{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:21:01Z","timestamp":1783056061815,"version":"3.54.6"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013223","name":"Chongqing Research Program of Basic Research and Frontier Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013223","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472053"],"award-info":[{"award-number":["62472053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.engappai.2026.114975","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:15:32Z","timestamp":1777569332000},"page":"114975","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Spatial-semantic collaborative embedding for object-aware multi-focus image fusion"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9335-2245","authenticated-orcid":false,"given":"Wenyi","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3217-9503","authenticated-orcid":false,"given":"Mingqiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6958-5807","authenticated-orcid":false,"given":"Di","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114975_b1","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.inffus.2014.05.003","article-title":"Quadtree-based multi-focus image fusion using a weighted focus-measure","volume":"22","author":"Bai","year":"2015","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b2","doi-asserted-by":"crossref","first-page":"2915","DOI":"10.1109\/TIP.2023.3276330","article-title":"A convolutional neural network-based conditional random field model for structured multi-focus image fusion robust to noise","volume":"32","author":"Bouzos","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"10.1016\/j.engappai.2026.114975_b3","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1016\/j.imavis.2007.12.002","article-title":"A new automated quality assessment algorithm for image fusion","volume":"27","author":"Chen","year":"2009","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.engappai.2026.114975_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102125","article-title":"A defocus and similarity attention-based cascaded network for multi-focus and misaligned image fusion","volume":"103","author":"Chen","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b5","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Chung, J., Tai, Y.W., Tang, C.K., 2020. Cascadepsp: Toward class-agnostic and very high-resolution segmentation via global and local refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8890\u20138899.","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"10.1016\/j.engappai.2026.114975_b6","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.inffus.2022.11.010","article-title":"Mufusion: A general unsupervised image fusion network based on memory unit","volume":"92","author":"Cheng","year":"2023","journal-title":"Inf. Fusion"},{"issue":"Jan","key":"10.1016\/j.engappai.2026.114975_b7","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.114975_b8","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The pascal visual object classes challenge: A retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.engappai.2026.114975_b9","doi-asserted-by":"crossref","unstructured":"Fang, G., Ma, X., Song, M., Mi, M.B., Wang, X., 2023. Depgraph: Towards any structural pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16091\u201316101.","DOI":"10.1109\/CVPR52729.2023.01544"},{"issue":"2","key":"10.1016\/j.engappai.2026.114975_b10","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.inffus.2011.08.002","article-title":"A new image fusion performance metric based on visual information fidelity","volume":"14","author":"Han","year":"2013","journal-title":"Inf. Fusion"},{"issue":"18","key":"10.1016\/j.engappai.2026.114975_b11","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1049\/el:20081754","article-title":"Comments on \u2018information measure for performance of image fusion\u2019","volume":"44","author":"Hossny","year":"2008","journal-title":"Electron. Lett."},{"key":"10.1016\/j.engappai.2026.114975_b12","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.inffus.2022.11.014","article-title":"ZMFF: Zero-shot multi-focus image fusion","volume":"92","author":"Hu","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b13","series-title":"International Conference on Machine Learning","first-page":"5562","article-title":"The lipschitz constant of self-attention","author":"Kim","year":"2021"},{"issue":"2","key":"10.1016\/j.engappai.2026.114975_b14","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.inffus.2005.09.006","article-title":"Pixel-and region-based image fusion with complex wavelets","volume":"8","author":"Lewis","year":"2007","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b15","doi-asserted-by":"crossref","first-page":"4816","DOI":"10.1109\/TIP.2020.2976190","article-title":"DRPL: Deep regression pair learning for multi-focus image fusion","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2026.114975_b16","article-title":"Preventing gradient attenuation in lipschitz constrained convolutional networks","volume":"32","author":"Li","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.114975_b17","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.inffus.2016.05.004","article-title":"Pixel-level image fusion: A survey of the state of the art","volume":"33","author":"Li","year":"2017","journal-title":"Inf. Fusion"},{"issue":"7","key":"10.1016\/j.engappai.2026.114975_b18","doi-asserted-by":"crossref","first-page":"2864","DOI":"10.1109\/TIP.2013.2244222","article-title":"Image fusion with guided filtering","volume":"22","author":"Li","year":"2013","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.engappai.2026.114975_b19","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.inffus.2011.07.001","article-title":"Image matting for fusion of multi-focus images in dynamic scenes","volume":"14","author":"Li","year":"2013","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b20","article-title":"FusionDiff: Multi-focus image fusion using denoising diffusion probabilistic models","volume":"238","author":"Li","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"12","key":"10.1016\/j.engappai.2026.114975_b21","doi-asserted-by":"crossref","first-page":"9904","DOI":"10.1109\/TPAMI.2021.3132068","article-title":"CTNet: Context-based tandem network for semantic segmentation","volume":"44","author":"Li","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"10.1016\/j.engappai.2026.114975_b22","doi-asserted-by":"crossref","first-page":"6009","DOI":"10.1109\/TCSVT.2023.3344222","article-title":"Generation and recombination for multifocus image fusion with free number of inputs","volume":"34","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.114975_b23","series-title":"European Conference on Computer Vision","first-page":"467","article-title":"Segment and recognize anything at any granularity","author":"Li","year":"2024"},{"key":"10.1016\/j.engappai.2026.114975_b24","article-title":"Fusion2Void: Unsupervised multi-focus image fusion based on image inpainting","author":"Lin","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"10.1016\/j.engappai.2026.114975_b25","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.1109\/LSP.2016.2618776","article-title":"Image fusion with convolutional sparse representation","volume":"23","author":"Liu","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.engappai.2026.114975_b26","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.inffus.2014.09.004","article-title":"A general framework for image fusion based on multi-scale transform and sparse representation","volume":"24","author":"Liu","year":"2015","journal-title":"Inf. Fusion"},{"issue":"7","key":"10.1016\/j.engappai.2026.114975_b27","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/JAS.2022.105686","article-title":"SwinFusion: Cross-domain long-range learning for general image fusion via swin transformer","volume":"9","author":"Ma","year":"2022","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.engappai.2026.114975_b28","doi-asserted-by":"crossref","first-page":"5793","DOI":"10.1007\/s00521-020-05358-9","article-title":"Sesf-fuse: An unsupervised deep model for multi-focus image fusion","volume":"33","author":"Ma","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.engappai.2026.114975_b29","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1016\/j.neucom.2022.01.005","article-title":"Review the state-of-the-art technologies of semantic segmentation based on deep learning","volume":"493","author":"Mo","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.114975_b30","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.inffus.2014.10.004","article-title":"Multi-focus image fusion using dictionary-based sparse representation","volume":"25","author":"Nejati","year":"2015","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125665","article-title":"FusionGCN: Multi-focus image fusion using superpixel features generation GCN and pixel-level feature reconstruction CNN","volume":"262","author":"Ouyang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114975_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.optlaseng.2020.106141","article-title":"Fractal dimension based parameter adaptive dual channel PCNN for multi-focus image fusion","volume":"133","author":"Panigrahy","year":"2020","journal-title":"Opt. Lasers Eng."},{"key":"10.1016\/j.engappai.2026.114975_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107404","article-title":"U2-net: Going deeper with nested U-structure for salient object detection","volume":"106","author":"Qin","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.engappai.2026.114975_b34","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., Jagersand, M., 2019. Basnet: Boundary-aware salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7479\u20137489.","DOI":"10.1109\/CVPR.2019.00766"},{"issue":"4","key":"10.1016\/j.engappai.2026.114975_b35","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2026.114975_b36","doi-asserted-by":"crossref","unstructured":"Wang, L., Lu, H., Wang, Y., Feng, M., Wang, D., Yin, B., Ruan, X., 2017. Learning to detect salient objects with image-level supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 136\u2013145.","DOI":"10.1109\/CVPR.2017.404"},{"key":"10.1016\/j.engappai.2026.114975_b37","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/B978-0-12-372529-5.00017-2","article-title":"Performance evaluation of image fusion techniques","volume":"19","author":"Wang","year":"2008","journal-title":"Image Fusion: Algorithms Appl."},{"key":"10.1016\/j.engappai.2026.114975_b38","article-title":"SPDFusion: A semantic prior knowledge-driven method for infrared and visible image fusion","author":"Xiao","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114975_b39","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.engappai.2026.114975_b40","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","article-title":"U2Fusion: A unified unsupervised image fusion network","volume":"44","author":"Xu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114975_b41","series-title":"MFFW: A new dataset for multi-focus image fusion","author":"Xu","year":"2020"},{"issue":"4","key":"10.1016\/j.engappai.2026.114975_b42","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1049\/el:20000267","article-title":"Objective image fusion performance measure","volume":"36","author":"Xydeas","year":"2000","journal-title":"Electron. Lett."},{"key":"10.1016\/j.engappai.2026.114975_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110223","article-title":"Semantic perceptive infrared and visible image fusion transformer","volume":"149","author":"Yang","year":"2024","journal-title":"Pattern Recognit."},{"issue":"2","key":"10.1016\/j.engappai.2026.114975_b44","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.inffus.2006.09.001","article-title":"A novel similarity based quality metric for image fusion","volume":"9","author":"Yang","year":"2008","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.107967","article-title":"Multi-focus image fusion via interactive transformer and asymmetric soft sharing","volume":"133","author":"Zhai","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"9","key":"10.1016\/j.engappai.2026.114975_b46","first-page":"4819","article-title":"Deep learning-based multi-focus image fusion: A survey and a comparative study","volume":"44","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114975_b47","doi-asserted-by":"crossref","first-page":"6276","DOI":"10.1109\/TIP.2020.2990341","article-title":"LFNet: Light field fusion network for salient object detection","volume":"29","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2026.114975_b48","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.inffus.2020.08.022","article-title":"MFF-GAN: An unsupervised generative adversarial network with adaptive and gradient joint constraints for multi-focus image fusion","volume":"66","author":"Zhang","year":"2021","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b49","doi-asserted-by":"crossref","first-page":"6411","DOI":"10.1109\/TMM.2024.3350924","article-title":"Exploit the best of both end-to-end and map-based methods for multi-focus image fusion","volume":"26","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.114975_b50","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.inffus.2019.07.011","article-title":"IFCNN: A general image fusion framework based on convolutional neural network","volume":"54","author":"Zhang","year":"2020","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103433","article-title":"SPGFusion: Semantic prior guided infrared and visible image fusion via pretrained vision models","volume":"125","author":"Zhang","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b52","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J., 2017. Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"10.1016\/j.engappai.2026.114975_b53","article-title":"Unfolding coupled convolutional sparse representation for multi-focus image fusion","author":"Zheng","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b54","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.inffus.2013.11.005","article-title":"Multi-scale weighted gradient-based fusion for multi-focus images","volume":"20","author":"Zhou","year":"2014","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114975_b55","article-title":"Cross-image pixel contrasting for semantic segmentation","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.114975_b56","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1109\/TMM.2021.3129609","article-title":"Semantic-supervised infrared and visible image fusion via a dual-discriminator generative adversarial network","volume":"25","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Multimed."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012571?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626012571?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:03:31Z","timestamp":1783055011000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626012571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":56,"alternative-id":["S0952197626012571"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114975","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Spatial-semantic collaborative embedding for object-aware multi-focus image fusion","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114975","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":"114975"}}