{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T13:11:22Z","timestamp":1778764282103,"version":"3.51.4"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["62576197"],"award-info":[{"award-number":["62576197"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023MF066"],"award-info":[{"award-number":["ZR2023MF066"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2025QC681"],"award-info":[{"award-number":["ZR2025QC681"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019M662432"],"award-info":[{"award-number":["2019M662432"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019TQ0190"],"award-info":[{"award-number":["2019TQ0190"]}],"id":[{"id":"10.13039\/501100002858","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":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.109003","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T23:53:16Z","timestamp":1776383596000},"page":"109003","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Task-driven infrared and visible image fusion via detail and semantic dual injection"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9218-5916","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2842-0855","authenticated-orcid":false,"given":"Ludan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6157-2051","authenticated-orcid":false,"given":"Jiande","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109003_bib0001","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7457","article-title":"Task-driven image fusion with learnable fusion loss","author":"Bai","year":"2025"},{"key":"10.1016\/j.neunet.2026.109003_bib0002","series-title":"Advances in neural information processing systems","first-page":"120311","article-title":"Conditional controllable image fusion","volume":"vol. 37","author":"Cao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109003_bib0003","doi-asserted-by":"crossref","unstructured":"Cao, J., Zhang, K., Luo, M., Yin, C., & Lai, X. (2016). Extreme learning machine and adaptive sparse representation for image classification. Neural Networks, 81, 91\u2013102.","DOI":"10.1016\/j.neunet.2016.06.001"},{"key":"10.1016\/j.neunet.2026.109003_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"28102","article-title":"One model for ALL: Low-level task interaction is a key to task-agnostic image fusion","author":"Cheng","year":"2025"},{"key":"10.1016\/j.neunet.2026.109003_bib0005","doi-asserted-by":"crossref","unstructured":"Dong, L., & Wang, J. (2025). FusionOC: Research on optimal control method for infrared and visible light image fusion. Neural Networks, 181, 106811.","DOI":"10.1016\/j.neunet.2024.106811"},{"key":"10.1016\/j.neunet.2026.109003_bib0006","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.neunet.2022.08.015","article-title":"Deep learning-based image deconstruction method with maintained saliency","volume":"155","author":"Fujimoto","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109003_bib0007","series-title":"Advances in neural information processing systems","first-page":"1140","article-title":"Segnext: Rethinking convolutional attention design for semantic segmentation","volume":"vol. 35","author":"Guo","year":"2022"},{"key":"10.1016\/j.neunet.2026.109003_bib0008","doi-asserted-by":"crossref","unstructured":"Hu, H., Ma, Y., Li, R., Feng, Z., Yang, S., Du, S., & Gao, Y. (2025). Cross-sensor contrastive learning-based pre-training for machinery fault diagnosis under sample-limited conditions. Knowledge-Based Systems, 311, 113075.","DOI":"10.1016\/j.knosys.2025.113075"},{"key":"10.1016\/j.neunet.2026.109003_bib0009","doi-asserted-by":"crossref","first-page":"3314","DOI":"10.1109\/TMM.2021.3096088","article-title":"Infrared and visible image fusion based on deep decomposition network and saliency analysis","volume":"24","author":"Jian","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109003_bib0010","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.inffus.2021.02.008","article-title":"An infrared and visible image fusion method based on multi-scale transformation and norm optimization","volume":"71","author":"Li","year":"2021","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109003_bib0011","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.inffus.2021.02.008","article-title":"An infrared and visible image fusion method based on multi-scale transformation and norm optimization","volume":"71","author":"Li","year":"2021","journal-title":"Information Fusion"},{"issue":"9","key":"10.1016\/j.neunet.2026.109003_bib0012","doi-asserted-by":"crossref","first-page":"11040","DOI":"10.1109\/TPAMI.2023.3268209","article-title":"Lrrnet: A novel representation learning guided fusion network for infrared and visible images","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109003_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3833","article-title":"Single image deraining: A comprehensive benchmark analysis","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2026.109003_bib0014","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.2026.109003_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110633","article-title":"Dsfusion: Infrared and visible image fusion method combining detail and scene information","volume":"154","author":"Liu","year":"2024","journal-title":"Pattern Recognition"},{"issue":"2","key":"10.1016\/j.neunet.2026.109003_bib0016","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1109\/TETCI.2024.3352490","article-title":"Stfnet: Self-supervised transformer for infrared and visible image fusion","volume":"8","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"10.1016\/j.neunet.2026.109003_bib0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112043","article-title":"Hsenet: Hierarchical semantic-enriched network for multi-modal image fusion","volume":"170","author":"Liu","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109003_bib0018","first-page":"1","article-title":"Stdfusionnet: An infrared and visible image fusion network based on salient target detection","volume":"70","author":"Ma","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.neunet.2026.109003_bib0019","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.neunet.2021.01.023","article-title":"Sam-gan: Self-attention supporting multi-stage generative adversarial networks for text-to-image synthesis","volume":"138","author":"Peng","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109003_bib0020","first-page":"1","article-title":"Tgfuse: An infrared and visible image fusion approach based on transformer and generative adversarial network","author":"Rao","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109003_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110728","article-title":"Semantic attention-based heterogeneous feature aggregation network for image fusion","volume":"155","author":"Ruan","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109003_bib0022","doi-asserted-by":"crossref","first-page":"7335","DOI":"10.1109\/TMM.2024.3366150","article-title":"Deep rank-n decomposition network for image fusion","volume":"26","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109003_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131279","article-title":"D2fusion: Dual-AE and latent-guided diffusion network for infrared and visible image fusion","volume":"654","author":"Sun","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109003_bib0024","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"4003","article-title":"Detfusion: A detection-driven infrared and visible image fusion network","author":"Sun","year":"2022"},{"issue":"1","key":"10.1016\/j.neunet.2026.109003_bib0025","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TPAMI.2025.3609323","article-title":"Mask-difuser: A masked diffusion model for unified unsupervised image fusion","volume":"48","author":"Tang","year":"2026","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109003_bib0026","series-title":"Advances in neural information processing systems","article-title":"Controlfusion: A controllable image fusion network with language-vision degradation prompts","author":"Tang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109003_bib0027","doi-asserted-by":"crossref","first-page":"5262","DOI":"10.1007\/s11263-025-02427-1","article-title":"C2RF: Bridging multi-modal image registration and fusion via commonality mining and contrastive learning","volume":"133","author":"Tang","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109003_bib0028","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.2026.109003_bib0029","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.2026.109003_bib0030","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.neunet.2019.12.024","article-title":"Attention-guided CNN for image denoising","volume":"124","author":"Tian","year":"2020","journal-title":"Neural Networks"},{"issue":"8","key":"10.1016\/j.neunet.2026.109003_bib0031","doi-asserted-by":"crossref","first-page":"3677","DOI":"10.1109\/TCSVT.2023.3239627","article-title":"A cross-scale iterative attentional adversarial fusion network for infrared and visible images","volume":"33","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109003_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107916","article-title":"Mhdbn: Mamba-based hybrid dual-branch network for multi-focus image fusion","volume":"192","author":"Wu","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109003_bib0033","series-title":"Thirty-eighth AAAI conference on artificial intelligence(AAAI)","first-page":"8637","article-title":"Smr-net: Semantic-guided mutually reinforcing network for cross-modal image fusion and salient object detection","author":"Xiao","year":"2025"},{"key":"10.1016\/j.neunet.2026.109003_bib0034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2024.3476526","article-title":"Fafusion: Learning for infrared and visible image fusion via frequency awareness","volume":"73","author":"Xiao","year":"2024","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.neunet.2026.109003_bib0035","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1016\/j.neunet.2021.05.029","article-title":"Self-spectral learning with GAN based spectral\u2013spatial target detection for hyperspectral image","volume":"142","author":"Xie","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109003_bib0036","first-page":"1","article-title":"Infrared and visible image fusion using visual saliency sparse representation and detail injection model","volume":"70","author":"Yang","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.neunet.2026.109003_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111561","article-title":"Identity-aware infrared person image generation and re-identification via controllable diffusion model","volume":"165","author":"Yu","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109003_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108450","article-title":"Cmmdl: Cross-modal multi-domain learning method for image fusion","volume":"196","author":"Yuan","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109003_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107026","article-title":"M4net: Multi-level multi-patch multi-receptive multi-dimensional attention network for infrared small target detection","volume":"183","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109003_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26477","article-title":"Dispel darkness for better fusion: A controllable visual enhancer based on cross-modal conditional adversarial learning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109003_bib0041","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.inffus.2021.06.008","article-title":"Image fusion meets deep learning: A survey and perspective","volume":"76","author":"Zhang","year":"2021","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109003_bib0042","series-title":"Advances in neural information processing systems","first-page":"52296","article-title":"E2e-mfd: Towards end-to-end synchronous multimodal fusion detection","volume":"vol. 37","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109003_bib0043","doi-asserted-by":"crossref","first-page":"2097","DOI":"10.1109\/TMM.2024.3521840","article-title":"Texture-content dual guided network for visible and infrared image fusion","volume":"27","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109003_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107351","article-title":"Spatial and frequency information fusion transformer for image super-resolution","volume":"187","author":"Zhang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109003_bib0045","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.2026.109003_bib0046","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26374","article-title":"Probing synergistic high-order interaction in infrared and visible image fusion","author":"Zheng","year":"2024"},{"key":"10.1016\/j.neunet.2026.109003_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102359","article-title":"Frequency integration and spatial compensation network for infrared and visible image fusion","volume":"109","author":"Zheng","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109003_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107613","article-title":"Hlgnet: High-light guided network for low-light instance segmentation with spatial-frequency domain enhancement","volume":"190","author":"Zhou","year":"2025","journal-title":"Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004648?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004648?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:40:46Z","timestamp":1778762446000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":48,"alternative-id":["S0893608026004648"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109003","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Task-driven infrared and visible image fusion via detail and semantic dual injection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109003","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":"109003"}}