{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T03:06:15Z","timestamp":1783825575301,"version":"3.55.0"},"reference-count":103,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302078"],"award-info":[{"award-number":["62302078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["2022YFA1004101"],"award-info":[{"award-number":["2022YFA1004101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["22B2052"],"award-info":[{"award-number":["22B2052"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["62027826"],"award-info":[{"award-number":["62027826"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010031","name":"Postdoctoral Research Foundation of China","doi-asserted-by":"publisher","award":["2023M73074"],"award-info":[{"award-number":["2023M73074"]}],"id":[{"id":"10.13039\/501100010031","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s11263-023-01952-1","type":"journal-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T20:01:25Z","timestamp":1702065685000},"page":"1748-1775","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":192,"title":["CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion"],"prefix":"10.1007","volume":"132","author":[{"given":"Jinyuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runjia","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanyao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Risheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongxuan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2085-2676","authenticated-orcid":false,"given":"Xin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,8]]},"reference":[{"issue":"4","key":"1952_CR1","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","volume":"2","author":"H Abdi","year":"2010","unstructured":"Abdi, H., & Williams, L. J. (2010). Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2(4), 433\u2013459.","journal-title":"Wiley Interdisciplinary Reviews: Computational Statistics"},{"issue":"12","key":"1952_CR2","first-page":"1890","volume":"69","author":"V Aslantas","year":"2015","unstructured":"Aslantas, V., & Bendes, E. (2015). A new image quality metric for image fusion: The sum of the correlations of differences. Aeu-International Journal of Electronics and Communications, 69(12), 1890\u20131896.","journal-title":"Aeu-International Journal of Electronics and Communications"},{"key":"1952_CR3","doi-asserted-by":"crossref","unstructured":"Bavirisetti, D. P. (2017). Multi-sensor image fusion based on fourth order partial differential equations. In 20th International Conference on Information Fusion (Fusion).","DOI":"10.23919\/ICIF.2017.8009719"},{"issue":"5","key":"1952_CR4","first-page":"1014","volume":"15","author":"G Bhatnagar","year":"2013","unstructured":"Bhatnagar, G., Wu, Q. J., & Liu, Z. (2013). Directive contrast based multimodal medical image fusion in NSCT domain. IEEE TMM, 15(5), 1014\u20131024.","journal-title":"IEEE TMM"},{"issue":"341","key":"1952_CR5","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.optcom.2014.12.032","volume":"341","author":"G Cui","year":"2015","unstructured":"Cui, G., Feng, H., Xu, Z., et al. (2015). Detail preserved fusion of visible and infrared images using regional saliency extraction and multi-scale image decomposition. Optics Communications, 341(341), 199\u2013209.","journal-title":"Optics Communications"},{"issue":"10","key":"1952_CR6","first-page":"3089","volume":"15","author":"AL Da Cunha","year":"2006","unstructured":"Da Cunha, A. L., Zhou, J., & Do, M. N. (2006). The nonsubsampled contourlet transform: theory, design, and applications. IEEE TIP, 15(10), 3089\u20133101.","journal-title":"IEEE TIP"},{"key":"1952_CR7","unstructured":"Dosovitskiy, A., Beyer, L., & Kolesnikov, A., et\u00a0al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929."},{"key":"1952_CR8","doi-asserted-by":"crossref","unstructured":"Duan, Z., Lan, J., & Xu, Y., et\u00a0al. (2017). Pedestrian detection via bi-directional multi-scale analysis. In ACM MM, ACM (pp. 1023\u20131031).","DOI":"10.1145\/3123266.3123356"},{"issue":"12","key":"1952_CR9","first-page":"2959","volume":"43","author":"AM Eskicioglu","year":"1995","unstructured":"Eskicioglu, A. M., & Fisher, P. S. (1995). Image quality measures and their performance. IEEE TCOM, 43(12), 2959\u20132965.","journal-title":"IEEE TCOM"},{"key":"1952_CR10","doi-asserted-by":"crossref","first-page":"4880","DOI":"10.1109\/TIP.2023.3307215","volume":"32","author":"X Fan","year":"2023","unstructured":"Fan, X., Li, Z., Li, Z., et al. (2023). Automated learning for deformable medical image registration by jointly optimizing network architectures and objective functions. IEEE Transactions on Image Processing, 32, 4880\u20134892.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"6","key":"1952_CR11","first-page":"1263","volume":"28","author":"VN Gangapure","year":"2017","unstructured":"Gangapure, V. N., Nanda, S., & Chowdhury, A. S. (2017). Superpixel-based causal multisensor video fusion. IEEE TCSVT, 28(6), 1263\u20131272.","journal-title":"IEEE TCSVT"},{"issue":"2","key":"1952_CR12","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.inffus.2011.08.002","volume":"14","author":"Y Han","year":"2013","unstructured":"Han, Y., Cai, Y., Cao, Y., et al. (2013). A new image fusion performance metric based on visual information fidelity. Information Fusion, 14(2), 127\u2013135.","journal-title":"Information Fusion"},{"key":"1952_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., & Wu, Y., et\u00a0al. (2020). Momentum contrast for unsupervised visual representation learning. In IEEE\/CVF CVPR (pp. 9729\u20139738).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1952_CR14","unstructured":"Henaff, O. (2020). Data-efficient image recognition with contrastive predictive coding. In ICML, PMLR (pp. 4182\u20134192)."},{"key":"1952_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., & Huang, L., et\u00a0al. (2019). CCNET: Criss-cross attention for semantic segmentation. In ICCV (pp. 603\u2013612).","DOI":"10.1109\/ICCV.2019.00069"},{"key":"1952_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liu, J., & Fan, X., et\u00a0al. (2022). Reconet: Recurrent correction network for fast and efficient multi-modality image fusion. In European conference on computer Vision, Springer (pp. 539\u2013555).","DOI":"10.1007\/978-3-031-19797-0_31"},{"issue":"4\u20135","key":"1952_CR17","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","volume":"13","author":"A Hyv\u00e4rinen","year":"2000","unstructured":"Hyv\u00e4rinen, A., & Oja, E. (2000). Independent component analysis: Algorithms and applications. Neural Networks, 13(4\u20135), 411\u2013430.","journal-title":"Neural Networks"},{"key":"1952_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zhang, Z., & Fan, X., et\u00a0al. (2022a). Towards all weather and unobstructed multi-spectral image stitching: Algorithm and benchmark. In Proceedings of the 30th ACM international conference on multimedia (pp. 3783\u20133791).","DOI":"10.1145\/3503161.3547966"},{"key":"1952_CR19","unstructured":"Jiang, Z., Zhang, Z., & Yu, Y., et\u00a0al. (2022b). Bilevel modeling investigated generative adversarial framework for image restoration. The Visual Computer 1\u201313."},{"key":"1952_CR20","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.inffus.2015.03.003","volume":"27","author":"M Kim","year":"2016","unstructured":"Kim, M., Han, D. K., & Ko, H. (2016). Joint patch clustering-based dictionary learning for multimodal image fusion. Information Fusion, 27, 198\u2013214.","journal-title":"Information Fusion"},{"key":"1952_CR21","doi-asserted-by":"crossref","unstructured":"Lei, J., Li, J., & Liu, J., et\u00a0al. (2023). Galfusion: Multi-exposure image fusion via a global-local aggregation learning network. IEEE Transactions on Instrumentation and Measurement.","DOI":"10.1109\/TIM.2023.3267525"},{"issue":"2","key":"1952_CR22","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.inffus.2005.09.006","volume":"8","author":"JJ Lewis","year":"2007","unstructured":"Lewis, J. J., O\u2019Callaghan, R. J., Nikolov, S. G., et al. (2007). Pixel-and region-based image fusion with complex wavelets. Information Fusion, 8(2), 119\u2013130.","journal-title":"Information Fusion"},{"issue":"5","key":"1952_CR23","first-page":"2614","volume":"28","author":"H Li","year":"2018","unstructured":"Li, H., & Wu, X. J. (2018). Densefuse: A fusion approach to infrared and visible images. IEEE TIP, 28(5), 2614\u20132623.","journal-title":"IEEE TIP"},{"key":"1952_CR24","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, X. J., & Kittler, J. (2018a). Infrared and visible image fusion using a deep learning framework. In 2018 24th international conference on pattern recognition (ICPR), IEEE (pp. 2705\u20132710).","DOI":"10.1109\/ICPR.2018.8546006"},{"key":"1952_CR25","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.inffus.2021.02.023","volume":"73","author":"H Li","year":"2021","unstructured":"Li, H., Wu, X. J., & Kittler, J. (2021). RFN-nest: An end-to-end residual fusion network for infrared and visible images. Information Fusion, 73, 72\u201386.","journal-title":"Information Fusion"},{"issue":"2","key":"1952_CR26","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1109\/TCSVT.2022.3202692","volume":"33","author":"J Li","year":"2022","unstructured":"Li, J., Liu, J., Zhou, S., et al. (2022). Learning a coordinated network for detail-refinement multiexposure image fusion. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 713\u2013727.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1952_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, J., & Liu, J., et\u00a0al. (2023a). Learning a graph neural network with cross modality interaction for image fusion. In ACM MM.","DOI":"10.1145\/3581783.3612135"},{"key":"1952_CR28","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, J., & Zhou, S., et\u00a0al. (2023b). Gesenet: A general semantic-guided network with couple mask ensemble for medical image fusion. IEEE Transactions on Neural Networks and Learning Systems.","DOI":"10.1109\/TNNLS.2023.3293274"},{"issue":"7","key":"1952_CR29","first-page":"2864","volume":"22","author":"S Li","year":"2013","unstructured":"Li, S., Kang, X., & Hu, J. (2013). Image fusion with guided filtering. IEEE TIP, 22(7), 2864\u20132875.","journal-title":"IEEE TIP"},{"issue":"4","key":"1952_CR30","first-page":"1172","volume":"66","author":"W Li","year":"2018","unstructured":"Li, W., Du, J., Zhao, Z., et al. (2018). Fusion of medical sensors using adaptive cloud model in local laplacian pyramid domain. IEEE TBE, 66(4), 1172\u20131183.","journal-title":"IEEE TBE"},{"key":"1952_CR31","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., & Wu, J., et\u00a0al. (2019). Expectation-maximization attention networks for semantic segmentation. In ICCV (pp. 9167\u20139176).","DOI":"10.1109\/ICCV.2019.00926"},{"issue":"8","key":"1952_CR32","first-page":"45","volume":"11","author":"Y Li","year":"2005","unstructured":"Li, Y., & Chi, Z. (2005). MR brain image segmentation based on self-organizing map network. International Journal of Information Technology, 11(8), 45\u201353.","journal-title":"International Journal of Information Technology"},{"key":"1952_CR33","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., & Jiang, J., et\u00a0al. (2021a). Learning a deep multi-scale feature ensemble and an edge-attention guidance for image fusion. In IEEE TCSVT.","DOI":"10.1109\/TCSVT.2021.3056725"},{"key":"1952_CR34","doi-asserted-by":"crossref","unstructured":"Liu, J., Shang, J., & Liu, R., et\u00a0al. (2021b). Halder: Hierarchical attention-guided learning with detail-refinement for multi-exposure image fusion. In ICME. IEEE (pp. 1\u20136).","DOI":"10.1109\/ICME51207.2021.9428192"},{"key":"1952_CR35","doi-asserted-by":"crossref","first-page":"1818","DOI":"10.1109\/LSP.2021.3109818","volume":"28","author":"J Liu","year":"2021","unstructured":"Liu, J., Wu, Y., Huang, Z., et al. (2021). SMOA: Searching a modality-oriented architecture for infrared and visible image fusion. IEEE Signal Processing Letters, 28, 1818\u20131822.","journal-title":"IEEE Signal Processing Letters"},{"key":"1952_CR36","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., & Huang, Z., et\u00a0al. (2022a). Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5802\u20135811).","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"1952_CR37","unstructured":"Liu, J., Jiang, Z., & Wu, G., et\u00a0al. (2022b). A unified image fusion framework with flexible bilevel paradigm integration. The Visual Computer 1\u201318."},{"issue":"8","key":"1952_CR38","doi-asserted-by":"crossref","first-page":"5026","DOI":"10.1109\/TCSVT.2022.3144455","volume":"32","author":"J Liu","year":"2022","unstructured":"Liu, J., Shang, J., Liu, R., et al. (2022). Attention-guided global-local adversarial learning for detail-preserving multi-exposure image fusion. IEEE Transactions on Circuits and Systems for Video Technology, 32(8), 5026\u20135040.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1952_CR39","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., & Wu, G., et\u00a0al. (2023a). Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8115\u20138124).","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"1952_CR40","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.inffus.2023.02.027","volume":"95","author":"J Liu","year":"2023","unstructured":"Liu, J., Wu, G., Luan, J., et al. (2023). Holoco: Holistic and local contrastive learning network for multi-exposure image fusion. Information Fusion, 95, 237\u2013249.","journal-title":"Information Fusion"},{"key":"1952_CR41","first-page":"723","volume":"2020","author":"R Liu","year":"2020","unstructured":"Liu, R., Li, Z., Zhang, Y., et al. (2020). Bi-level probabilistic feature learning for deformable image registration. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI, 2020, 723\u2013730.","journal-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI"},{"key":"1952_CR42","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1109\/TIP.2020.3043125","volume":"30","author":"R Liu","year":"2021","unstructured":"Liu, R., Liu, J., Jiang, Z., et al. (2021). A bilevel integrated model with data-driven layer ensemble for multi-modality image fusion. IEEE TIP, 30, 1261\u20131274. https:\/\/doi.org\/10.1109\/TIP.2020.3043125","journal-title":"IEEE TIP"},{"key":"1952_CR43","doi-asserted-by":"crossref","unstructured":"Liu, R., Ma, L., & Zhang, J., et\u00a0al. (2021). Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10,561\u201310,570).","DOI":"10.1109\/CVPR46437.2021.01042"},{"key":"1952_CR44","doi-asserted-by":"crossref","first-page":"4922","DOI":"10.1109\/TIP.2022.3190209","volume":"31","author":"R Liu","year":"2022","unstructured":"Liu, R., Jiang, Z., Yang, S., et al. (2022). Twin adversarial contrastive learning for underwater image enhancement and beyond. IEEE Transactions on Image Processing, 31, 4922\u20134936.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"11","key":"1952_CR45","doi-asserted-by":"crossref","first-page":"7688","DOI":"10.1109\/TPAMI.2021.3115825","volume":"44","author":"R Liu","year":"2022","unstructured":"Liu, R., Li, Z., Fan, X., et al. (2022). Learning deformable image registration from optimization: Perspective, modules, bilevel training and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 7688\u20137704.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"1952_CR46","first-page":"5953","volume":"45","author":"R Liu","year":"2022","unstructured":"Liu, R., Ma, L., Ma, T., et al. (2022). Learning with nested scene modeling and cooperative architecture search for low-light vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5953\u20135969.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5","key":"1952_CR47","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1049\/iet-ipr.2014.0311","volume":"9","author":"Y Liu","year":"2015","unstructured":"Liu, Y., & Wang, Z. (2015). Simultaneous image fusion and denoising with adaptive sparse representation. IET Image Processing, 9(5), 347\u2013357.","journal-title":"IET Image Processing"},{"key":"1952_CR48","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.inffus.2014.09.004","volume":"24","author":"Y Liu","year":"2015","unstructured":"Liu, Y., Liu, S., & Wang, Z. (2015). A general framework for image fusion based on multi-scale transform and sparse representation. Information Fusion, 24, 147\u2013164.","journal-title":"Information Fusion"},{"issue":"3","key":"1952_CR49","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/LSP.2019.2895749","volume":"26","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Chen, X., Ward, R. K., et al. (2019). Medical image fusion via convolutional sparsity based morphological component analysis. IEEE Signal Processing Letters, 26(3), 485\u2013489.","journal-title":"IEEE Signal Processing Letters"},{"key":"1952_CR50","doi-asserted-by":"crossref","unstructured":"Liu, Z., Liu, J., & Wu, G., et\u00a0al. (2023c). Bi-level dynamic learning for jointly multi-modality image fusion and beyond. In IJCAI.","DOI":"10.24963\/ijcai.2023\/138"},{"key":"1952_CR51","doi-asserted-by":"crossref","unstructured":"Liu, Z., Liu, J., & Zhang, B., et\u00a0al. (2023d). PAIF: Perception-aware infrared-visible image fusion for attack-tolerant semantic segmentation. In ACM MM.","DOI":"10.1145\/3581783.3611928"},{"key":"1952_CR52","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1016\/j.infrared.2014.09.007","volume":"67","author":"X Lu","year":"2014","unstructured":"Lu, X., Zhang, B., Zhao, Y., et al. (2014). The infrared and visible image fusion algorithm based on target separation and sparse representation. Infrared Physics & Technology, 67, 397\u2013407.","journal-title":"Infrared Physics & Technology"},{"key":"1952_CR53","unstructured":"Lv, F., Li, Y., & Lu, F. (2019). Attention guided low-light image enhancement with a large scale low-light simulation dataset. arXiv preprint arXiv:1908.00682."},{"key":"1952_CR54","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.inffus.2016.02.001","volume":"31","author":"J Ma","year":"2016","unstructured":"Ma, J., Chen, C., Li, C., et al. (2016). Infrared and visible image fusion via gradient transfer and total variation minimization. Information Fusion, 31, 100\u2013109.","journal-title":"Information Fusion"},{"key":"1952_CR55","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.infrared.2017.02.005","volume":"82","author":"J Ma","year":"2017","unstructured":"Ma, J., Zhou, Z., Wang, B., et al. (2017). Infrared and visible image fusion based on visual saliency map and weighted least square optimization. Infrared Physics & Technology, 82, 8\u201317.","journal-title":"Infrared Physics & Technology"},{"key":"1952_CR56","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.inffus.2018.02.004","volume":"45","author":"J Ma","year":"2019","unstructured":"Ma, J., Ma, Y., & Li, C. (2019). Infrared and visible image fusion methods and applications: A survey. Information Fusion, 45, 153\u2013178.","journal-title":"Information Fusion"},{"key":"1952_CR57","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.inffus.2018.09.004","volume":"48","author":"J Ma","year":"2019","unstructured":"Ma, J., Yu, W., Liang, P., et al. (2019). Fusiongan: A generative adversarial network for infrared and visible image fusion. Information Fusion, 48, 11\u201326.","journal-title":"Information Fusion"},{"key":"1952_CR58","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1007\/s11263-018-1117-z","volume":"127","author":"J Ma","year":"2019","unstructured":"Ma, J., Zhao, J., Jiang, J., et al. (2019). Locality preserving matching. International Journal of Computer Vision, 127, 512\u2013531.","journal-title":"International Journal of Computer Vision"},{"key":"1952_CR59","first-page":"4980","volume":"29","author":"J Ma","year":"2020","unstructured":"Ma, J., Xu, H., Jiang, J., et al. (2020). Ddcgan: A dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE TIP, 29, 4980\u20134995.","journal-title":"IEEE TIP"},{"key":"1952_CR60","first-page":"1","volume":"70","author":"J Ma","year":"2020","unstructured":"Ma, J., Zhang, H., Shao, Z., et al. (2020). Ganmcc: A generative adversarial network with multiclassification constraints for infrared and visible image fusion. IEEE TIM, 70, 1\u201314.","journal-title":"IEEE TIM"},{"issue":"7","key":"1952_CR61","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1109\/JAS.2022.105686","volume":"9","author":"J Ma","year":"2022","unstructured":"Ma, J., Tang, L., Fan, F., et al. (2022). Swinfusion: Cross-domain long-range learning for general image fusion via swin transformer. IEEE\/CAA Journal of Automatica Sinica, 9(7), 1200\u20131217.","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"1952_CR62","doi-asserted-by":"crossref","unstructured":"Ma, L., Liu, R., & Wang, Y., et\u00a0al. (2022b). Low-light image enhancement via self-reinforced retinex projection model. IEEE Transactions on Multimedia.","DOI":"10.1109\/TMM.2022.3162493"},{"key":"1952_CR63","doi-asserted-by":"crossref","unstructured":"Ma, L., Ma, T., & Liu, R., et\u00a0al. (2022c). Toward fast, flexible, and robust low-light image enhancement. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5637\u20135646).","DOI":"10.1109\/CVPR52688.2022.00555"},{"key":"1952_CR64","doi-asserted-by":"crossref","unstructured":"Ma, L., Jin, D., & An, N., et\u00a0al. (2023). Bilevel fast scene adaptation for low-light image enhancement. arXiv preprint arXiv:2306.01343.","DOI":"10.1007\/s11263-023-01900-z"},{"key":"1952_CR65","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1016\/j.compeleceng.2016.09.019","volume":"62","author":"F Meng","year":"2017","unstructured":"Meng, F., Song, M., Guo, B., et al. (2017). Image fusion based on object region detection and non-subsampled contourlet transform. Computers & Electrical Engineering, 62, 375\u2013383.","journal-title":"Computers & Electrical Engineering"},{"issue":"3","key":"1952_CR66","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.imavis.2009.06.006","volume":"28","author":"S Montabone","year":"2010","unstructured":"Montabone, S., & Soto, A. (2010). Human detection using a mobile platform and novel features derived from a visual saliency mechanism. Image and Vision Computing, 28(3), 391\u2013402.","journal-title":"Image and Vision Computing"},{"key":"1952_CR67","unstructured":"Nguyen, T., Dax, M., & Mummadi, C. K., et\u00a0al. (2019). Deepusps: Deep robust unsupervised saliency prediction via self-supervision. Advances in Neural Information Processing Systems 32."},{"key":"1952_CR68","doi-asserted-by":"crossref","unstructured":"Parikh, A. P., T\u00e4ckstr\u00f6m, O., & Das, D., et\u00a0al. (2016). A decomposable attention model for natural language inference. arXiv preprint arXiv:1606.01933.","DOI":"10.18653\/v1\/D16-1244"},{"issue":"2","key":"1952_CR69","first-page":"228","volume":"13","author":"VS Petrovic","year":"2004","unstructured":"Petrovic, V. S., & Xydeas, C. S. (2004). Gradient-based multiresolution image fusion. IEEE TIP, 13(2), 228\u2013237.","journal-title":"IEEE TIP"},{"key":"1952_CR70","doi-asserted-by":"crossref","unstructured":"Pu, M., Huang, Y., & Guan, Q., et\u00a0al. (2018). Graphnet: Learning image pseudo annotations for weakly-supervised semantic segmentation. In ACM MM, ACM (pp. 483\u2013491).","DOI":"10.1145\/3240508.3240542"},{"issue":"1","key":"1952_CR71","first-page":"1","volume":"2","author":"WJ Roberts","year":"2008","unstructured":"Roberts, W. J., Van, J. A. A., & Ahmed, F. (2008). Assessment of image fusion procedures using entropy, image quality, and multispectral classification. Journal of Applied Remote Sensing, 2(1), 1\u201328.","journal-title":"Journal of Applied Remote Sensing"},{"key":"1952_CR72","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"issue":"12","key":"1952_CR73","doi-asserted-by":"crossref","first-page":"2121","DOI":"10.1109\/JAS.2022.106082","volume":"9","author":"L Tang","year":"2022","unstructured":"Tang, L., Deng, Y., Ma, Y., et al. (2022). Superfusion: A versatile image registration and fusion network with semantic awareness. IEEE\/CAA Journal of Automatica Sinica, 9(12), 2121\u20132137.","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"issue":"4","key":"1952_CR74","first-page":"309","volume":"1","author":"TM Tu","year":"2004","unstructured":"Tu, T. M., Huang, P. S., Hung, C. L., et al. (2004). A fast intensity-hue-saturation fusion technique with spectral adjustment for Ikonos imagery. IEEE GRSLS, 1(4), 309\u2013312.","journal-title":"IEEE GRSLS"},{"key":"1952_CR75","unstructured":"Vaswani, A., Shazeer, N., & Parmar, N., et\u00a0al. (2017a). Attention is all you need. Advances in Neural Information Processing Systems 30."},{"key":"1952_CR76","unstructured":"Vaswani, A., Shazeer, N., & Parmar, N., et\u00a0al. (2017b). Attention is all you need. In Advances in neural information processing systems (pp. 5998\u20136008)."},{"key":"1952_CR77","doi-asserted-by":"crossref","unstructured":"VS, V., Valanarasu, J. M. J., & Oza, P., et\u00a0al. (2021). Image fusion transformer. arXiv preprint arXiv:2107.09011.","DOI":"10.1109\/ICIP46576.2022.9897280"},{"key":"1952_CR78","doi-asserted-by":"crossref","unstructured":"Wang, D., Liu, J., & Fan, X., et\u00a0al. (2022). Unsupervised misaligned infrared and visible image fusion via cross-modality image generation and registration. arXiv preprint arXiv:2205.11876.","DOI":"10.24963\/ijcai.2022\/487"},{"issue":"101","key":"1952_CR79","first-page":"828","volume":"98","author":"D Wang","year":"2023","unstructured":"Wang, D., Liu, J., Liu, R., et al. (2023). An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection. Information Fusion, 98(101), 828.","journal-title":"Information Fusion"},{"issue":"4","key":"1952_CR80","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R., et al. (2004). Image quality assessment: From error visibility to structural similarity. IEEE TIP, 13(4), 600\u2013612.","journal-title":"IEEE TIP"},{"issue":"2","key":"1952_CR81","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1038\/nmat4771","volume":"16","author":"MH Wong","year":"2017","unstructured":"Wong, M. H., Giraldo, J. P., Kwak, S. Y., et al. (2017). Nitroaromatic detection and infrared communication from wild-type plants using plant nanobionics. Nature Materials, 16(2), 264\u2013271.","journal-title":"Nature Materials"},{"key":"1952_CR82","doi-asserted-by":"crossref","unstructured":"Wu, H., Qu, Y., & Lin, S., et\u00a0al. (2021). Contrastive learning for compact single image dehazing. In IEEE\/CVF CVPR (pp. 10,551\u201310,560).","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"1952_CR83","doi-asserted-by":"crossref","unstructured":"Xie, E., Ding, J., & Wang, W., et\u00a0al. (2021a). Detco: Unsupervised contrastive learning for object detection. In ICCV (pp. 8392\u20138401).","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"1952_CR84","unstructured":"Xie, E., Wang, W., & Yu, Z., et\u00a0al. (2021b). Segformer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems 34, 12,077\u201312,090."},{"key":"1952_CR85","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.inffus.2021.06.001","volume":"76","author":"H Xu","year":"2021","unstructured":"Xu, H., & Ma, J. (2021). Emfusion: An unsupervised enhanced medical image fusion network. Information Fusion, 76, 177\u2013186.","journal-title":"Information Fusion"},{"key":"1952_CR86","doi-asserted-by":"crossref","unstructured":"Xu, H., Liang, P., & Yu, W., et\u00a0al. (2019). Learning a generative model for fusing infrared and visible images via conditional generative adversarial network with dual discriminators. In IJCAI-19 (pp. 3954\u20133960).","DOI":"10.24963\/ijcai.2019\/549"},{"key":"1952_CR87","unstructured":"Xu, H., Ma, J., & Jiang, J., et\u00a0al. (2020). U2fusion: A unified unsupervised image fusion network. In IEEE TPAMI."},{"issue":"9","key":"1952_CR88","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1364\/JOSAA.32.001643","volume":"32","author":"X Yan","year":"2015","unstructured":"Yan, X., Qin, H., Li, J., et al. (2015). Infrared and visible image fusion with spectral graph wavelet transform. JOSA A, 32(9), 1643\u20131652.","journal-title":"JOSA A"},{"issue":"1","key":"1952_CR89","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.neucom.2008.02.025","volume":"72","author":"L Yang","year":"2008","unstructured":"Yang, L., Guo, B. L., & Ni, W. (2008). Multimodality medical image fusion based on multiscale geometric analysis of contourlet transform. Neurocomputing, 72(1), 203\u2013211.","journal-title":"Neurocomputing"},{"key":"1952_CR90","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.neucom.2016.11.051","volume":"226","author":"M Yin","year":"2017","unstructured":"Yin, M., Duan, P., Liu, W., et al. (2017). A novel infrared and visible image fusion algorithm based on shift-invariant dual-tree complex shearlet transform and sparse representation. Neurocomputing, 226, 182\u2013191.","journal-title":"Neurocomputing"},{"issue":"10","key":"1952_CR91","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.1007\/s11263-021-01501-8","volume":"129","author":"H Zhang","year":"2021","unstructured":"Zhang, H., & Ma, J. (2021). Sdnet: A versatile squeeze-and-decomposition network for real-time image fusion. International Journal of Computer Vision, 129(10), 2761\u20132785.","journal-title":"International Journal of Computer Vision"},{"key":"1952_CR92","unstructured":"Zhang, H., Xu, H., & Xiao, Y., et\u00a0al. (2020a). Rethinking the image fusion: A fast unified image fusion network based on proportional maintenance of gradient and intensity. In AAAI (pp. 12,797\u201312,804)."},{"key":"1952_CR93","unstructured":"Zhang, J., Lu, S., & Zhan, F., et\u00a0al. (2021a). Blind image super-resolution via contrastive representation learning. arXiv preprint arXiv:2107.00708."},{"key":"1952_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Fu, Y., & Li, H., et\u00a0al. (2013). Dictionary learning method for joint sparse representation-based image fusion. Optical Engineering 52(5), 057,006\u20131\u2013057,006\u201311.","DOI":"10.1117\/1.OE.52.5.057006"},{"key":"1952_CR95","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.inffus.2017.05.006","volume":"40","author":"Q Zhang","year":"2018","unstructured":"Zhang, Q., Liu, Y., Blum, R. S., et al. (2018). Sparse representation based multi-sensor image fusion for multi-focus and multi-modality images: A review. Information Fusion, 40, 57\u201375.","journal-title":"Information Fusion"},{"key":"1952_CR96","unstructured":"Zhang, Y., Li, K., & Li, K., et\u00a0al. (2019). Residual non-local attention networks for image restoration. arXiv preprint arXiv:1903.10082."},{"key":"1952_CR97","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Liu, Y., Sun, P., et al. (2020). Ifcnn: A general image fusion framework based on convolutional neural network. Information Fusion, 54, 99\u2013118. https:\/\/doi.org\/10.1016\/j.inffus.2019.07.011","DOI":"10.1016\/j.inffus.2019.07.011"},{"key":"1952_CR98","first-page":"1949","volume":"30","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Lin, Z., Xu, J., et al. (2021). Bilateral attention network for RGB-D salient object detection. IEEE TIP, 30, 1949\u20131961.","journal-title":"IEEE TIP"},{"issue":"4","key":"1952_CR99","first-page":"866","volume":"20","author":"W Zhao","year":"2018","unstructured":"Zhao, W., Lu, H., & Wang, D. (2018). Multisensor image fusion and enhancement in spectral total variation domain. IEEE TMM, 20(4), 866\u2013879.","journal-title":"IEEE TMM"},{"key":"1952_CR100","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Xu, S., & Zhang, C., et\u00a0al. (2020a). Didfuse: Deep image decomposition for infrared and visible image fusion. arXiv preprint arXiv:2003.09210.","DOI":"10.24963\/ijcai.2020\/135"},{"key":"1952_CR101","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Xu, S., Zhang, C., et al. (2020). Bayesian fusion for infrared and visible images. Signal Processing, 177(107), 734.","DOI":"10.1016\/j.sigpro.2020.107734"},{"key":"1952_CR102","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., & Zhang, J., et\u00a0al. (2023a). Cddfuse: Correlation-driven dual-branch feature decomposition for multi-modality image fusion. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5906\u20135916).","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"1952_CR103","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., & Zhu, Y., et\u00a0al. (2023b). DDFM: Denoising diffusion model for multi-modality image fusion. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00742"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01952-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01952-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01952-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T08:17:52Z","timestamp":1715069872000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01952-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,8]]},"references-count":103,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["1952"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01952-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,8]]},"assertion":[{"value":"5 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}