{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T15:17:53Z","timestamp":1783178273377,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["262102210025"],"award-info":[{"award-number":["262102210025"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["235200810022"],"award-info":[{"award-number":["235200810022"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006407","name":"Henan Province Natural Science Foundation","doi-asserted-by":"publisher","award":["252300 420389"],"award-info":[{"award-number":["252300 420389"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473341"],"award-info":[{"award-number":["62473341"]}],"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":["62272423"],"award-info":[{"award-number":["62272423"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018607","name":"Henan Province Science and Technology Innovation Talent Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.image.2026.117583","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T15:32:13Z","timestamp":1780155133000},"page":"117583","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dynamic multi-modal prompt generation for Visual-Language Tracking"],"prefix":"10.1016","volume":"148","author":[{"given":"Huanlong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6338-4051","authenticated-orcid":false,"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.image.2026.117583_b1","series-title":"Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.image.2026.117583_b2","doi-asserted-by":"crossref","first-page":"3351","DOI":"10.1109\/TIP.2019.2959256","article-title":"Local semantic siamese networks for fast tracking","volume":"29","author":"Liang","year":"2019","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"10.1016\/j.image.2026.117583_b3","first-page":"8049","article-title":"Adaptive siamese tracking with a compact latent network","volume":"45","author":"Dong","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2026.117583_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110286","article-title":"SiamSTC: Updatable siamese tracking network via spatio-temporal context","volume":"263","author":"Wei","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.image.2026.117583_b5","unstructured":"Zhenyang Li, Ran Tao, Efstratios Gavves, Cees G.M. Snoek, Arnold W.M. Smeulders, Tracking by natural language specification, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6495\u20136503."},{"key":"10.1016\/j.image.2026.117583_b6","doi-asserted-by":"crossref","unstructured":"Xiao Wang, Xiujun Shu, Zhipeng Zhang, Bo Jiang, Yaowei Wang, Yonghong Tian, Feng 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.image.2026.117583_b7","doi-asserted-by":"crossref","unstructured":"Li Zhou, Zikun Zhou, Kaige Mao, Zhenyu 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.image.2026.117583_b8","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."},{"key":"10.1016\/j.image.2026.117583_b9","doi-asserted-by":"crossref","unstructured":"Qi Feng, Vitaly Ablavsky, Qinxun Bai, Stan 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.image.2026.117583_b10","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.image.2026.117583_b11","unstructured":"Yihao Li, Jun Yu, Zhongpeng Cai, Yuwen Pan, Cross-modal target retrieval for tracking by natural language, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4931\u20134940."},{"key":"10.1016\/j.image.2026.117583_b12","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2024.3410141","article-title":"Language-guided dual-modal local correspondence for single object tracking","author":"Yu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"issue":"9","key":"10.1016\/j.image.2026.117583_b13","doi-asserted-by":"crossref","first-page":"6267","DOI":"10.1109\/TCSVT.2022.3165536","article-title":"Target-distractor aware deep tracking with discriminative enhancement learning loss","volume":"32","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117583_b14","unstructured":"Kaiwen Liu, Jin Gao, Haowei Liu, Liang Li, Bing Li, Weiming Hu, Exploring motion information for distractor suppression in visual tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1924\u20131932."},{"key":"10.1016\/j.image.2026.117583_b15","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Procontext: Exploring progressive context transformer for tracking","author":"Lan","year":"2023"},{"issue":"5","key":"10.1016\/j.image.2026.117583_b16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3726529","article-title":"Beyond visual cues: Synchronously exploring target-centric semantics for vision-language tracking","volume":"21","author":"Ge","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.image.2026.117583_b17","doi-asserted-by":"crossref","unstructured":"Jiawei Ge, Jiuxin Cao, Xuelin Zhu, Xinyu Zhang, Chang Liu, Kun Wang, Bo 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.image.2026.117583_b18","first-page":"4107","article-title":"Unifying visual and vision-language tracking via contrastive learning","volume":"38","author":"Ma","year":"2024"},{"key":"10.1016\/j.image.2026.117583_b19","doi-asserted-by":"crossref","unstructured":"Xiaohai Li, Bineng Zhong, Qihua Liang, Zhiyi Mo, Jian Nong, Shuxiang Song, Dynamic Updates for Language Adaptation in Visual-Language Tracking, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 19165\u201319174.","DOI":"10.1109\/CVPR52734.2025.01785"},{"key":"10.1016\/j.image.2026.117583_b20","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"8025","article-title":"Textual tokens classification for multi-modal alignment in vision-language tracking","author":"Mao","year":"2024"},{"key":"10.1016\/j.image.2026.117583_b21","doi-asserted-by":"crossref","unstructured":"Xuchen Li, Xiaokun Feng, Shiyu Hu, Meiqi Wu, Dailing Zhang, Jing Zhang, Kaiqi Huang, Dtllm-vlt: Diverse text generation for visual language tracking based on llm, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 7283\u20137292.","DOI":"10.1109\/CVPRW63382.2024.00724"},{"key":"10.1016\/j.image.2026.117583_b22","doi-asserted-by":"crossref","unstructured":"Xin Li, Yuqing Huang, Zhenyu He, Yaowei Wang, Huchuan Lu, Ming-Hsuan 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.image.2026.117583_b23","unstructured":"Zhihong Fu, Qingjie Liu, Zehua Fu, Yunhong Wang, Stmtrack: Template-free visual tracking with space-time memory networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13774\u201313783."},{"issue":"5","key":"10.1016\/j.image.2026.117583_b24","doi-asserted-by":"crossref","first-page":"2976","DOI":"10.1109\/TCSVT.2021.3094645","article-title":"Object tracking via spatial-temporal memory network","volume":"32","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117583_b25","series-title":"Learning historical status prompt for accurate and robust visual tracking","author":"Cai","year":"2023"},{"key":"10.1016\/j.image.2026.117583_b26","article-title":"Attention-driven memory network for online visual tracking","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.image.2026.117583_b27","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.ins.2022.03.047","article-title":"Residual memory inference network for regression tracking with weighted gradient harmonized loss","volume":"597","author":"Zhang","year":"2022","journal-title":"Inform. Sci."},{"issue":"6","key":"10.1016\/j.image.2026.117583_b28","doi-asserted-by":"crossref","first-page":"2120","DOI":"10.1007\/s12559-023-10173-0","article-title":"A perceptually adaptive long-term tracking method for the complete occlusion and disappearance of a target","volume":"15","author":"Chen","year":"2023","journal-title":"Cogn. Comput."},{"key":"10.1016\/j.image.2026.117583_b29","doi-asserted-by":"crossref","unstructured":"Dawei Yang, Jianfeng He, Yinchao Ma, Qianjin Yu, Tianzhu 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.image.2026.117583_b30","unstructured":"Goutam Yelluru Gopal, Maria A. Amer, Separable self and mixed attention transformers for efficient object tracking, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 6708\u20136717."},{"issue":"21","key":"10.1016\/j.image.2026.117583_b31","doi-asserted-by":"crossref","first-page":"798","DOI":"10.1049\/ell2.12610","article-title":"Joint visual template and natural language for robust visual tracking","volume":"58","author":"Wang","year":"2022","journal-title":"Electron. Lett."},{"key":"10.1016\/j.image.2026.117583_b32","article-title":"Towards unified token learning for vision-language tracking","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117583_b33","doi-asserted-by":"crossref","unstructured":"Yanyan Shao, Shuting He, Qi Ye, Yuchao Feng, Wenhan Luo, Jiming 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.image.2026.117583_b34","doi-asserted-by":"crossref","unstructured":"Chunhui Zhang, Xin Sun, Yiqian Yang, Li Liu, Qiong Liu, Xi Zhou, Yanfeng Wang, All in one: Exploring unified vision-language tracking with multi-modal alignment, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 5552\u20135561.","DOI":"10.1145\/3581783.3611803"},{"key":"10.1016\/j.image.2026.117583_b35","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.image.2026.117583_b36","doi-asserted-by":"crossref","first-page":"49250","DOI":"10.52202\/075280-2142","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.image.2026.117583_b37","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.image.2026.117583_b38","doi-asserted-by":"crossref","unstructured":"Xin Chen, Bin Yan, Jiawen Zhu, Dong Wang, Xiaoyun Yang, Huchuan 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.image.2026.117583_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113230","article-title":"Target\u2013background interaction modeling transformer for object tracking","volume":"315","author":"Zhang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.image.2026.117583_b40","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.patrec.2023.02.023","article-title":"Transformer vision-language tracking via proxy token guided cross-modal fusion","volume":"168","author":"Zhao","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.image.2026.117583_b41","doi-asserted-by":"crossref","unstructured":"Heng Fan, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Hexin Bai, Yong Xu, Chunyuan Liao, Haibin 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.image.2026.117583_b42","doi-asserted-by":"crossref","unstructured":"Ning Wang, Wengang Zhou, Jie Wang, Houqiang 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.image.2026.117583_b43","series-title":"Learning target-aware representation for visual tracking via informative interactions","author":"Guo","year":"2022"},{"issue":"10","key":"10.1016\/j.image.2026.117583_b44","doi-asserted-by":"crossref","first-page":"9774","DOI":"10.1109\/TCSVT.2024.3402436","article-title":"Robust tracking via combing top-down and bottom-up attention","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"7","key":"10.1016\/j.image.2026.117583_b45","doi-asserted-by":"crossref","first-page":"5831","DOI":"10.1007\/s00521-024-10921-9","article-title":"Historical states modeling for visual tracking","volume":"37","author":"Shi","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.image.2026.117583_b46","article-title":"Progressive semantic-visual alignment and refinement for vision-language tracking","author":"Liang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117583_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110787","article-title":"Joint feature extraction and alignment in object tracking with vision-language model","volume":"152","author":"Zhu","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.image.2026.117583_b48","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.image.2026.117583_b49","series-title":"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)","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.image.2026.117583_b50","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"}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526001062?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526001062?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:37:51Z","timestamp":1783175871000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596526001062"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"alternative-id":["S0923596526001062"],"URL":"https:\/\/doi.org\/10.1016\/j.image.2026.117583","relation":{},"ISSN":["0923-5965"],"issn-type":[{"value":"0923-5965","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dynamic multi-modal prompt generation for Visual-Language Tracking","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.image.2026.117583","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":"117583"}}