022"]}],"id":[{"id":"10.13039\/501100011447","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.jvcir.2026.104786","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T07:53:47Z","timestamp":1774338827000},"page":"104786","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Enhancing target semantic information for vision-language tracking"],"prefix":"10.1016","volume":"117","author":[{"given":"Changjun","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengqi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiaohua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanlong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhoujingzi","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.jvcir.2026.104786_b1","doi-asserted-by":"crossref","first-page":"3619","DOI":"10.1109\/TCSVT.2023.3316990","article-title":"Uav-ground visual tracking: A unified dataset and collaborative learning approach","volume":"34","author":"Sun","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"5","key":"10.1016\/j.jvcir.2026.104786_b2","doi-asserted-by":"crossref","first-page":"3943","DOI":"10.1109\/TITS.2020.3046478","article-title":"Deep learning for visual tracking: A comprehensive survey","volume":"23","author":"Marvasti-Zadeh","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.jvcir.2026.104786_b3","series-title":"CASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1670","article-title":"A new framework for multiple deep correlation filters based object tracking","author":"Liu","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104786_b4","doi-asserted-by":"crossref","first-page":"3346","DOI":"10.1109\/TMM.2020.3023794","article-title":"Temporal constraint background-aware correlation filter with saliency map","volume":"23","author":"Liao","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104786_b5","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1109\/TIP.2023.3251027","article-title":"Joint correlation and attention based feature fusion network for accurate visual tracking","volume":"32","author":"Yang","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"10.1016\/j.jvcir.2026.104786_b6","doi-asserted-by":"crossref","first-page":"4552","DOI":"10.1109\/TCSVT.2023.3281557","article-title":"Cross-drone transformer network for robust single object tracking","volume":"33","author":"Chen","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104786_b7","doi-asserted-by":"crossref","first-page":"4814","DOI":"10.1109\/TIP.2021.3076272","article-title":"Learning deep lucas-kanade siamese network for visual tracking","volume":"30","author":"Yao","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104786_b8","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.jvcir.2026.104786_b9","article-title":"Divert more attention to vision-language object tracking","author":"Guo","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104786_b10","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.jvcir.2026.104786_b11","doi-asserted-by":"crossref","unstructured":"D. Ma, X. Wu, Capsule-based object tracking with natural language specification, in: Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 1948\u20131956.","DOI":"10.1145\/3474085.3475349"},{"key":"10.1016\/j.jvcir.2026.104786_b12","unstructured":"Z. Chunhui, S. Xin, L. Li, Y. Yiqian, L. Qiong, Z. Xi, W. Yanfeng, All in one: Exploring unified vision-language tracking with multi-modal alignment, in: ACM International Conference on Multimedia, ACMMM, 2023."},{"key":"10.1016\/j.jvcir.2026.104786_b13","doi-asserted-by":"crossref","first-page":"1720","DOI":"10.1109\/TMM.2023.3285441","article-title":"One-stream vision-language memory network for object tracking","volume":"26","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"issue":"4","key":"10.1016\/j.jvcir.2026.104786_b14","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.jvcir.2026.104786_b15","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.jvcir.2026.104786_b16","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104786_b17","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104786_b18","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.jvcir.2026.104786_b19","doi-asserted-by":"crossref","unstructured":"Z. Song, J. Yu, Y.-P.P. Chen, W. Yang, Transformer tracking with cyclic shifting window attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8791\u20138800.","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"10.1016\/j.jvcir.2026.104786_b20","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.jvcir.2026.104786_b21","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.jvcir.2026.104786_b22","doi-asserted-by":"crossref","unstructured":"S. Gao, C. Zhou, J. Zhang, Generalized relation modeling for transformer tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18686\u201318695.","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"10.1016\/j.jvcir.2026.104786_b23","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.jvcir.2026.104786_b24","first-page":"2321","article-title":"Compact transformer tracker with correlative masked modeling","volume":"vol. 37","author":"Song","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104786_b25","article-title":"Robust tracking via combing top-down and bottom-up attention","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104786_b26","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.jvcir.2026.104786_b27","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14572","article-title":"Seqtrack: Sequence to sequence learning for visual object tracking","author":"Chen","year":"2023"},{"issue":"7","key":"10.1016\/j.jvcir.2026.104786_b28","doi-asserted-by":"crossref","first-page":"9370","DOI":"10.1109\/TITS.2025.3570076","article-title":"Hierarchical attention-enhanced correlation refinement for robust visual tracking","volume":"26","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.jvcir.2026.104786_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106380","article-title":"DeforT: Deformable transformer for visual tracking","volume":"176","author":"Yang","year":"2024","journal-title":"Neural Netw."},{"issue":"10","key":"10.1016\/j.jvcir.2026.104786_b30","doi-asserted-by":"crossref","first-page":"9053","DOI":"10.1109\/TCSVT.2024.3395352","article-title":"One-stream stepwise decreasing for vision-language tracking","volume":"34","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104786_b31","unstructured":"G. Zhang, B. Zhong, Q. Liang, Z. Mo, S. Song, Diffusion mask-driven visual-language tracking, in: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, 2024, pp. 1652\u20131660."},{"key":"10.1016\/j.jvcir.2026.104786_b32","first-page":"4107","article-title":"Unifying visual and vision-language tracking via contrastive learning","volume":"vol. 38","author":"Ma","year":"2024"},{"issue":"5","key":"10.1016\/j.jvcir.2026.104786_b33","doi-asserted-by":"crossref","first-page":"4271","DOI":"10.1109\/TCSVT.2024.3520354","article-title":"Progressive semantic-visual alignment and refinement for vision-language tracking","volume":"35","author":"Liang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104786_b34","unstructured":"X. Feng, X. Li, S. Hu, D. Zhang, MemVLT: Vision-language tracking with adaptive memory-based prompts. Journal Name, volume:pages, year."},{"key":"10.1016\/j.jvcir.2026.104786_b35","series-title":"ATCTrack: Aligning target-context cues with dynamic target states for robust vision-language tracking","author":"Feng","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104786_b36","doi-asserted-by":"crossref","unstructured":"X. Feng, D. Zhang, S. Hu, et al., Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues, in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2025, pp. 1\u20135.","DOI":"10.1109\/ICASSP49660.2025.10888064"},{"key":"10.1016\/j.jvcir.2026.104786_b37","series-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104786_b38","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Doll\u00e1r, Focal Loss for Dense Object Detection, in: Proc. IEEE Int. Conf. Comput. Vis., ICCV, 2017, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.jvcir.2026.104786_b39","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.jvcir.2026.104786_b40","unstructured":"X. Zhang, Y. Tian, L. Xie, W. Huang, Q. Dai, Q. Ye, Q. Tian, Hivit: A simpler and more efficient design of hierarchical vision transformer, in: The Eleventh International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.jvcir.2026.104786_b41","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.jvcir.2026.104786_b42","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.jvcir.2026.104786_b43","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.jvcir.2026.104786_b44","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"},{"key":"10.1016\/j.jvcir.2026.104786_b45","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1007\/s11263-020-01387-y","article-title":"Lasot: A high-quality large-scale single object tracking benchmark","volume":"129","author":"Fan","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104786_b46","unstructured":"S. Hu, D. Zhang, M. Wu, X. Feng, X. Li, X. Zhao, K. Huang, A Multi-Modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-Temporal and Causal Relationship, in: Proc. 37th Int. Conf. Neural Inf. Process. Syst., NeurIPS, New Orleans, LA, USA, 2023, pp. 1\u201324, 1087."},{"key":"10.1016\/j.jvcir.2026.104786_b47","doi-asserted-by":"crossref","unstructured":"Z. Chen, B. Zhong, G. Li, S. Zhang, R. Ji, Siamese box adaptive network for visual tracking, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 6667\u20136676.","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"10.1016\/j.jvcir.2026.104786_b48","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-021-01559-4","article-title":"Joint classification and regression for visual tracking with fully convolutional siamese networks","author":"Cui","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104786_b49","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.jvcir.2026.104786_b50","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.jvcir.2026.104786_b51","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1109\/TMM.2021.3074239","article-title":"SiamCorners: Siamese corner networks for visual tracking","volume":"24","author":"Yang","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104786_b52","series-title":"Learning target-aware representation for visual tracking via informative interactions","author":"Guo","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104786_b53","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1109\/TMM.2023.3264851","article-title":"CMAT: Integrating convolution mixer and self-attention for visual tracking","volume":"26","author":"Wang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104786_b54","series-title":"Autoregressive queries for adaptive tracking with spatio-temporal transformers","first-page":"19300","author":"Xie","year":"2024"},{"issue":"11","key":"10.1016\/j.jvcir.2026.104786_b55","doi-asserted-by":"crossref","first-page":"11362","DOI":"10.1109\/TCSVT.2025.3578479","article-title":"Robust object tracking via long-range spatial representation and local feature enhancement","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"10.1016\/j.jvcir.2026.104786_b56","doi-asserted-by":"crossref","first-page":"10192","DOI":"10.1109\/TPAMI.2025.3593543","article-title":"Towards universal modal tracking with online dense temporal token learning","volume":"47","author":"Zheng","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104786_b57","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"},{"issue":"9","key":"10.1016\/j.jvcir.2026.104786_b58","doi-asserted-by":"crossref","first-page":"3433","DOI":"10.1109\/TCSVT.2020.3038720","article-title":"Grounding-tracking-integration","volume":"31","author":"Yang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104786_b59","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.jvcir.2026.104786_b60","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"},{"issue":"9","key":"10.1016\/j.jvcir.2026.104786_b61","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 Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"10.1016\/j.jvcir.2026.104786_b62","doi-asserted-by":"crossref","first-page":"11362","DOI":"10.1109\/TCSVT.2025.3578479","article-title":"Robust object tracking via long-range spatial representation and local feature enhancement","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"7","key":"10.1016\/j.jvcir.2026.104786_b63","doi-asserted-by":"crossref","first-page":"9370","DOI":"10.1109\/TITS.2025.3570076","article-title":"Hierarchical attention-enhanced correlation refinement for robust visual tracking","volume":"26","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000817?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000817?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T04:23:04Z","timestamp":1776140584000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":63,"alternative-id":["S1047320326000817"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104786","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing target semantic information for vision-language tracking","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104786","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104786"}}