{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:46:24Z","timestamp":1776786384497,"version":"3.51.2"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"name":"National Key Research and Development Program Project of China","award":["2024YFC3306902"],"award-info":[{"award-number":["2024YFC3306902"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China under","doi-asserted-by":"crossref","award":["U24A20242, 62272267"],"award-info":[{"award-number":["U24A20242, 62272267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["LZ26F020008, LY23F020023, LQZSZ25E050002"],"award-info":[{"award-number":["LZ26F020008, LY23F020023, LQZSZ25E050002"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100022955","name":"Fundamental Research Funds for the Provincial Universities of Zhejiang","doi-asserted-by":"crossref","award":["RF-A2024013"],"award-info":[{"award-number":["RF-A2024013"]}],"id":[{"id":"10.13039\/100022955","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhejiang Key Laboratory of Intelligent Manufacturing for Aerodynamic Equipment","award":["2025ZY01027,2025E10033"],"award-info":[{"award-number":["2025ZY01027,2025E10033"]}]},{"name":"Hangzhou AI major scientific and technological innovation project","award":["2022AIZD0061"],"award-info":[{"award-number":["2022AIZD0061"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>In general, local Visual-Language (VL) trackers search targets around the previous bounding box by initial VL annotations. However, there is an inherent contradiction between the local searching perspective of the tracker and the orientation descriptions in language conducted under the global perspective. Furthermore, most methods only fuse modality information in a single stage, which tends to an insufficient relation modeling. To address these issues, we propose a Global Vision-Language Tracker (GVLTrack) with multi-stage modal fusion. First, it tracks the target in the entire image instead of local tracking based on previous results to resolve the above contradiction. Second, GVLTrack incorporates three modal interaction modules: Consistent Relationship Modeling (CRM), VL-Guided Query (VLQ) Initialization, and Recurrent Cross-Modal Decoder (RC-Decoder) to fuse vision-language modality and refine the bounding box progressively comprehensively. We conduct extensive experiments on several benchmarks and achieve competitive performance, demonstrating the effectiveness of our approach. The code will be made publicly available as soon as it is accepted.<\/jats:p>","DOI":"10.1145\/3803863","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T13:51:36Z","timestamp":1774533096000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GVLTrack: Global Vision-Language Tracking with Multi-Stage Modal Fusion"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1809-5138","authenticated-orcid":false,"given":"Jian","family":"Tao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8916-1174","authenticated-orcid":false,"given":"Sixian","family":"Chan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China and Zhejiang Key Laboratory of Intelligent Manufacturing for Aerodynamic Equipment, Quzhou University, Quzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6177-3862","authenticated-orcid":false,"given":"Cong","family":"Bai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0958-7285","authenticated-orcid":false,"given":"Xiaoqin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_13"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148876"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3674980"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V39I2.32223"},{"key":"e_1_3_1_7_2","first-page":"8126","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201921)","author":"Chen Xin","year":"2021","unstructured":"Xin Chen, Bin Yan, Jiawen Zhu, Dong Wang, Xiaoyun Yang, and Huchuan Lu. 2021. Transformer tracking. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201921). IEEE, 8126\u20138135."},{"key":"e_1_3_1_8_2","first-page":"6668","volume-title":"The IEEE Conference on Computer Vision and Pattern Recognition","author":"Chen Zedu","year":"2020","unstructured":"Zedu Chen, Bineng Zhong, Guorong Li, Shengping Zhang, and Rongrong Ji. 2020. Siamese box adaptive network for visual tracking. In The IEEE Conference on Computer Vision and Pattern Recognition, 6668\u20136677."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/S11263-021-01559-4"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"e_1_3_1_11_2","volume-title":"International Conference on Learning Representations (ICLR \u201921)","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, and Sylvain Gelly. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR \u201921). OpenReview.net."},{"key":"e_1_3_1_12_2","first-page":"5374","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201919)","author":"Fan Heng","year":"2019","unstructured":"Heng Fan, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Hexin Bai, Yong Xu, Chunyuan Liao, and Haibin Ling. 2019. Lasot: A high-quality benchmark for large-scale single object tracking. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201919), 5374\u20135383."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"e_1_3_1_15_2","unstructured":"Zhihong Fu Zehua Fu Qingjie Liu Wenrui Cai and Yunhong Wang. 2022. SparseTT: Visual tracking with sparse transformers. arXiv:2205.03776. Retrieved from https:\/\/arxiv.org\/abs\/2205.03776"},{"key":"e_1_3_1_16_2","unstructured":"Shenyuan Gao Chunluan Zhou and Jun Zhang. 2023. Generalized relation modeling for transformer tracking. arXiv:2303.16580. Retrieved from https:\/\/arxiv.org\/abs\/2303.16580"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3726529"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2950508"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2984256"},{"key":"e_1_3_1_20_2","unstructured":"Mingzhe Guo Zhipeng Zhang Heng Fan and Liping Jing. 2022. Divert more attention to vision-language tracking. arXiv:2207.01076. Retrieved from https:\/\/arxiv.org\/abs\/2207.01076"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01801"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.3115\/V1\/D14-1086"},{"key":"e_1_3_1_23_2","first-page":"4282","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201919)","author":"Li Bo","year":"2019","unstructured":"Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, and Junjie Yan. 2019. Siamrpn++: Evolution of siamese visual tracking with very deep networks. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201919), 4282\u20134291."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"e_1_3_1_25_2","first-page":"4927","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW \u201922)","author":"Li Yihao","year":"2022","unstructured":"Yihao Li, Jun Yu, Zhongpeng Cai, and Yuwen Pan. 2022. Cross-modal target retrieval for tracking by natural language. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW \u201922). IEEE, 4927\u20134936."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3520354"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00816"},{"key":"e_1_3_1_30_2","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv:1907.11692. Retrieved from https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_1_32_2","volume-title":"International Conference on Learning Representations (ICLR \u201919)","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In International Conference on Learning Representations (ICLR \u201919). OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475349"},{"key":"e_1_3_1_34_2","first-page":"14012","volume-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV \u201923)","author":"Ma Ding","year":"2023","unstructured":"Ding Ma and Xiangqian Wu. 2023. Tracking by natural language specification with long short-term context decoupling. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV \u201923), 14012\u201314021."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.3115\/V1\/D14-1162"},{"key":"e_1_3_1_36_2","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML \u201921)","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning (ICML \u201921). PMLR, 8748\u20138763. Retrieved from http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_1_37_2","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1109\/CVPR.2019.00075","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201919)","author":"Rezatofighi Hamid","year":"2019","unstructured":"Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian D. Reid, and Silvio Savarese. 2019. Generalized intersection over union: A metric and a loss for bounding box regression. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201919), 658\u2013666."},{"key":"e_1_3_1_38_2","volume-title":"35th Conference on Neural Information Processing Systems (NeurIPS)","author":"Ridnik Tal","year":"2021","unstructured":"Tal Ridnik, Emanuel Ben Baruch, Asaf Noy, and Lihi Zelnik. 2021. ImageNet-21K pretraining for the masses. In 35th Conference on Neural Information Processing Systems (NeurIPS). Retrieved from https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/98f13708210194c475687be6106a3b84-Abstract-round1.html"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3442290"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01817"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3227466"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/J.PATCOG.2024.111128"},{"key":"e_1_3_1_43_2","first-page":"1571","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR \u201921)","author":"Wang Ning","year":"2021","unstructured":"Ning Wang, Wengang Zhou, Jie Wang, and Houqiang Li. 2021. Transformer meets tracker: Exploiting temporal context for robust visual tracking. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR \u201921). IEEE, 1571\u20131580."},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"e_1_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Bin Yan Yi Jiang Jiannan Wu Dong Wang Ping Luo Zehuan Yuan and Huchuan Lu. 2023. Universal instance perception as object discovery and retrieval. arXiv:2303.06674. Retrieved from https:\/\/arxiv.org\/abs\/2303.06674","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00247"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"e_1_3_1_50_2","unstructured":"Botao Ye Hong Chang Bingpeng Ma and Shiguang Shan. 2022. Joint feature learning and relation modeling for tracking: A one-stream framework. arXiv:2203.11991. Retrieved from https:\/\/arxiv.org\/abs\/2203.11991"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3208605"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413959"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232854"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103604"},{"key":"e_1_3_1_55_2","volume-title":"International Conference on Learning Representations (ICLR \u201923)","author":"Zhang Hao","year":"2023","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M. Ni, and Heung-Yeung Shum. 2023. DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection. In International Conference on Learning Representations (ICLR \u201923). OpenReview.net. Retrieved from https:\/\/openreview.net\/pdf?id=3mRwyG5one"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3736581"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651308"},{"key":"e_1_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Li Zhou Zikun Zhou Kaige Mao and Zhenyu He. 2023. Joint visual grounding and tracking with natural language specification. arXiv:2303.12027. Retrieved from https:\/\/arxiv.org\/abs\/2303.12027","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630100"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00856"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00972"},{"key":"e_1_3_1_62_2","volume-title":"International Conference on Learning Representations (ICLR \u201921)","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable DETR: Deformable transformers for end-to-end object detection. In International Conference on Learning Representations (ICLR \u201921). OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:57:19Z","timestamp":1776783439000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":61,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3803863"],"URL":"https:\/\/doi.org\/10.1145\/3803863","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"assertion":[{"value":"2025-10-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}