{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:27:43Z","timestamp":1793608063839,"version":"4.5.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012659","name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301093"],"award-info":[{"award-number":["62301093"]}],"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":["62301092"],"award-info":[{"award-number":["62301092"]}],"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":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109707","type":"journal-article","created":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T17:19:02Z","timestamp":1791652742000},"page":"109707","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Adjusting modal contributions via differential-driven SoftMax fusion for RGB-IR object detection"],"prefix":"10.1016","volume":"206","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4800-1552","authenticated-orcid":false,"given":"Hang","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boya","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanli","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xichuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5782-4543","authenticated-orcid":false,"given":"Haijun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109707_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.inffus.2022.06.008","article-title":"Locality guided cross-modal feature aggregation and pixel-level fusion for multispectral pedestrian detection","volume":"88","author":"Cao","year":"2022","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109707_bib0002","series-title":"European conference on computer vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neunet.2026.109707_bib0003","doi-asserted-by":"crossref","first-page":"16664","DOI":"10.52202\/068431-1212","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109707_bib0004","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929."},{"issue":"2","key":"10.1016\/j.neunet.2026.109707_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.engmed.2025.100069","article-title":"Artificial intelligence for the noninvasive diagnosis of clinically significant portal hypertension","volume":"2","author":"Du","year":"2025","journal-title":"EngMedicine"},{"issue":"10","key":"10.1016\/j.neunet.2026.109707_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\u2013infrared object detection","volume":"35","author":"Fu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109707_bib0007","series-title":"European conference on computer vision","first-page":"464","article-title":"DAMSDet: Dynamic adaptive multispectral detection transformer with competitive query selection and adaptive feature fusion","author":"Guo","year":"2024"},{"key":"10.1016\/j.neunet.2026.109707_bib0008","series-title":"2016 IEEE conference on computer vision and pattern recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2026.109707_bib0009","doi-asserted-by":"crossref","first-page":"4400","DOI":"10.1109\/TMM.2025.3543056","article-title":"Deformle cross-attention trnsformer for wekly aligned rgb\u2013t pedestrin detection","volume":"27","author":"Hu","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109707_bib0010","series-title":"IEEE\/CVF international conference on computer vision","first-page":"3496","article-title":"LLVIP: A visible-infrared paired dataset for low-light vision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neunet.2026.109707_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2026.134289","article-title":"MiddleCLIP: Unleashing the potential of the middle layers in CLIP for training-free open-vocabulary semantic segmentation","volume":"698","author":"Jin","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109707_bib0012","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.neucom.2022.04.015","article-title":"FCMNet: Frequency-aware cross-modality attention networks for RGB-D salient object detection","volume":"491","author":"Jin","year":"2022","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.neunet.2026.109707_bib0013","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/TCDS.2021.3135948","article-title":"Visual sentiment classification via low-rank regularization and label relaxation","volume":"14","author":"Jin","year":"2022","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"issue":"11","key":"10.1016\/j.neunet.2026.109707_bib0014","doi-asserted-by":"crossref","first-page":"7632","DOI":"10.1109\/TCSVT.2022.3180274","article-title":"MoADNet: Mobile asymmetric dual-stream networks for real-time and lightweight RGB-D salient object detection","volume":"32","author":"Jin","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109707_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129129","article-title":"DFD-NAS: General deepfake detection via efficient neural architecture search","volume":"619","author":"Jin","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109707_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128607","article-title":"Image manipulation localization via dynamic cross-modality fusion and progressive integration","volume":"610","author":"Jin","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109707_bib0017","unstructured":"Khanam, R., & Hussain, M. (2024). What is YOLOv5: A deep look into the internal features of the popular object detector. arXiv: 2407.20892."},{"key":"10.1016\/j.neunet.2026.109707_bib0018","unstructured":"Li, M., Ye, P., Huang, Y., Zhang, L., Chen, T., He, T., Fan, J., & Ouyang, W. (2024a). Adapter-X: A novel general parameter-efficient fine-tuning framework for vision. arXiv: 2406.03051."},{"key":"10.1016\/j.neunet.2026.109707_bib0019","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.2026.109707_bib0020","series-title":"European conference on computer vision","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.109707_bib0021","series-title":"IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5802","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.2026.109707_bib0022","unstructured":"Liu, J., Zhang, S., Wang, S., & Metaxas, D. N. (2016). Multispectral deep neural networks for pedestrian detection. arXiv: 1611.02644."},{"key":"10.1016\/j.neunet.2026.109707_bib0023","series-title":"IEEE\/CVF international conference on computer vision","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"7","key":"10.1016\/j.neunet.2026.109707_bib0024","doi-asserted-by":"crossref","first-page":"4486","DOI":"10.1109\/TCSVT.2021.3127149","article-title":"SwinNet: Swin transformer drives edge-aware RGB-d and RGB-T salient object detection","volume":"32","author":"Liu","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109707_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108421","article-title":"Balanced multi-modality knowledge mining for RGB-infrared object detection","volume":"196","author":"Ma","year":"2026","journal-title":"Neural Networks"},{"issue":"4","key":"10.1016\/j.neunet.2026.109707_bib0026","doi-asserted-by":"crossref","first-page":"6321","DOI":"10.1109\/LRA.2021.3093871","article-title":"GEM: Glare or gloom, i can still see you\u2013end-to-end multi-modal object detection","volume":"6","author":"Mazhar","year":"2021","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109707_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2026.108997","article-title":"Cross-modal transformer fusion via local sampling for drone RGB-infrared object detection","volume":"202","author":"Qi","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109707_bib0028","unstructured":"Qingyun, F., Dapeng, H., & Zhaokui, W. (2021). Cross-modality fusion transformer for multispectral object detection. arXiv: 2111.00273."},{"key":"10.1016\/j.neunet.2026.109707_bib0029","unstructured":"Redmon, J., & Farhadi, A. (2018). YOLOV3: An incremental improvement. arXiv: 1804.02767."},{"issue":"6","key":"10.1016\/j.neunet.2026.109707_bib0030","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.2026.109707_bib0031","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.2026.109707_bib0032","unstructured":"Si, C., Yang, X., & Shen, W. (2024). See further for parameter efficient fine-tuning by standing on the shoulders of decomposition. arXiv: 2407.05417."},{"issue":"3","key":"10.1016\/j.neunet.2026.109707_bib0033","doi-asserted-by":"crossref","first-page":"2576","DOI":"10.1109\/LRA.2019.2904733","article-title":"RTFNet: RGB-thermal fusion network for semantic segmentation of urban scenes","volume":"4","author":"Sun","year":"2019","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.neunet.2026.109707_bib0034","doi-asserted-by":"crossref","unstructured":"Tian, C., Zhou, Z., Yang, C., Zhu, G., Zhong, F., & He, Z. (2026). Modality-decoupled RGB-thermal object detector via query fusion. arXiv: 2601.08458.","DOI":"10.1109\/ICASSP55912.2026.11461564"},{"issue":"5","key":"10.1016\/j.neunet.2026.109707_bib0035","doi-asserted-by":"crossref","first-page":"2949","DOI":"10.1109\/TCSVT.2021.3099120","article-title":"CGFNet: Cross-guided fusion network for RGB-T salient object detection","volume":"32","author":"Wang","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109707_bib0036","unstructured":"Xiang, X., Zhou, G., Wen, Z., Li, W., Niu, B., Wang, F., Huang, L., Wang, Q., Liu, Y., Pan, Z., Hu, Y. (2026). SLGNet: Synergizing structural priors and language-guided modulation for multimodal object detection. arXiv: 2601.02249."},{"issue":"8","key":"10.1016\/j.neunet.2026.109707_bib0037","doi-asserted-by":"crossref","first-page":"4149","DOI":"10.1109\/TCSVT.2023.3241196","article-title":"Cross-modality double bidirectional interaction and fusion network for RGB-T salient object detection","volume":"33","author":"Xie","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"1","key":"10.1016\/j.neunet.2026.109707_bib0038","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":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109707_bib0039","series-title":"Proceedings of the 33rd ACM international conference on multimedia","first-page":"2409","article-title":"UniRGB-IR: A unified framework for visible-infrared semantic tasks via adapter tuning","author":"Yuan","year":"2025"},{"key":"10.1016\/j.neunet.2026.109707_bib0040","series-title":"2020 IEEE international conference on image processing (ICIP)","first-page":"276","article-title":"Multispectral fusion for object detection with cyclic fuse-and-refine blocks","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109707_bib0041","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L. M., & Shum, H.-Y. (2022). DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv: 2203.03605."},{"issue":"3","key":"10.1016\/j.neunet.2026.109707_bib0042","doi-asserted-by":"crossref","first-page":"4145","DOI":"10.1109\/TNNLS.2021.3105143","article-title":"Weakly aligned feature fusion for multimodal object detection","volume":"36","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109707_bib0043","unstructured":"Zhang, Y., Gao, C., Liu, F., Guo, J., Wang, L., Peng, X., & Meng, D. (2024). IV- tuning: Parameter-efficient transfer learning for infrared-visible tasks. arXiv: 2412.16654."},{"key":"10.1016\/j.neunet.2026.109707_bib0044","series-title":"2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109707_bib0045","article-title":"DMPFDet: An end-to-end deformable mutual-promotion learning network for multispectral visible\u2013infrared fusion detection","author":"Zheng","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109707_bib0046","doi-asserted-by":"crossref","first-page":"7444","DOI":"10.1109\/TMM.2025.3599097","article-title":"COFNet: Contrastive object-aware fusion using box-level masks for multispectral object detection","volume":"27","author":"Zhou","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"issue":"9","key":"10.1016\/j.neunet.2026.109707_bib0047","doi-asserted-by":"crossref","first-page":"9984","DOI":"10.1109\/TITS.2023.3266487","article-title":"Multi-modal feature pyramid transformer for RGB-infrared object detection","volume":"24","author":"Zhu","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011627?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011627?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:41:28Z","timestamp":1793605288000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":47,"alternative-id":["S0893608026011627"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109707","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adjusting modal contributions via differential-driven SoftMax fusion for RGB-IR object detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109707","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":"109707"}}