{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T21:12:12Z","timestamp":1772917932938,"version":"3.50.1"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005320","name":"Xidian University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005320","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1016\/j.inffus.2024.102531","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:24:50Z","timestamp":1718904290000},"page":"102531","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":16,"special_numbering":"C","title":["Multi-modal visual tracking based on textual generation"],"prefix":"10.1016","volume":"112","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-0375-9253","authenticated-orcid":false,"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2024.102531_b1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"vol. 33","author":"Brown","year":"2020"},{"issue":"1","key":"10.1016\/j.inffus.2024.102531_b2","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2024.102531_b3","series-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"10.1016\/j.inffus.2024.102531_b4","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.inffus.2024.102531_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.inffus.2024.102531_b6","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.inffus.2024.102531_b7","doi-asserted-by":"crossref","unstructured":"Y. Li, J. Yu, Z. Cai, Y. 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.","DOI":"10.1109\/CVPRW56347.2022.00540"},{"key":"10.1016\/j.inffus.2024.102531_b8","article-title":"Language-aware spatial-temporal collaboration for referring video segmentation","author":"Hui","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2024.102531_b9","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.inffus.2024.102531_b10","doi-asserted-by":"crossref","unstructured":"C. Li, N. Zhao, Y. Lu, C. Zhu, J. Tang, Weighted sparse representation regularized graph learning for RGB-T object tracking, in: Proceedings of the 25th ACM International Conference on Multimedia, 2017, pp. 1856\u20131864.","DOI":"10.1145\/3123266.3123289"},{"key":"10.1016\/j.inffus.2024.102531_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.106977","article-title":"RGB-T object tracking: Benchmark and baseline","volume":"96","author":"Li","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.inffus.2024.102531_b12","series-title":"2015 12th International Conference on Fuzzy Systems and Knowledge Discovery","first-page":"930","article-title":"Robust object tracking using color and depth images with a depth based occlusion handling and recovery","author":"Ding","year":"2015"},{"key":"10.1016\/j.inffus.2024.102531_b13","series-title":"2018 24th International Conference on Pattern Recognition","first-page":"2112","article-title":"Depth masked discriminative correlation filter","author":"Kart","year":"2018"},{"issue":"20","key":"10.1016\/j.inffus.2024.102531_b14","doi-asserted-by":"crossref","first-page":"9522","DOI":"10.1109\/JSEN.2019.2925821","article-title":"Target-aware correlation filter tracking in RGBD videos","volume":"19","author":"Kuai","year":"2019","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.inffus.2024.102531_b15","doi-asserted-by":"crossref","first-page":"67761","DOI":"10.1109\/ACCESS.2019.2916895","article-title":"Online non-negative multi-modality feature template learning for RGB-assisted infrared tracking","volume":"7","author":"Lan","year":"2019","journal-title":"IEEE Access"},{"issue":"6","key":"10.1016\/j.inffus.2024.102531_b16","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","article-title":"Deep multimodal learning: A survey on recent advances and trends","volume":"34","author":"Ramachandram","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"issue":"2","key":"10.1016\/j.inffus.2024.102531_b17","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s41095-023-0345-5","article-title":"Multi-modal visual tracking: Review and experimental comparison","volume":"10","author":"Zhang","year":"2024","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.inffus.2024.102531_b18","doi-asserted-by":"crossref","unstructured":"P. Zhang, J. Zhao, D. Wang, H. Lu, X. Ruan, Visible-thermal UAV tracking: A large-scale benchmark and new baseline, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8886\u20138895.","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"10.1016\/j.inffus.2024.102531_b19","doi-asserted-by":"crossref","unstructured":"L. Zhang, M. Danelljan, A. Gonzalez-Garcia, J. Van De Weijer, F. Shahbaz Khan, Multi-modal fusion for end-to-end RGB-T tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019.","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"10.1016\/j.inffus.2024.102531_b20","first-page":"2831","article-title":"Attribute-based progressive fusion network for rgbt tracking","volume":"vol. 36","author":"Xiao","year":"2022"},{"key":"10.1016\/j.inffus.2024.102531_b21","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.neucom.2017.11.068","article-title":"Fusing two-stream convolutional neural networks for RGB-T object tracking","volume":"281","author":"Li","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.inffus.2024.102531_b22","doi-asserted-by":"crossref","unstructured":"J. Yang, Z. Li, F. Zheng, A. Leonardis, J. Song, Prompting for multi-modal tracking, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 3492\u20133500.","DOI":"10.1145\/3503161.3547851"},{"key":"10.1016\/j.inffus.2024.102531_b23","doi-asserted-by":"crossref","unstructured":"J. Zhu, S. Lai, X. Chen, D. Wang, H. Lu, Visual prompt multi-modal tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9516\u20139526.","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"10.1016\/j.inffus.2024.102531_b24","series-title":"Beyond visual cues: Synchronously exploring target-centric semantics for vision-language tracking","author":"Ge","year":"2023"},{"key":"10.1016\/j.inffus.2024.102531_b25","series-title":"A survey of vision-language pre-trained models","author":"Du","year":"2022"},{"key":"10.1016\/j.inffus.2024.102531_b26","series-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"10.1016\/j.inffus.2024.102531_b27","doi-asserted-by":"crossref","unstructured":"D. Li, J. Li, H. Li, J.C. Niebles, S.C. Hoi, Align and prompt: Video-and-language pre-training with entity prompts, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4953\u20134963.","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"10.1016\/j.inffus.2024.102531_b28","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume":"34","author":"Xue","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2024.102531_b29","series-title":"A survey on deep learning technique for video segmentation","author":"Wang","year":"2021"},{"key":"10.1016\/j.inffus.2024.102531_b30","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.inffus.2024.102531_b31","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2024.102531_b32","series-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2024.102531_b33","series-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022"},{"key":"10.1016\/j.inffus.2024.102531_b34","series-title":"European Conference on Computer Vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.inffus.2024.102531_b35","series-title":"Prompt vision transformer for domain generalization","author":"Zheng","year":"2022"},{"key":"10.1016\/j.inffus.2024.102531_b36","doi-asserted-by":"crossref","unstructured":"Y. Lu, J. Liu, Y. Zhang, Y. Liu, X. Tian, Prompt distribution learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5206\u20135215.","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"10.1016\/j.inffus.2024.102531_b37","doi-asserted-by":"crossref","unstructured":"Z. Du, Y. Qian, X. Liu, M. Ding, J. Qiu, Z. Yang, J. Tang, GLM: General Language Model Pretraining with Autoregressive Blank Infilling, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 320\u2013335.","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"10.1016\/j.inffus.2024.102531_b38","series-title":"European Conference on Computer Vision","first-page":"105","article-title":"Prompting visual-language models for efficient video understanding","author":"Ju","year":"2022"},{"key":"10.1016\/j.inffus.2024.102531_b39","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.inffus.2024.102531_b40","doi-asserted-by":"crossref","unstructured":"S. Yan, J. Yang, J. K\u00e4pyl\u00e4, F. Zheng, A. Leonardis, J.-K. K\u00e4m\u00e4r\u00e4inen, Depthtrack: Unveiling the power of rgbd tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10725\u201310733.","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"10.1016\/j.inffus.2024.102531_b41","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/TIP.2021.3130533","article-title":"LasHeR: A large-scale high-diversity benchmark for RGBT tracking","volume":"31","author":"Li","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2024.102531_b42","series-title":"Visevent: Reliable object tracking via collaboration of frame and event flows","author":"Wang","year":"2021"},{"key":"10.1016\/j.inffus.2024.102531_b43","doi-asserted-by":"crossref","unstructured":"C.-Y. Wang, A. Bochkovskiy, H.-Y.M. Liao, YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7464\u20137475.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"10.1016\/j.inffus.2024.102531_b44","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.inffus.2024.102531_b45","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.inffus.2024.102531_b46","series-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot","year":"2010"},{"key":"10.1016\/j.inffus.2024.102531_b47","doi-asserted-by":"crossref","unstructured":"H. Nam, B. Han, Learning multi-domain convolutional neural networks for visual tracking, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4293\u20134302.","DOI":"10.1109\/CVPR.2016.465"},{"issue":"3","key":"10.1016\/j.inffus.2024.102531_b48","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TMM.2018.2863604","article-title":"Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in RGB-D videos","volume":"21","author":"Liu","year":"2018","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2024.102531_b49","unstructured":"M. Kristan, J. Matas, A. Leonardis, M. Felsberg, R. Pflugfelder, J.-K. Kamarainen, L. \u030cCehovin Zajc, O. Drbohlav, A. Lukezic, A. Berg, et al., The seventh visual object tracking VOT2019 challenge results, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019."},{"key":"10.1016\/j.inffus.2024.102531_b50","series-title":"2020 25th International Conference on Pattern Recognition","first-page":"7825","article-title":"DAL: A deep depth-aware long-term tracker","author":"Qian","year":"2021"},{"key":"10.1016\/j.inffus.2024.102531_b51","series-title":"Computer Vision\u2013ECCV 2020 Workshops: Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16","first-page":"547","article-title":"The eighth visual object tracking VOT2020 challenge results","author":"Kristan","year":"2020"},{"key":"10.1016\/j.inffus.2024.102531_b52","doi-asserted-by":"crossref","unstructured":"M. Danelljan, G. Bhat, F.S. Khan, M. Felsberg, Atom: Accurate tracking by overlap maximization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4660\u20134669.","DOI":"10.1109\/CVPR.2019.00479"},{"key":"10.1016\/j.inffus.2024.102531_b53","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXI 16","first-page":"771","article-title":"Ocean: Object-aware anchor-free tracking","author":"Zhang","year":"2020"},{"key":"10.1016\/j.inffus.2024.102531_b54","first-page":"3870","article-title":"RGBD1K: A large-scale dataset and benchmark for RGB-D object tracking","volume":"vol. 37","author":"Zhu","year":"2023"},{"key":"10.1016\/j.inffus.2024.102531_b55","doi-asserted-by":"crossref","unstructured":"C. Wang, C. Xu, Z. Cui, L. Zhou, T. Zhang, X. Zhang, J. Yang, Cross-modal pattern-propagation for RGB-T tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 7064\u20137073.","DOI":"10.1109\/CVPR42600.2020.00709"},{"key":"10.1016\/j.inffus.2024.102531_b56","doi-asserted-by":"crossref","unstructured":"Y. Gao, C. Li, Y. Zhu, J. Tang, T. He, F. Wang, Deep adaptive fusion network for high performance RGBT tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019.","DOI":"10.1109\/ICCVW.2019.00017"},{"issue":"1","key":"10.1016\/j.inffus.2024.102531_b57","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/TIV.2020.2980735","article-title":"Quality-aware feature aggregation network for robust RGBT tracking","volume":"6","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"2","key":"10.1016\/j.inffus.2024.102531_b58","doi-asserted-by":"crossref","first-page":"393","DOI":"10.3390\/s20020393","article-title":"Object tracking in RGB-T videos using modal-aware attention network and competitive learning","volume":"20","author":"Zhang","year":"2020","journal-title":"Sensors"},{"key":"10.1016\/j.inffus.2024.102531_b59","series-title":"European Conference on Computer Vision","first-page":"222","article-title":"Challenge-aware RGBT tracking","author":"Li","year":"2020"},{"key":"10.1016\/j.inffus.2024.102531_b60","doi-asserted-by":"crossref","first-page":"3335","DOI":"10.1109\/TIP.2021.3060862","article-title":"Jointly modeling motion and appearance cues for robust RGB-T tracking","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2024.102531_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101881","article-title":"Exploring fusion strategies for accurate RGBT visual object tracking","author":"Tang","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2024.102531_b62","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101816","article-title":"Multi-modal multi-task feature fusion for RGBT tracking","volume":"97","author":"Cai","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2024.102531_b63","doi-asserted-by":"crossref","unstructured":"C. Li, C. Zhu, Y. Huang, J. Tang, L. Wang, Cross-modal ranking with soft consistency and noisy labels for robust RGB-T tracking, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 808\u2013823.","DOI":"10.1007\/978-3-030-01261-8_49"},{"key":"10.1016\/j.inffus.2024.102531_b64","unstructured":"C. Long Li, A. Lu, A. Hua Zheng, Z. Tu, J. Tang, Multi-adapter RGBT tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 2019."},{"key":"10.1016\/j.inffus.2024.102531_b65","article-title":"Online learning samples and adaptive recovery for robust RGB-T tracking","author":"Liu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2024.102531_b66","first-page":"1","article-title":"Learning multi-layer attention aggregation siamese network for robust RGBT tracking","author":"Feng","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2024.102531_b67","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.inffus.2024.102531_b68","series-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"10.1016\/j.inffus.2024.102531_b69","series-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.inffus.2024.102531_b70","series-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023"},{"key":"10.1016\/j.inffus.2024.102531_b71","series-title":"Minigpt-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.inffus.2024.102531_b72","series-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S1566253524003099?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S1566253524003099?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T13:58:06Z","timestamp":1728309486000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253524003099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":72,"alternative-id":["S1566253524003099"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.inffus.2024.102531","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-modal visual tracking based on textual generation","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.inffus.2024.102531","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 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":"102531"}}