{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T21:10:14Z","timestamp":1784149814275,"version":"3.55.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018553","name":"Science and Technology Plan Project of Wenzhou Municipality","doi-asserted-by":"publisher","award":["ZG2024012"],"award-info":[{"award-number":["ZG2024012"]}],"id":[{"id":"10.13039\/501100018553","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772102"],"award-info":[{"award-number":["61772102"]}],"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":["62176036"],"award-info":[{"award-number":["62176036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["3132023523"],"award-info":[{"award-number":["3132023523"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011996","name":"Dalian Maritime University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011996","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104401","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:52:51Z","timestamp":1776959571000},"page":"104401","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["BSPFusion: A bottom-up semantically progressive network for infrared and visible image fusion"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3934-1323","authenticated-orcid":false,"given":"Wenyu","family":"Shao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9296-9975","authenticated-orcid":false,"given":"Hongbo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-7347","authenticated-orcid":false,"given":"Weiping","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2899-9816","authenticated-orcid":false,"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.inffus.2026.104401_bib0001","doi-asserted-by":"crossref","first-page":"2349","DOI":"10.1109\/TPAMI.2024.3521416","article-title":"Infrared and visible image fusion: from data compatibility to task adaption","volume":"47","author":"Liu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104401_bib0002","doi-asserted-by":"crossref","first-page":"3139","DOI":"10.1109\/TIP.2025.3571339","article-title":"SDSFusion: a semantic-aware infrared and visible image fusion network for degraded scenes","volume":"34","author":"Chen","year":"2025","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"10.1016\/j.inffus.2026.104401_bib0003","doi-asserted-by":"crossref","first-page":"17794","DOI":"10.1109\/TITS.2024.3426539","article-title":"CEFusion: an infrared and visible image fusion network based on cross-modal multi-granularity information interaction and edge guidance","volume":"25","author":"Yang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"7","key":"10.1016\/j.inffus.2026.104401_bib0004","doi-asserted-by":"crossref","first-page":"9767","DOI":"10.1109\/TITS.2025.3562267","article-title":"Dual-modal prior semantic guided infrared and visible image fusion for intelligent transportation system","volume":"26","author":"Li","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.inffus.2026.104401_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111949","article-title":"AITFuse: infrared and visible image fusion via adaptive interactive transformer learning","volume":"299","author":"Wang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.inffus.2026.104401_bib0006","doi-asserted-by":"crossref","first-page":"4776","DOI":"10.1109\/TMM.2023.3326296","article-title":"CAMF: an interpretable infrared and visible image fusion network based on class activation mapping","volume":"26","author":"Tang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104401_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2020.107734","article-title":"Bayesian fusion for infrared and visible images","volume":"177","author":"Zhao","year":"2020","journal-title":"Signal Process."},{"key":"10.1016\/j.inffus.2026.104401_bib0008","doi-asserted-by":"crossref","first-page":"4733","DOI":"10.1109\/TIP.2020.2975984","article-title":"MDLatLRR: a novel decomposition method for infrared and visible image fusion","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104401_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.infrared.2023.104715","article-title":"An illumination-dependent adaptive fusion method for infrared and visible images","volume":"131","author":"Li","year":"2023","journal-title":"Infrared Phys. Technol."},{"key":"10.1016\/j.inffus.2026.104401_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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.inffus.2026.104401_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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.inffus.2026.104401_bib0012","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"8115","article-title":"Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104401_bib0013","series-title":"Advances in Neural Information Processing Systems","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104401_bib0014","series-title":"Proceedings of the 41St International Conference on Machine Learning","first-page":"60749","article-title":"Image fusion via vision-language model","volume":"235","author":"Zhao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104401_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102790","article-title":"TextFusion: unveiling the power of textual semantics for controllable image fusion","volume":"117","author":"Cheng","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104401_bib0016","doi-asserted-by":"crossref","DOI":"10.1145\/3748510","article-title":"Infrared and visible image fusion via text-prior guided frequency-Domain decomposition","author":"Shao","year":"2025","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"10.1016\/j.inffus.2026.104401_bib0017","series-title":"Advances in Neural Information Processing Systems","first-page":"39552","article-title":"Text-DiFuse: an interactive multi-Modal image fusion framework based on text-modulated diffusion model","volume":"37","author":"Zhang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104401_bib0018","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"12637","article-title":"Highlight what you want: weakly-supervised instance-Level controllable infrared-Visible image fusion","author":"Wang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104401_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"27026","article-title":"Text-IF: leveraging semantic text guidance for degradation-Aware and interactive image fusion","author":"Yi","year":"2024"},{"issue":"9","key":"10.1016\/j.inffus.2026.104401_bib0020","doi-asserted-by":"crossref","first-page":"7577","DOI":"10.1109\/TPAMI.2025.3568433","article-title":"OmniFuse: composite degradation-Robust image fusion with language-Driven semantics","volume":"47","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10.1016\/j.inffus.2026.104401_bib0021","doi-asserted-by":"crossref","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","article-title":"DenseFuse: a fusion approach to infrared and visible images","volume":"28","author":"Li","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104401_bib0022","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12797","article-title":"Rethinking the image fusion: a fast unified image fusion network based on proportional maintenance of gradient and intensity","author":"Zhang","year":"2020"},{"key":"10.1016\/j.inffus.2026.104401_bib0023","series-title":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","article-title":"TCFusion: a three-branch cross-domain fusion network for infrared and visible images","author":"Shao","year":"2024"},{"issue":"9","key":"10.1016\/j.inffus.2026.104401_bib0024","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 Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"10.1016\/j.inffus.2026.104401_bib0025","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.inffus.2026.104401_bib0026","first-page":"1","article-title":"SwinFuse: a residual swin transformer fusion network for infrared and visible images","volume":"71","author":"Wang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.inffus.2026.104401_bib0027","doi-asserted-by":"crossref","first-page":"5413","DOI":"10.1109\/TMM.2022.3192661","article-title":"YDTR: infrared and visible image fusion via Y-shape dynamic transformer","volume":"25","author":"Tang","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104401_bib0028","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"25912","article-title":"Equivariant multi-modality image fusion","author":"Zhao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104401_bib0029","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.inffus.2018.09.004","article-title":"FusionGAN: a generative adversarial network for infrared and visible image fusion","volume":"48","author":"Ma","year":"2019","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104401_bib0030","doi-asserted-by":"crossref","first-page":"7800","DOI":"10.1109\/TMM.2022.3228685","article-title":"Infrared and visible image fusion via interactive compensatory attention adversarial learning","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Trans. Multimed."},{"issue":"8","key":"10.1016\/j.inffus.2026.104401_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 Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104401_bib0032","article-title":"TGFuse: an infrared and visible image fusion approach based on transformer and generative adversarial network","author":"Rao","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.inffus.2026.104401_bib0033","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1109\/TCSVT.2024.3460172","article-title":"FreqGAN: infrared and visible image fusion via unified frequency adversarial learning","volume":"35","author":"Wang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104401_bib0034","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"8082","article-title":"DDFM: denoising diffusion model for multi-modality image fusion","author":"Zhao","year":"2023"},{"key":"10.1016\/j.inffus.2026.104401_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102450","article-title":"Diff-IF: multi-modality image fusion via diffusion model with fusion knowledge prior","volume":"110","author":"Yi","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104401_bib0036","doi-asserted-by":"crossref","first-page":"5705","DOI":"10.1109\/TIP.2023.3322046","article-title":"Dif-fusion: toward high color fidelity in infrared and visible image fusion with diffusion models","volume":"32","author":"Yue","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.inffus.2026.104401_bib0037","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 Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104401_bib0038","doi-asserted-by":"crossref","first-page":"5803","DOI":"10.1109\/TIP.2025.3607628","article-title":"URFusion: unsupervised unified degradation-robust image fusion network","volume":"34","author":"Xu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104401_bib0039","series-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems","article-title":"Deno-IF: unsupervised noisy visible and infrared image fusion method","author":"Xu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104401_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114003","article-title":"Knowledge enhancement and disentanglement learning for video captioning","volume":"326","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"11","key":"10.1016\/j.inffus.2026.104401_bib0041","doi-asserted-by":"crossref","first-page":"9845","DOI":"10.1109\/TPAMI.2025.3591930","article-title":"An efficient image fusion network exploiting unifying language and mask guidance","volume":"47","author":"Cao","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104401_bib0042","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"139","author":"Radford","year":"2021"},{"key":"10.1016\/j.inffus.2026.104401_bib0043","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume":"139","author":"Jia","year":"2021"},{"key":"10.1016\/j.inffus.2026.104401_bib0044","series-title":"Proceedings of the 39th International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","volume":"162","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2026.104401_bib0045","series-title":"Proceedings of the 40th International Conference on Machine Learning","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume":"202","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2026.104401_bib0046","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":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104401_bib0047","doi-asserted-by":"crossref","first-page":"7943","DOI":"10.1109\/TIP.2025.3635048","article-title":"Text-guided semantic alignment network with spatial-frequency interaction for infrared-visible image fusion under extreme illumination","volume":"34","author":"Yue","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104401_bib0048","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TMM.2026.3668472","article-title":"Entity-guided multi-task learning for infrared and visible image fusion","author":"Shao","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.inffus.2026.104401_bib0049","series-title":"Advances in Neural Information Processing Systems","first-page":"72983","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer","year":"2023"},{"key":"10.1016\/j.inffus.2026.104401_bib0050","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","article-title":"PIAFusion: a progressive infrared and visible image fusion network based on illumination aware","volume":"83","author":"Tang","year":"2022","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104401_bib0051","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12484","article-title":"Fusiondn: a unified densely connected network for image fusion","author":"Xu","year":"2020"},{"key":"10.1016\/j.inffus.2026.104401_bib0052","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"779","article-title":"You only look once: unified, real-Time object detection","author":"Redmon","year":"2016"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002800?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002800?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:17:47Z","timestamp":1784146667000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526002800"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":52,"alternative-id":["S1566253526002800"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104401","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BSPFusion: A bottom-up semantically progressive network for infrared and visible image fusion","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104401","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104401"}}