{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:58:05Z","timestamp":1780934285956,"version":"3.54.1"},"reference-count":41,"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"}],"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.2026.113961","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T22:56:56Z","timestamp":1779145016000},"page":"113961","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["LiteTrack: Towards efficient vision-language tracking with parameter freezing and feature selection"],"prefix":"10.1016","volume":"180","author":[{"given":"Liqiang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingling","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfang","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiantian","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anyuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113961_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109630","article-title":"SiamRank: A siamese based visual tracking network with ranking strategy","volume":"141","author":"Meng","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113961_b2","unstructured":"Zhenyang Li, Ran Tao, Efstratios Gavves, Cees GM Snoek, Arnold WM 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.patcog.2026.113961_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112225","article-title":"ConsistencyTrack: A robust multi-object tracker with a generation strategy of consistency model","volume":"171","author":"Jiang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113961_b4","article-title":"Transstc: transformer tracker meets efficient spatial-temporal cues","volume":"172","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113961_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111389","article-title":"Multi-domain universal representation learning for hyperspectral object tracking","volume":"162","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113961_b6","series-title":"2021 International Joint Conference on Neural Networks","first-page":"1","article-title":"Transformer with local-feature extractor for relation extraction","author":"Liu","year":"2021"},{"issue":"8","key":"10.1016\/j.patcog.2026.113961_b7","doi-asserted-by":"crossref","first-page":"1076","DOI":"10.3390\/sym16081076","article-title":"UAV tracking via saliency-aware and spatial\u2013temporal regularization correlation filter learning","volume":"16","author":"Liu","year":"2024","journal-title":"Symmetry"},{"key":"10.1016\/j.patcog.2026.113961_b8","doi-asserted-by":"crossref","unstructured":"Bo Li, Junjie Yan, Wei Wu, Zheng Zhu, Xiaolin Hu, High performance visual tracking with siamese region proposal network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8971\u20138980.","DOI":"10.1109\/CVPR.2018.00935"},{"key":"10.1016\/j.patcog.2026.113961_b9","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.patcog.2026.113961_b10","first-page":"16743","article-title":"Swintrack: A simple and strong baseline for transformer tracking","volume":"35","author":"Lin","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113961_b11","article-title":"FocTrack: Focus attention for visual tracking","volume":"160","author":"Tao","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113961_b12","series-title":"Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning","author":"He","year":"2023"},{"key":"10.1016\/j.patcog.2026.113961_b13","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"},{"key":"10.1016\/j.patcog.2026.113961_b14","doi-asserted-by":"crossref","unstructured":"Qi Feng, Vitaly Ablavsky, Qinxun Bai, Guorong Li, Stan 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":"5","key":"10.1016\/j.patcog.2026.113961_b15","doi-asserted-by":"crossref","first-page":"3156","DOI":"10.1109\/TPAMI.2023.3339661","article-title":"X2-VLM: All-in-one pre-trained model for vision-language tasks","volume":"46","author":"Zeng","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113961_b16","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.patcog.2026.113961_b17","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.patcog.2026.113961_b18","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: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 19165\u201319174.","DOI":"10.1109\/CVPR52734.2025.01785"},{"key":"10.1016\/j.patcog.2026.113961_b19","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.patcog.2026.113961_b20","first-page":"4107","article-title":"Unifying visual and vision-language tracking via contrastive learning","volume":"vol. 38","author":"Ma","year":"2024"},{"issue":"1","key":"10.1016\/j.patcog.2026.113961_b21","doi-asserted-by":"crossref","first-page":"24356","DOI":"10.1038\/s41598-025-09101-z","article-title":"ResNet-based image processing approach for precise detection of cracks in photovoltaic panels","volume":"15","author":"Abdelsattar","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.patcog.2026.113961_b22","article-title":"Detecting dusty and clean photovoltaic surfaces using MobileNet variants for image classification","author":"Abdelsattar","year":"2025","journal-title":"SVU-International J. Eng. Sci. Appl."},{"issue":"1","key":"10.1016\/j.patcog.2026.113961_b23","doi-asserted-by":"crossref","first-page":"15650","DOI":"10.1038\/s41598-025-98607-7","article-title":"Comparative analysis of machine learning techniques for temperature and humidity prediction in photovoltaic environments","volume":"15","author":"Abdelsattar","year":"2025","journal-title":"Sci Rep"},{"key":"10.1016\/j.patcog.2026.113961_b24","doi-asserted-by":"crossref","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina 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), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.patcog.2026.113961_b25","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, Ross Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000\u201316009."},{"key":"10.1016\/j.patcog.2026.113961_b26","doi-asserted-by":"crossref","unstructured":"Ailin Deng, Tri Cao, Zhirui Chen, Bryan Hooi, Words or Vision: Do Vision-Language Models Have Blind Faith in Text?, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 3867\u20133876.","DOI":"10.1109\/CVPR52734.2025.00366"},{"key":"10.1016\/j.patcog.2026.113961_b27","unstructured":"Mu Cai, Jianwei Yang, Jianfeng Gao, Yong Jae Lee, Matryoshka multimodal models, in: Workshop on Video-Language Models@ NeurIPS 2024, 2024."},{"key":"10.1016\/j.patcog.2026.113961_b28","doi-asserted-by":"crossref","unstructured":"Yi Wu, Jongwoo Lim, Ming-Hsuan Yang, Online object tracking: A benchmark, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 2411\u20132418.","DOI":"10.1109\/CVPR.2013.312"},{"key":"10.1016\/j.patcog.2026.113961_b29","doi-asserted-by":"crossref","unstructured":"Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, Alan L Yuille, Kevin Murphy, Generation and comprehension of unambiguous object descriptions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 11\u201320.","DOI":"10.1109\/CVPR.2016.9"},{"issue":"5","key":"10.1016\/j.patcog.2026.113961_b30","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":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113961_b31","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.patcog.2026.113961_b32","series-title":"Robust visual object tracking with natural language region proposal network","first-page":"8","author":"Feng","year":"2019"},{"issue":"9","key":"10.1016\/j.patcog.2026.113961_b33","doi-asserted-by":"crossref","first-page":"3433","DOI":"10.1109\/TCSVT.2020.3038720","article-title":"Grounding-tracking-integration","volume":"31","author":"Yang","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113961_b34","doi-asserted-by":"crossref","unstructured":"Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan, Siamrpn++: Evolution of siamese visual tracking with very deep networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4282\u20134291.","DOI":"10.1109\/CVPR.2019.00441"},{"key":"10.1016\/j.patcog.2026.113961_b35","series-title":"European Conference on Computer Vision","first-page":"771","article-title":"Ocean: Object-aware anchor-free tracking","author":"Zhang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113961_b36","first-page":"12549","article-title":"Siamfc++: Towards robust and accurate visual tracking with target estimation guidelines","volume":"vol. 34","author":"Xu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113961_b37","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.patcog.2026.113961_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.2026.113961_b39","doi-asserted-by":"crossref","unstructured":"Li Yang, Yan Xu, Chunfeng Yuan, Wei Liu, Bing Li, Weiming Hu, Improving visual grounding with visual-linguistic verification and iterative reasoning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9499\u20139508.","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"10.1016\/j.patcog.2026.113961_b40","doi-asserted-by":"crossref","unstructured":"Bin Yan, Houwen Peng, Jianlong Fu, Dong Wang, Huchuan 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.2026.113961_b41","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"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600926X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600926X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:03:31Z","timestamp":1780931011000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032600926X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":41,"alternative-id":["S003132032600926X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113961","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":"LiteTrack: Towards efficient vision-language tracking with parameter freezing and feature selection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113961","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":"113961"}}