{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:06:58Z","timestamp":1792789618501,"version":"4.5.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373102"],"award-info":[{"award-number":["62373102"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,4]]},"DOI":"10.1016\/j.neunet.2025.108421","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T07:52:46Z","timestamp":1764661966000},"page":"108421","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":10,"special_numbering":"C","title":["Balanced multi-modality knowledge mining for RGB-infrared object detection"],"prefix":"10.1016","volume":"196","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1954-2240","authenticated-orcid":false,"given":"You","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihan","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingling","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108421_bib0001","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6154","article-title":"Cascade r-cnn: Delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.neunet.2025.108421_bib0002","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition workshops","first-page":"403","article-title":"Multimodal object detection by channel switching and spatial attention","author":"Cao","year":"2023"},{"key":"10.1016\/j.neunet.2025.108421_bib0003","doi-asserted-by":"crossref","unstructured":"Fang, Q., Han, D., & Wang, Z. (2021). Cross-modality fusion transformer for multispectral object detection. arXiv:2111.00273.","DOI":"10.2139\/ssrn.4227745"},{"key":"10.1016\/j.neunet.2025.108421_bib0004","article-title":"Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery","volume":"130","author":"Fang","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108421_bib0006","doi-asserted-by":"crossref","first-page":"13232","DOI":"10.1109\/TNNLS.2023.3266452","article-title":"Lraf-net: Long-range attention fusion network for visible-infrared object detection","volume":"35","author":"Fu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.108421_bib0007","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv:2107.08430."},{"key":"10.1016\/j.neunet.2025.108421_bib0008","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2961","article-title":"Mask r-cnn","author":"He","year":"2017"},{"key":"10.1016\/j.neunet.2025.108421_bib0009","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"1465","article-title":"Multispectral object detection via cross-modal conflict-aware learning","author":"He","year":"2023"},{"key":"10.1016\/j.neunet.2025.108421_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106156","article-title":"Cross-modality interaction for few-shot multispectral object detection with semantic knowledge","volume":"173","author":"Huang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108421_bib0011","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision workshops","first-page":"3489","article-title":"LLVIP: A visible-infrared paired dataset for low-light vision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neunet.2025.108421_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.jag.2024.103918","article-title":"M2FNet: Multi-modal fusion network for object detection from visible and thermal infrared images","volume":"130","author":"Jiang","year":"2024","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"10.1016\/j.neunet.2025.108421_bib0013","series-title":"YOLOv5 by ultralytics","author":"Jocher","year":"2020"},{"key":"10.1016\/j.neunet.2025.108421_bib0014","series-title":"YOLO by ultralytics","author":"Jocher","year":"2023"},{"issue":"3","key":"10.1016\/j.neunet.2025.108421_bib0015","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1109\/TCSVT.2021.3076466","article-title":"Uncertainty-guided cross-modal learning for robust multispectral pedestrian detection","volume":"32","author":"Kim","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.108421_bib0016","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.patrec.2024.02.012","article-title":"CrossFormer: Cross-guided attention for multi-modal object detection","volume":"179","author":"Lee","year":"2024","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2025.108421_bib0020","doi-asserted-by":"crossref","first-page":"3420","DOI":"10.1109\/TMM.2022.3160589","article-title":"Confidence-aware fusion using dempster-shafer theory for multispectral pedestrian detection","volume":"25","author":"Li","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108421_bib0017","doi-asserted-by":"crossref","first-page":"8678","DOI":"10.1109\/TMM.2024.3381377","article-title":"M2FNet: Mask-guided multi-level fusion for RGB-T pedestrian detection","volume":"26","author":"Li","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108421_bib0018","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","article-title":"Illumination-aware faster R-CNN for robust multispectral pedestrian detection","volume":"85","author":"Li","year":"2019","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108421_bib0019","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.inffus.2021.02.023","article-title":"RFN-nest: An end-to-end residual fusion network for infrared and visible images","volume":"73","author":"Li","year":"2021","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.108421_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106890","article-title":"UMS2-ODNet: Unified-scale domain adaptation mechanism driven object detection network with multi-scale attention","volume":"181","author":"Li","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108421_bib0022","series-title":"Proceedings of the European conference on computer vision","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.neunet.2025.108421_bib0023","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5792","article-title":"Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2025.108421_bib0024","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2025.108421_bib0025","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9992","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2025.108421_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107098","article-title":"Identity Model transformation for boosting performance and efficiency in object detection network","volume":"184","author":"Lu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108421_bib0027","first-page":"1","article-title":"Scale decoupled pyramid for object detection in aerial images","volume":"61","author":"Ma","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.108421_bib0028","doi-asserted-by":"crossref","first-page":"4980","DOI":"10.1109\/TIP.2020.2977573","article-title":"DDcGAN: A dual-discriminator conditional generative adversarial network for multi-resolution image fusion","volume":"29","author":"Ma","year":"2020","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.108421_bib0029","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.jvcir.2015.11.002","article-title":"Vehicle detection in aerial imagery: A small target detection benchmark","volume":"34","author":"Razakarivony","year":"2016","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.1016\/j.neunet.2025.108421_bib0030","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016"},{"issue":"6","key":"10.1016\/j.neunet.2025.108421_bib0031","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108421_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109913","article-title":"ICAFusion: Iterative cross-attention guided feature fusion for multispectral object detection","volume":"145","author":"Shen","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108421_bib0033","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.inffus.2022.10.034","article-title":"DIVFusion: Darkness-free infrared and visible image fusion","volume":"91","author":"Tang","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.108421_bib0034","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","article-title":"Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network","volume":"82","author":"Tang","year":"2022","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.108421_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101870","article-title":"Rethinking the necessity of image fusion in high-level vision tasks: A practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity","volume":"99","author":"Tang","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.108421_bib0036","doi-asserted-by":"crossref","first-page":"6449","DOI":"10.1109\/TMM.2024.3350926","article-title":"Cross-modality proposal-guided feature mining for unregistered RGB-thermal pedestrian detection","volume":"26","author":"Tian","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108421_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7464","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2025.108421_bib0038","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108421_bib0039","doi-asserted-by":"crossref","first-page":"9427","DOI":"10.1109\/TITS.2024.3382841","article-title":"Progressive critical region transfer for cross-domain visual object detection","volume":"25","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2025.108421_bib0040","first-page":"1","article-title":"Cross-modal oriented object detection of UAV aerial images based on image feature","volume":"62","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.108421_bib0041","series-title":"Proceedings of the European conference on computer vision","first-page":"1","article-title":"Yolov9: Learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"10.1016\/j.neunet.2025.108421_bib0042","doi-asserted-by":"crossref","first-page":"8933","DOI":"10.1109\/JSTARS.2023.3315544","article-title":"Cross-modal local calibration and global context modeling network for RGB-infrared remote-sensing object detection","volume":"16","author":"Xie","year":"2023","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.108421_bib0043","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1109\/TCSVT.2024.3454631","article-title":"Multidimensional fusion network for multispectral object detection","volume":"35","author":"Yang","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.108421_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102246","article-title":"Improving RGB-infrared object detection with cascade alignment-guided transformer","volume":"105","author":"Yuan","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.108421_bib0045","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1109\/TCSVT.2024.3418965","article-title":"MMI-Det: Exploring multi-modal integration for visible and infrared object detection","volume":"34","author":"Zeng","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.108421_bib0046","first-page":"1","article-title":"Rethinking early-fusion strategies for improved multispectral object detection","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"10.1016\/j.neunet.2025.108421_bib0047","series-title":"Proceedings of the IEEE International conference on image processing","first-page":"276","article-title":"Multispectral fusion for object detection with cyclic fuse-and-refine blocks","author":"Zhang","year":"2020"},{"issue":"9","key":"10.1016\/j.neunet.2025.108421_bib0048","first-page":"5185","article-title":"Moving vehicle detection for remote sensing video surveillance with nonstationary satellite platform","volume":"44","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108421_bib0049","first-page":"1","article-title":"SuperYOLO: Super resolution assisted object detection in multimodal remote sensing imagery","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2025.108421_bib0050","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.inffus.2018.09.015","article-title":"Cross-modality interactive attention network for multispectral pedestrian detection","volume":"50","author":"Zhang","year":"2019","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2025.108421_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5906","article-title":"Cddfuse: Correlation-driven dual-branch feature decomposition for multi-modality image fusion","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2025.108421_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13955","article-title":"Metafusion: Infrared and visible image fusion via meta-feature embedding from object detection","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2025.108421_bib0053","unstructured":"Zhao, T., Yuan, M., Jiang, F., Wang, N., & Wei, X. (2024). Removal and selection: Improving RGB-infrared object detection via coarse-to-fine fusion. arXiv:2401.10731."},{"key":"10.1016\/j.neunet.2025.108421_bib0054","series-title":"Proceedings of the European conference on computer vision","first-page":"787","article-title":"Improving multispectral pedestrian detection by addressing modality imbalance problems","author":"Zhou","year":"2020"},{"key":"10.1016\/j.neunet.2025.108421_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110693","article-title":"CMIGNet: Cross-modal inverse guidance network for RGB-depth salient object detection","volume":"155","author":"Zhu","year":"2024","journal-title":"Pattern Recognition"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025013024?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025013024?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T15:45:54Z","timestamp":1769701554000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025013024"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":54,"alternative-id":["S0893608025013024"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108421","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Balanced multi-modality knowledge mining for RGB-infrared object detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108421","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":"108421"}}