{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T15:14:08Z","timestamp":1786202048247,"version":"3.56.0"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100010097","name":"China Association for Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010097","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62266049"],"award-info":[{"award-number":["62266049"]}],"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":["62576303"],"award-info":[{"award-number":["62576303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132081","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:14:22Z","timestamp":1773828862000},"page":"132081","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["CoReTrack: Consensus-residual fusion for reliability-aware RGBT tracking"],"prefix":"10.1016","volume":"319","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4840-4696","authenticated-orcid":false,"given":"Yujia","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-1687","authenticated-orcid":false,"given":"Haiyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0763-9179","authenticated-orcid":false,"given":"Ruxun","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1258-9637","authenticated-orcid":false,"given":"Shuran","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7069-2143","authenticated-orcid":false,"given":"Xinfeng","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5755-5143","authenticated-orcid":false,"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-1671","authenticated-orcid":false,"given":"Pengfei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3150-7029","authenticated-orcid":false,"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132081_bib0001","series-title":"European conference on computer vision","first-page":"644","article-title":"Fear: Fast, efficient, accurate and robust visual tracker","author":"Borsuk","year":"2022"},{"key":"10.1016\/j.eswa.2026.132081_bib0002","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"927","article-title":"Bi-directional adapter for multimodal tracking","author":"Cao","year":"2024"},{"key":"10.1016\/j.eswa.2026.132081_bib0003","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"1573","article-title":"Simplifying cross-modal interaction via modality-shared features for RGBT tracking","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.132081_bib0004","doi-asserted-by":"crossref","first-page":"12388","DOI":"10.1109\/TCSVT.2024.3435722","article-title":"Top-down cross-modal guidance for robust RGB-T tracking","volume":"34","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology."},{"key":"10.1016\/j.eswa.2026.132081_bib0005","series-title":"Proceedings of the 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.eswa.2026.132081_bib0006","series-title":"Proceedings of the thirty-fourth international joint conference on artificial intelligence, IJCAI-25","first-page":"909","article-title":"Template-based uncertainty multimodal fusion network for RGBT tracking","author":"Ding","year":"2025"},{"key":"10.1016\/j.eswa.2026.132081_bib0007","unstructured":"Dosovitskiy, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929."},{"key":"10.1016\/j.eswa.2026.132081_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126031","article-title":"Your data is not perfect: Towards cross-domain out-of-distribution detection in class-imbalanced data","volume":"267","author":"Fang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0009","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1109\/TAI.2021.3116546","article-title":"Animc: A soft approach for autoweighted noisy and incomplete multiview clustering","volume":"3","author":"Fang","year":"2021","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132081_bib0010","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1109\/TETCI.2021.3077909","article-title":"Unbalanced incomplete multi-view clustering via the scheme of view evolution: Weak views are meat; strong views do eat","volume":"6","author":"Fang","year":"2021","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"10.1016\/j.eswa.2026.132081_bib0011","doi-asserted-by":"crossref","unstructured":"Fang, X., Hu, Y., Zhou, P., & Wu, D. O. (2021c). VH: View variation and view heredity for incomplete multiview clustering. IEEE Transactions on Artificial Intelligence, 1, 233\u2013247.","DOI":"10.1109\/TAI.2021.3052425"},{"key":"10.1016\/j.eswa.2026.132081_bib0012","doi-asserted-by":"crossref","unstructured":"Fang, X., Liu, D., Zhou, P., & Hu, Y. (2022). Multi-modal cross-domain alignment network for video moment retrieval. IEEE Transactions on Multimedia, 25, 7517\u20137532.","DOI":"10.1109\/TMM.2022.3222965"},{"key":"10.1016\/j.eswa.2026.132081_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2448","article-title":"You can ground earlier than see: An effective and efficient pipeline for temporal sentence grounding in compressed videos","author":"Fang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132081_bib0014","doi-asserted-by":"crossref","first-page":"3263","DOI":"10.1109\/TMM.2023.3309551","article-title":"Hierarchical local-global transformer for temporal sentence grounding","volume":"26","author":"Fang","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132081_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102492","article-title":"Rgbt tracking: A comprehensive review","volume":"110","author":"Feng","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132081_bib0016","doi-asserted-by":"crossref","first-page":"24819","DOI":"10.1109\/JIOT.2025.3557564","article-title":"TVTracker: Target-adaptive text-guided visual fusion for multi-modal RGB-T tracking","volume":"12","author":"Gao","year":"2025","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.eswa.2026.132081_bib0017","article-title":"Ramr: A role-adaptive modality recalibration network for RGBT tracking","author":"Gao","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119890","article-title":"A joint local\u2013global search mechanism for long-term tracking with dynamic memory network","volume":"223","author":"Gao","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0019","doi-asserted-by":"crossref","first-page":"7176","DOI":"10.1109\/TCSVT.2024.3370981","article-title":"Target-aware tracking with spatial-temporal context attention","volume":"34","author":"He","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.132081_bib0020","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv: 1503.02531."},{"key":"10.1016\/j.eswa.2026.132081_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19079","article-title":"Onetracker: Unifying visual object tracking with foundation models and efficient tuning","author":"Hong","year":"2024"},{"key":"10.1016\/j.eswa.2026.132081_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26551","article-title":"SDSTrack: Self-distillation symmetric adapter learning for multi-modal visual object tracking","author":"Hou","year":"2024"},{"key":"10.1016\/j.eswa.2026.132081_bib0023","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13630","article-title":"Bridging search region interaction with template for RGB-T tracking","author":"Hui","year":"2023"},{"key":"10.1016\/j.eswa.2026.132081_bib0024","doi-asserted-by":"crossref","first-page":"5743","DOI":"10.1109\/TIP.2016.2614135","article-title":"Learning collaborative sparse representation for grayscale-thermal tracking","volume":"25","author":"Li","year":"2016","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132081_bib0025","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 Recognition"},{"key":"10.1016\/j.eswa.2026.132081_bib0026","series-title":"European conference on computer vision","first-page":"222","article-title":"Challenge-aware RGBT tracking","author":"Li","year":"2020"},{"key":"10.1016\/j.eswa.2026.132081_bib0027","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 Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132081_bib0028","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"808","article-title":"Cross-modal ranking with soft consistency and noisy labels for robust RGB-T tracking","author":"Li","year":"2018"},{"key":"10.1016\/j.eswa.2026.132081_bib0029","unstructured":"Li, H., Wang, Y., Hu, X., Hao, W., Zhang, P., Wang, D., & Lu, H. (2025a). Cadtrack: Learning contextual aggregation with deformable alignment for robust RGBT tracking. arXiv preprint arXiv: 2511.17967."},{"key":"10.1016\/j.eswa.2026.132081_bib0030","doi-asserted-by":"crossref","first-page":"28891","DOI":"10.1109\/JSEN.2025.3579339","article-title":"Transformer-based RGB-T tracking with channel and spatial feature fusion","volume":"25","author":"Li","year":"2025","journal-title":"IEEE Sensors Journal"},{"key":"10.1016\/j.eswa.2026.132081_bib0031","article-title":"RGBT tracking via supervised mutual guiding","author":"Liu","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132081_bib0032","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"3129","article-title":"Quality-aware rgbt tracking via supervised reliability learning and weighted residual guidance","author":"Liu","year":"2023"},{"key":"10.1016\/j.eswa.2026.132081_bib0033","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1109\/TMM.2025.3623526","article-title":"Scale-aware attention and multi-modal prompt learning with fusion adapter for RGBT tracking","volume":"28","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132081_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.112983","article-title":"Two-stage unidirectional fusion network for RGBT tracking","volume":"310","author":"Liu","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132081_bib0035","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv: 1711.05101."},{"key":"10.1016\/j.eswa.2026.132081_bib0036","doi-asserted-by":"crossref","first-page":"5613","DOI":"10.1109\/TIP.2021.3087341","article-title":"RGBT tracking via multi-adapter network with hierarchical divergence loss","volume":"30","author":"Lu","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132081_bib0037","doi-asserted-by":"crossref","first-page":"4118","DOI":"10.1109\/TNNLS.2022.3157594","article-title":"Duality-gated mutual condition network for RGBT tracking","volume":"36","author":"Lu","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132081_bib0038","doi-asserted-by":"crossref","first-page":"4386","DOI":"10.1109\/TIP.2025.3586467","article-title":"After: Attention-based fusion router for RGBT tracking","volume":"34","author":"Lu","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132081_bib0039","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"9291","article-title":"Breaking modality gap in RGBT tracking: Coupled knowledge distillation","author":"Lu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132081_bib0040","doi-asserted-by":"crossref","first-page":"6609","DOI":"10.3390\/s23146609","article-title":"Learning modality complementary features with mixed attention mechanism for RGB-T tracking","volume":"23","author":"Luo","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.eswa.2026.132081_bib0041","unstructured":"Luo, Y., Guo, X., & Li, H. (2024). From two-stream to one-stream: Efficient RGB-T tracking via mutual prompt learning and knowledge distillation. arXiv preprint arXiv: 2403.16834."},{"key":"10.1016\/j.eswa.2026.132081_bib0042","article-title":"OTKD: A general knowledge distillation pipeline for object tracking","author":"Pan","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0043","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132081_bib0044","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","article-title":"Fine-tuning cnn image retrieval with no human annotation","volume":"41","author":"Radenovi\u0107","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132081_bib0045","doi-asserted-by":"crossref","first-page":"12059","DOI":"10.1109\/TCSVT.2024.3425455","article-title":"Transformer RGBT tracking with spatio-temporal multimodal tokens","volume":"34","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.132081_bib0046","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5189","article-title":"Generative-based fusion mechanism for multi-modal tracking","author":"Tang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132081_bib0047","doi-asserted-by":"crossref","first-page":"7235","DOI":"10.1109\/TIP.2025.3611687","article-title":"Revisiting rgbt tracking benchmarks from the perspective of modality validity: A new benchmark, problem, and solution","volume":"34","author":"Tang","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132081_bib0048","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5436","article-title":"Temporal adaptive RGBT tracking with modality prompt","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132081_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119865","article-title":"RGBT tracking using randomly projected cnn features","volume":"223","author":"Wang","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0050","unstructured":"Xia, J., Shi, D., Song, K., Song, L., Wang, X., Jin, S., Zhou, L., Cheng, Y., Jin, L., & Zhu, Z., et al. (2023). Unified single-stage transformer network for efficient RGB-T tracking. arXiv preprint arXiv: 2308.13764."},{"key":"10.1016\/j.eswa.2026.132081_bib0051","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2831","article-title":"Attribute-based progressive fusion network for RGBT tracking","author":"Xiao","year":"2022"},{"key":"10.1016\/j.eswa.2026.132081_bib0052","doi-asserted-by":"crossref","first-page":"1783","DOI":"10.1109\/TMM.2024.3521798","article-title":"Frequency-assisted mamba for remote sensing image super-resolution","volume":"27","author":"Xiao","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132081_bib0053","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1109\/TIP.2023.3349004","article-title":"TTST: A top-k token selective transformer for remote sensing image super-resolution","volume":"33","author":"Xiao","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132081_bib0054","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8682","article-title":"Cross-modulated attention transformer for RGBT tracking","author":"Xiao","year":"2025"},{"key":"10.1016\/j.eswa.2026.132081_bib0055","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/TCSVT.2025.3601598","article-title":"FMTrack: frequency-aware interaction and multi-expert fusion for RGB-T tracking","volume":"36","author":"Xue","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.132081_bib0056","article-title":"Tiptrack: Time-series information prompt network for RGBT tracking","author":"Yan","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0057","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"3492","article-title":"Prompting for multi-modal tracking","author":"Yang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132081_bib0058","first-page":"1","article-title":"Dual-modality space-time memory network for RGBT tracking","volume":"72","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2026.132081_bib0059","first-page":"1","article-title":"A comprehensive review of RGBT tracking","volume":"73","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.eswa.2026.132081_bib0060","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8886","article-title":"Visible-thermal UAV tracking: A large-scale benchmark and new baseline","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132081_bib0061","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5404","article-title":"Efficient RGB-T tracking via cross-modality distillation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132081_bib0062","doi-asserted-by":"crossref","first-page":"7386","DOI":"10.1109\/TCSVT.2024.3377471","article-title":"AMNet: Learning to align multi-modality for RGB-T tracking","volume":"34","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.132081_bib0063","article-title":"FDBPL: Faster distillation-based prompt learning for region-aware vision-language models adaptation","author":"Zhang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0064","first-page":"1","article-title":"Robust RGB-T tracking via adaptive modality weight correlation filters and cross-modality learning","volume":"20","author":"Zhou","year":"2023","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.eswa.2026.132081_bib0065","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9516","article-title":"Visual prompt multi-modal tracking","author":"Zhu","year":"2023"},{"key":"10.1016\/j.eswa.2026.132081_bib0066","series-title":"Proceedings of the 27th ACM international conference on multimedia","first-page":"465","article-title":"Dense feature aggregation and pruning for RGBT tracking","author":"Zhu","year":"2019"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426009942?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426009942?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T02:36:23Z","timestamp":1780972583000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426009942"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":66,"alternative-id":["S0957417426009942"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132081","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CoReTrack: Consensus-residual fusion for reliability-aware RGBT tracking","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132081","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":"132081"}}