{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T04:26:15Z","timestamp":1793679975421,"version":"4.5.1"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133865","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T06:02:41Z","timestamp":1785996161000},"page":"133865","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["MTFusion: A unified multi-task framework for joint infrared-visible image fusion and general vision tasks"],"prefix":"10.1016","volume":"333","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3692-6545","authenticated-orcid":false,"given":"Jiangtao","family":"Nie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8040-3850","authenticated-orcid":false,"given":"Lihao","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5042-646X","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7528-420X","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8101-5738","authenticated-orcid":false,"given":"Chen","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2936-2870","authenticated-orcid":false,"given":"Jiangbin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133865_bib0001","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.infrared.2017.01.026","article-title":"Fusion of infrared and visible images based on nonsubsampled contourlet transform and sparse K-SVD dictionary learning","volume":"82","author":"Cai","year":"2017","journal-title":"Infrared Physics & Technology"},{"key":"10.1016\/j.eswa.2026.133865_bib0002","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1109\/TMM.2021.3057493","article-title":"Multi-focus image fusion based on multi-scale gradients and image matting","volume":"24","author":"Chen","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.133865_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130884","article-title":"HSFusion: Hierarchical multi-scale feature fusion network based on state space model for infrared and visible image fusion","volume":"305","author":"Cheng","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133865_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111391","article-title":"Sam-guided multi-level collaborative transformer for infrared and visible image fusion","volume":"162","author":"Guo","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133865_bib0005","series-title":"International conference on machine learning","first-page":"3854","article-title":"Learning to branch for multi-task learning","author":"Guo","year":"2020"},{"key":"10.1016\/j.eswa.2026.133865_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125639","article-title":"A model-based infrared and visible image fusion network with cooperative optimization","volume":"263","author":"Hu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133865_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112419","article-title":"PCFFusion: Progressive cross-modal feature fusion network for infrared and visible images","volume":"172","author":"Huang","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133865_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127229","article-title":"FefDM-Transformer: Dual\u2013channel multi\u2013stage Transformer\u2013based encoding and fusion mode for infrared\u2013visible images","volume":"277","author":"Li","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133865_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127229","article-title":"FefDM-Transformer: Dual-channel multi-stage transformer-based encoding and fusion mode for infrared\u2013visible images","volume":"277","author":"Li","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133865_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110972","article-title":"Object matching of visible\u2013infrared image based on attention mechanism and feature fusion","volume":"158","author":"Li","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133865_bib0011","doi-asserted-by":"crossref","first-page":"4060","DOI":"10.1109\/LRA.2023.3272269","article-title":"Explicit attention-enhanced fusion for RGB-thermal perception tasks","volume":"8","author":"Liang","year":"2023","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.133865_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","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.eswa.2026.133865_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","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.eswa.2026.133865_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102352","article-title":"A semantic-driven coupled network for infrared and visible image fusion","volume":"108","author":"Liu","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.133865_bib0015","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.neucom.2017.01.006","article-title":"Structure tensor and nonsubsampled shearlet transform based algorithm for CT and MRI image fusion","volume":"235","author":"Liu","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.133865_bib0016","doi-asserted-by":"crossref","first-page":"6375","DOI":"10.1109\/TMM.2024.3349865","article-title":"Prompt guided transformer for multi-task dense prediction","volume":"26","author":"Lu","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.133865_bib0017","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 Journal of Automatica Sinica"},{"key":"10.1016\/j.eswa.2026.133865_bib0018","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":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.133865_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103832","article-title":"Interactive visible and infrared image fusion and segmentation","volume":"127","author":"Nie","year":"2026","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.133865_bib0020","series-title":"Computer vision\u2013ECCV 2020: 16th European conference","first-page":"235","article-title":"Hierarchical dynamic filtering network for RGB-D salient object detection","author":"Pang","year":"2020"},{"key":"10.1016\/j.eswa.2026.133865_bib0021","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4714","article-title":"DeepFuse: A deep unsupervised approach for exposure fusion with extreme exposure image pairs","author":"Prabhakar","year":"2017"},{"key":"10.1016\/j.eswa.2026.133865_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125682","article-title":"A novel infrared and visible image fusion network based on cross-modality reinforcement and multi-attention fusion strategy","volume":"264","author":"Qi","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133865_bib0023","series-title":"2023 IEEE International conference on multimedia and expo (ICME)","first-page":"1859","article-title":"Scale-aware task message transferring for multi-task learning","author":"Sirejiding","year":"2023"},{"key":"10.1016\/j.eswa.2026.133865_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125472","article-title":"SFINet: A semantic feature interactive learning network for full-time infrared and visible image fusion","volume":"261","author":"Song","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133865_bib0025","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"},{"key":"10.1016\/j.eswa.2026.133865_bib0026","series-title":"2022 IEEE International symposium on circuits and systems (ISCAS)","first-page":"3299","article-title":"TAFNet: A three-stream adaptive fusion network for RGB-T crowd counting","author":"Tang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133865_bib0027","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.eswa.2026.133865_bib0028","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":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.133865_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.eswa.2026.133865_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101828","article-title":"An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection","volume":"98","author":"Wang","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.133865_bib0031","doi-asserted-by":"crossref","first-page":"3658","DOI":"10.1109\/TGRS.2014.2381272","article-title":"Hyperspectral and multispectral image fusion based on a sparse representation","volume":"53","author":"Wei","year":"2015","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.133865_bib0032","series-title":"Advances in neural information processing systems","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"vol. 34","author":"Xie","year":"2021"},{"key":"10.1016\/j.eswa.2026.133865_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122753","article-title":"CAGNet: Coordinated attention guidance network for RGB-T crowd counting","volume":"243","author":"Yang","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133865_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26974","article-title":"MRFS: Mutually reinforcing image fusion and segmentation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133865_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8297","article-title":"Wide-area crowd counting via ground-plane density maps and multi-view fusion cnns","author":"Zhang","year":"2019"},{"key":"10.1016\/j.eswa.2026.133865_bib0036","series-title":"Proceedings of the Asian conference on computer vision","first-page":"90","article-title":"Spatio-channel attention blocks for cross-modal crowd counting","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133865_bib0037","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":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.133865_bib0038","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.eswa.2026.133865_bib0039","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.eswa.2026.133865_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"25912","article-title":"Equivariant multi-modality image fusion","author":"Zhao","year":"2024"},{"key":"10.1016\/j.eswa.2026.133865_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26384","article-title":"Probing synergistic high-order interaction in infrared and visible image fusion","author":"Zheng","year":"2024"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426027739?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426027739?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T03:44:25Z","timestamp":1793677465000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426027739"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":41,"alternative-id":["S0957417426027739"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133865","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MTFusion: A unified multi-task framework for joint infrared-visible image fusion and general vision tasks","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133865","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":"133865"}}