{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T02:56:39Z","timestamp":1794538599934,"version":"4.9.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004832","name":"Changsha University of Science\u00a0and\u00a0Technology","doi-asserted-by":"publisher","award":["CLSJCX24059"],"award-info":[{"award-number":["CLSJCX24059"]}],"id":[{"id":"10.13039\/501100004832","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jinhua Public Welfare Technology Application Research Project","award":["2022-4-060"],"award-info":[{"award-number":["2022-4-060"]}]},{"name":"the Key Project of Natural Science Foundation of Hunan Province"},{"name":"the Practical Innovation and Entrepreneurship Ability Improvement Plan for Professional Degree Postgraduate of Changsha University of Science and Technology"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972056"],"award-info":[{"award-number":["61972056"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2025JJ50379"],"award-info":[{"award-number":["2025JJ50379"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2024JJ3017"],"award-info":[{"award-number":["2024JJ3017"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1016\/j.neunet.2025.107707","type":"journal-article","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T10:53:49Z","timestamp":1749898429000},"page":"107707","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":43,"special_numbering":"C","title":["MGNet: RGBT tracking via cross-modality cross-region mutual guidance"],"prefix":"10.1016","volume":"190","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4278-0805","authenticated-orcid":false,"given":"Jianming","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2659-8247","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1706-3433","authenticated-orcid":false,"given":"Yu","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5645-160X","authenticated-orcid":false,"given":"Zhu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-8738","authenticated-orcid":false,"given":"Jin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107707_b1","doi-asserted-by":"crossref","unstructured":"Cao, B., Guo, J., Zhu, P., & Hu, Q. (2024). Bi-directional adapter for multimodal tracking. vol. 38, In Proceedings of the AAAI conference on artificial intelligence (pp. 927\u2013935).","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"10.1016\/j.neunet.2025.107707_b2","series-title":"2022 18th IEEE international conference on advanced video and signal based surveillance","first-page":"1","article-title":"Fusion tree network for RGBT tracking","author":"Cheng","year":"2022"},{"key":"10.1016\/j.neunet.2025.107707_b3","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., & Wu, G. (2022). Mixformer: End-to-end tracking with iterative mixed attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13608\u201313618).","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"10.1016\/j.neunet.2025.107707_b4","doi-asserted-by":"crossref","DOI":"10.1109\/TIP.2024.3393298","article-title":"QueryTrack: Joint-modality query fusion network for RGBT tracking","author":"Fan","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.107707_b5","article-title":"Learning multi-layer attention aggregation siamese network for robust RGBT tracking","author":"Feng","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107707_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107273","article-title":"Sparse mixed attention aggregation network for multimodal images fusion tracking","volume":"127","author":"Feng","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2025.107707_b7","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.neunet.2025.107707_b8","doi-asserted-by":"crossref","unstructured":"Hong, L., Yan, S., Zhang, R., Li, W., Zhou, X., Guo, P., et al. (2024). Onetracker: Unifying visual object tracking with foundation models and efficient tuning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19079\u201319091).","DOI":"10.1109\/CVPR52733.2024.01805"},{"key":"10.1016\/j.neunet.2025.107707_b9","series-title":"2022 IEEE international conference on multimedia and expo","first-page":"1","article-title":"Mirnet: A robust rgbt tracking jointly with multi-modal interaction and refinement","author":"Hou","year":"2022"},{"key":"10.1016\/j.neunet.2025.107707_b10","doi-asserted-by":"crossref","unstructured":"Hou, X., Xing, J., Qian, Y., Guo, Y., Xin, S., Chen, J., et al. (2024). Sdstrack: Self-distillation symmetric adapter learning for multi-modal visual object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 26551\u201326561).","DOI":"10.1109\/CVPR52733.2024.02507"},{"key":"10.1016\/j.neunet.2025.107707_b11","doi-asserted-by":"crossref","unstructured":"Hui, T., Xun, Z., Peng, F., Huang, J., Wei, X., Wei, X., et al. (2023). Bridging search region interaction with template for rgb-t tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13630\u201313639).","DOI":"10.1109\/CVPR52729.2023.01310"},{"issue":"12","key":"10.1016\/j.neunet.2025.107707_b12","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.neunet.2025.107707_b13","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.neunet.2025.107707_b14","series-title":"European conference on computer vision","first-page":"222","article-title":"Challenge-aware RGBT tracking","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2025.107707_b15","series-title":"Transformer-based RGB-T tracking with channel and spatial feature fusion","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2025.107707_b16","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.neunet.2025.107707_b17","article-title":"Rgbt tracking via challenge-based appearance disentanglement and interaction","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.107707_b18","doi-asserted-by":"crossref","unstructured":"Long Li, C., Lu, A., Hua Zheng, A., Tu, Z., & Tang, J. (2019). Multi-adapter RGBT tracking. In Proceedings of the IEEE\/CVF international conference on computer vision workshops.","DOI":"10.1109\/ICCVW.2019.00279"},{"key":"10.1016\/j.neunet.2025.107707_b19","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.neunet.2025.107707_b20","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.neunet.2025.107707_b21","article-title":"Duality-gated mutual condition network for RGBT tracking","author":"Lu","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.107707_b22","series-title":"AFter: Attention-based fusion router for RGBT tracking","author":"Lu","year":"2024"},{"issue":"7","key":"10.1016\/j.neunet.2025.107707_b23","doi-asserted-by":"crossref","first-page":"7301","DOI":"10.1109\/JSEN.2023.3244834","article-title":"Differential reinforcement and global collaboration network for RGBT tracking","volume":"23","author":"Mei","year":"2023","journal-title":"IEEE Sensors Journal"},{"issue":"4","key":"10.1016\/j.neunet.2025.107707_b24","doi-asserted-by":"crossref","first-page":"3822","DOI":"10.1109\/TITS.2022.3229830","article-title":"Dynamic fusion network for RGBT tracking","volume":"24","author":"Peng","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2025.107707_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106493","article-title":"Reliable object tracking by multimodal hybrid feature extraction and transformer-based fusion","volume":"178","author":"Sun","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107707_b26","series-title":"Transformer RGBT tracking with Spatio-Temporal multimodal tokens","author":"Sun","year":"2024"},{"key":"10.1016\/j.neunet.2025.107707_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106110","article-title":"EMAT: Efficient feature fusion network for visual tracking via optimized multi-head attention","volume":"172","author":"Wang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107707_b28","doi-asserted-by":"crossref","first-page":"4335","DOI":"10.1109\/TMM.2022.3174341","article-title":"MFGNet: Dynamic modality-aware filter generation for RGB-T tracking","volume":"25","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107707_b29","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zheng, J., Ren, X., Vasluianu, F.-A., Ma, C., Paudel, D. P., et al. (2024). Single-model and any-modality for video object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 19156\u201319166).","DOI":"10.1109\/CVPR52733.2024.01812"},{"key":"10.1016\/j.neunet.2025.107707_b30","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Yang, M., Li, C., Liu, L., & Tang, J. (2022). Attribute-based progressive fusion network for rgbt tracking. vol. 36, In Proceedings of the AAAI conference on artificial intelligence (pp. 2831\u20132838).","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"10.1016\/j.neunet.2025.107707_b31","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, Z., Zheng, F., Leonardis, A., & Song, J. (2022). Prompting for multi-modal tracking. In Proceedings of the 30th ACM international conference on multimedia (pp. 3492\u20133500).","DOI":"10.1145\/3503161.3547851"},{"key":"10.1016\/j.neunet.2025.107707_b32","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.neunet.2025.107707_b33","doi-asserted-by":"crossref","unstructured":"Zhang, L., Danelljan, M., Gonzalez-Garcia, A., Van De Weijer, J., & Shahbaz Khan, F. (2019). Multi-modal fusion for end-to-end RGB-T tracking. In Proceedings of the IEEE\/CVF international conference on computer vision workshops.","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"10.1016\/j.neunet.2025.107707_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.108485","article-title":"SCSTCF: spatial-channel selection and temporal regularized correlation filters for visual tracking","volume":"118","author":"Zhang","year":"2022","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.neunet.2025.107707_b35","doi-asserted-by":"crossref","unstructured":"Zhang, T., Guo, H., Jiao, Q., Zhang, Q., & Han, J. (2023). Efficient rgb-t tracking via cross-modality distillation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5404\u20135413).","DOI":"10.1109\/CVPR52729.2023.00523"},{"issue":"3","key":"10.1016\/j.neunet.2025.107707_b36","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1109\/TCSVT.2021.3072207","article-title":"SiamCDA: Complementarity-and distractor-aware RGB-T tracking based on siamese network","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"2","key":"10.1016\/j.neunet.2025.107707_b37","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1109\/TETCI.2024.3349464","article-title":"A robust real-time Anchor-Free traffic sign detector with One-Level feature","volume":"8","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"issue":"2","key":"10.1016\/j.neunet.2025.107707_b38","doi-asserted-by":"crossref","first-page":"1900","DOI":"10.1109\/TITS.2024.3512551","article-title":"SiamTFA: Siamese triple-stream feature aggregation network for efficient RGBT tracking","volume":"26","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2025.107707_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2022.107730","article-title":"An object tracking framework with recapture based on correlation filters and siamese networks","volume":"98","author":"Zhang","year":"2022","journal-title":"Computers & Electrical Engineering"},{"key":"10.1016\/j.neunet.2025.107707_b40","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1007\/s11263-021-01495-3","article-title":"Learning adaptive attribute-driven representation for real-time RGB-T tracking","volume":"129","author":"Zhang","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2025.107707_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128908","article-title":"RGBT tracking via frequency-aware feature enhancement and unidirectional mixed attention","volume":"616","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"issue":"2","key":"10.1016\/j.neunet.2025.107707_b42","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.neunet.2025.107707_b43","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 Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.107707_b44","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., & Lu, H. (2023). Visual prompt multi-modal tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9516\u20139526).","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"10.1016\/j.neunet.2025.107707_b45","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Li, C., Luo, B., Tang, J., & Wang, X. (2019). Dense feature aggregation and pruning for RGBT tracking. In Proceedings of the 27th ACM international conference on multimedia (pp. 465\u2013472).","DOI":"10.1145\/3343031.3350928"},{"issue":"1","key":"10.1016\/j.neunet.2025.107707_b46","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 Transactions on Intelligent Vehicles"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025005878?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025005878?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:17:36Z","timestamp":1778545056000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025005878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":46,"alternative-id":["S0893608025005878"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107707","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MGNet: RGBT tracking via cross-modality cross-region mutual guidance","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107707","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107707"}}