{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:06:06Z","timestamp":1774937166480,"version":"3.50.1"},"reference-count":97,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00371-024-03423-1","type":"journal-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T09:02:28Z","timestamp":1716973348000},"page":"1335-1350","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["SimpliFusion: a simplified infrared and visible image fusion network"],"prefix":"10.1007","volume":"41","author":[{"given":"Yong","family":"Liu","sequence":"first","affiliation":[]},{"given":"Xingyuan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"3423_CR1","first-page":"1","volume":"40","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Xia, R., Yang, K., Zou, K.: MFFN: image super-resolution via multi-level features fusion network. Vis. Comput. 40, 1\u201316 (2023)","journal-title":"Vis. Comput."},{"key":"3423_CR2","first-page":"1","volume":"38","author":"K Bayoudh","year":"2021","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis. Comput. 38, 1\u201332 (2021)","journal-title":"Vis. Comput."},{"issue":"1","key":"3423_CR3","first-page":"502","volume":"44","author":"X Han","year":"2020","unstructured":"Han, X., Ma, J., Jiang, J., Guo, X., Ling, H.: U2fusion: a unified unsupervised image fusion network. IEEE Trans. Pattern Anal. Mach. Intell. 44(1), 502\u2013518 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3423_CR4","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.: A general framework for image fusion based on multi-scale transform and sparse representation. Inf. Fusion 24, 147\u2013164 (2015)","journal-title":"Inf. Fusion"},{"key":"3423_CR5","first-page":"12797","volume":"34","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Han, X., Xiao, Y., Guo, X., Ma, J.: Rethinking the image fusion: a fast unified image fusion network based on proportional maintenance of gradient and intensity. Proc. AAAI Conf. Artif. Intell. 34, 12797\u201312804 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"3423_CR6","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., Huang, J.: Infrared and visible image fusion via gradient transfer and total variation minimization. Inf. Fusion 31, 100\u2013109 (2016)","journal-title":"Inf. Fusion"},{"key":"3423_CR7","doi-asserted-by":"crossref","first-page":"4733","DOI":"10.1109\/TIP.2020.2975984","volume":"29","author":"H Li","year":"2020","unstructured":"Li, H., Xiao-Jun, W., Kittler, J.: MDLatLRR: a novel decomposition method for infrared and visible image fusion. IEEE Trans. Image Process. 29, 4733\u20134746 (2020)","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"3423_CR8","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1109\/TMM.2017.2760100","volume":"20","author":"W Zhao","year":"2017","unstructured":"Zhao, W., Huimin, L., Wang, D.: Multisensor image fusion and enhancement in spectral total variation domain. IEEE Trans. Multimed. 20(4), 866\u2013879 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"3423_CR9","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.inffus.2019.07.011","volume":"54","author":"Z Yu","year":"2020","unstructured":"Yu, Z., Yu, L., Peng, S., Yan, H., Zhao, X., Zhang, L.: IFCNN: a general image fusion framework based on convolutional neural network. Inf. Fusion 54, 99\u2013118 (2020)","journal-title":"Inf. Fusion"},{"key":"3423_CR10","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.inffus.2021.06.002","volume":"76","author":"F Zhao","year":"2021","unstructured":"Zhao, F., Zhao, W., Yao, L., Liu, Y.: Self-supervised feature adaption for infrared and visible image fusion. Inf. Fusion 76, 189\u2013203 (2021)","journal-title":"Inf. Fusion"},{"issue":"5","key":"3423_CR11","doi-asserted-by":"crossref","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2018","unstructured":"Li, H., Xiao-Jun, W.: Densefuse: a fusion approach to infrared and visible images. IEEE Trans. Image Process. 28(5), 2614\u20132623 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"3423_CR12","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TCI.2021.3100986","volume":"7","author":"X Han","year":"2021","unstructured":"Han, X., Zhang, H., Ma, J.: Classification saliency-based rule for visible and infrared image fusion. IEEE Trans. Comput. Imaging 7, 824\u2013836 (2021)","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"3423_CR13","doi-asserted-by":"crossref","unstructured":"Ma, J., Han, X., Jiang, J., Mei, X., Zhang, X.-P.: DDCGAN: a dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE Trans. Image Process. 29, 4980\u20134995 (2020)","DOI":"10.1109\/TIP.2020.2977573"},{"key":"3423_CR14","doi-asserted-by":"crossref","first-page":"7203","DOI":"10.1109\/TIP.2020.2999855","volume":"29","author":"X Han","year":"2020","unstructured":"Han, X., Ma, J., Zhang, X.-P.: MEF-GAN: multi-exposure image fusion via generative adversarial networks. IEEE Trans. Image Process. 29, 7203\u20137216 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"3423_CR15","doi-asserted-by":"crossref","first-page":"55145","DOI":"10.1109\/ACCESS.2020.2982016","volume":"8","author":"H Jun","year":"2020","unstructured":"Jun, H., Le, Z., Ma, Y., Fan, F., Zhang, H., Yang, L.: MGMDCGAN: medical image fusion using multi-generator multi-discriminator conditional generative adversarial network. IEEE Access 8, 55145\u201355157 (2020)","journal-title":"IEEE Access"},{"key":"3423_CR16","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.ins.2019.08.066","volume":"508","author":"J Chen","year":"2020","unstructured":"Chen, J., Li, X., Luo, L., Mei, X., Ma, J.: Infrared and visible image fusion based on target-enhanced multiscale transform decomposition. Inf. Sci. 508, 64\u201378 (2020)","journal-title":"Inf. Sci."},{"key":"3423_CR17","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, (2017)"},{"key":"3423_CR18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, (2020)"},{"key":"3423_CR19","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer, (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3423_CR20","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H.S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890, (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"3423_CR21","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., Gao, W.: Pre-trained image processing transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299\u201312310, (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"3423_CR22","first-page":"2126","volume":"36","author":"Q Linhao","year":"2022","unstructured":"Linhao, Q., Liu, S., Wang, M., Song, Z.: Transmef: a transformer-based multi-exposure image fusion framework using self-supervised multi-task learning. Proc. AAAI Conf. Artif. Intell. 36, 2126\u20132134 (2022)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"3423_CR23","doi-asserted-by":"crossref","unstructured":"Vs, V., Valanarasu, J.M.J., Oza, P., Patel, V.M.: Image fusion transformer. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 3566\u20133570. IEEE, (2022)","DOI":"10.1109\/ICIP46576.2022.9897280"},{"key":"3423_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273451","author":"D Rao","year":"2023","unstructured":"Rao, D., Xu, T., Wu, X.-J.: TGFuse: An infrared and visible image fusion approach based on transformer and generative adversarial network. IEEE Trans. Image Process. (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3273451","journal-title":"IEEE Trans. Image Process."},{"key":"3423_CR25","unstructured":"Fu, Y., Xu, T.Y., Wu, X.J., Kittler, J.: Ppt fusion: pyramid patch transformerfor a case study in image fusion. arXiv preprint arXiv:2107.13967, (2021)"},{"key":"3423_CR26","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Yang, Q., Sheng, B.: Deep colorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 415\u2013423, (2015)","DOI":"10.1109\/ICCV.2015.55"},{"key":"3423_CR27","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.neucom.2018.09.018","volume":"320","author":"K He","year":"2018","unstructured":"He, K., Zhou, D., Zhang, X., Nie, R.: Multi-focus: focused region finding and multi-scale transform for image fusion. Neurocomputing 320, 157\u2013170 (2018)","journal-title":"Neurocomputing"},{"issue":"1","key":"3423_CR28","doi-asserted-by":"crossref","first-page":"2041","DOI":"10.3390\/s150102041","volume":"15","author":"W Huang","year":"2015","unstructured":"Huang, W., Xiao, L., Liu, H., Wei, Z.: Hyperspectral imagery super-resolution by compressive sensing inspired dictionary learning and spatial-spectral regularization. Sensors 15(1), 2041\u20132058 (2015)","journal-title":"Sensors"},{"key":"3423_CR29","doi-asserted-by":"crossref","first-page":"8823","DOI":"10.1109\/JSTARS.2021.3108233","volume":"14","author":"X Honghui","year":"2021","unstructured":"Honghui, X., Qin, M., Chen, S., Zheng, Y., Zheng, J.: Hyperspectral-multispectral image fusion via tensor ring and subspace decompositions. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14, 8823\u20138837 (2021)","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"3423_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2015.10.080","volume":"177","author":"F Meng","year":"2016","unstructured":"Meng, F., Guo, B., Song, M., Zhang, X.: Image fusion with saliency map and interest points. Neurocomputing 177, 1\u20138 (2016)","journal-title":"Neurocomputing"},{"key":"3423_CR31","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1007\/s11517-020-02136-6","volume":"58","author":"SP Yadav","year":"2020","unstructured":"Yadav, S.P., Yadav, S.: Image fusion using hybrid methods in multimodality medical images. Med. Biol. Eng. Comput. 58, 669\u2013687 (2020)","journal-title":"Med. Biol. Eng. Comput."},{"issue":"10","key":"3423_CR32","doi-asserted-by":"crossref","first-page":"3089","DOI":"10.1109\/TIP.2006.877507","volume":"15","author":"AL Da Cunha","year":"2006","unstructured":"Da Cunha, A.L., Zhou, J., Minh Do, N.: The nonsubsampled contourlet transform: theory, design, and applications. IEEE Trans. Image Process. 15(10), 3089\u20133101 (2006)","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"3423_CR33","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1109\/TMM.2013.2244870","volume":"15","author":"QM Gaurav Bhatnagar","year":"2013","unstructured":"Gaurav Bhatnagar, Q.M., Jonathan, W., Liu, Z.: Directive contrast based multimodal medical image fusion in NSCT domain. IEEE Trans. Multimed. 15(5), 1014\u20131024 (2013)","journal-title":"IEEE Trans. Multimed."},{"key":"3423_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Yao, L., Song, R., Xie, H.: A new infrared and visible image fusion algorithm in NSCT domain. In: ICIC, pp 420\u2013431. Springer, (2017)","DOI":"10.1007\/978-3-319-63309-1_39"},{"issue":"12","key":"3423_CR35","doi-asserted-by":"crossref","first-page":"2706","DOI":"10.1109\/TMM.2017.2711422","volume":"19","author":"H Hai-Miao","year":"2017","unstructured":"Hai-Miao, H., Jiawei, W., Li, B., Guo, Q., Zheng, J.: An adaptive fusion algorithm for visible and infrared videos based on entropy and the cumulative distribution of gray levels. IEEE Trans. Multimed. 19(12), 2706\u20132719 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"3423_CR36","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.inffus.2017.05.006","volume":"40","author":"Qiang Zhang","year":"2018","unstructured":"Zhang, Qiang, Liu, Yi., Blum, Rick S., Han, Jungong, Tao, Dacheng: Sparse representation based multi-sensor image fusion for multi-focus and multi-modality images: a review. Inf. Fusion 40, 57\u201375 (2018)","journal-title":"Inf. Fusion"},{"issue":"04","key":"3423_CR37","doi-asserted-by":"crossref","first-page":"1650024","DOI":"10.1142\/S0219691316500247","volume":"14","author":"Yang Bin","year":"2016","unstructured":"Bin, Yang, Chao, Yang, Guoyu, Huang: Efficient image fusion with approximate sparse representation. Int. J. Wavelets Multiresolut. Inf. Process. 14(04), 1650024 (2016)","journal-title":"Int. J. Wavelets Multiresolut. Inf. Process."},{"issue":"12","key":"3423_CR38","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.1109\/LSP.2016.2618776","volume":"23","author":"Yu Liu","year":"2016","unstructured":"Liu, Yu., Chen, Xun, Ward, Rabab K., Jane Wang, Z.: Image fusion with convolutional sparse representation. IEEE Signal Process. Lett. 23(12), 1882\u20131886 (2016)","journal-title":"IEEE Signal Process. Lett."},{"issue":"11","key":"3423_CR39","doi-asserted-by":"crossref","first-page":"7646","DOI":"10.1109\/TCSVT.2022.3184840","volume":"32","author":"Guibiao Liao","year":"2022","unstructured":"Liao, Guibiao, Gao, Wei, Li, Ge., Wang, Junle, Kwong, Sam: Cross-collaborative fusion-encoder network for robust RGB-thermal salient object detection. IEEE Trans. Circuits Syst. Video Technol. 32(11), 7646\u20137661 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3423_CR40","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.infrared.2015.11.002","volume":"74","author":"He Li","year":"2016","unstructured":"Li, He., Liu, Lei, Huang, Wei, Yue, Chao: An improved fusion algorithm for infrared and visible images based on multi-scale transform. Infrared Phys. Technol. 74, 28\u201337 (2016)","journal-title":"Infrared Phys. Technol."},{"key":"3423_CR41","doi-asserted-by":"crossref","unstructured":"Bavirisetti, D. P., Xiao, G., Liu, G.: Multi-sensor image fusion based on fourth order partial differential equations. In: 2017 20th International Conference on Information Fusion (Fusion), pp. 1\u20139. IEEE, (2017)","DOI":"10.23919\/ICIF.2017.8009719"},{"issue":"5","key":"3423_CR42","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1109\/JSEN.2007.894926","volume":"7","author":"N Cvejic","year":"2007","unstructured":"Cvejic, N., Bull, D., Canagarajah, N.: Region-based multimodal image fusion using ICA bases. IEEE Sens. J. 7(5), 743\u2013751 (2007)","journal-title":"IEEE Sens. J."},{"key":"3423_CR43","first-page":"1046","volume":"2","author":"J Mou","year":"2013","unstructured":"Mou, J., Gao, W., Song, Z.: Image fusion based on non-negative matrix factorization and infrared feature extraction. CISP 2, 1046\u20131050 (2013)","journal-title":"CISP"},{"key":"3423_CR44","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.infrared.2017.04.018","volume":"83","author":"CH Liu","year":"2017","unstructured":"Liu, C.H., Qi, Y., Ding, W.R.: Infrared and visible image fusion method based on saliency detection in sparse domain. Infrared Phys. Technol. 83, 94\u2013102 (2017)","journal-title":"Infrared Phys. Technol."},{"issue":"12","key":"3423_CR45","first-page":"1508","volume":"34","author":"Qu Xiao-Bo","year":"2008","unstructured":"Xiao-Bo, Qu., Jing-Wen, Yan, Hong-Zhi, X.I.A.O., Zi-Qian, Zhu: Image fusion algorithm based on spatial frequency-motivated pulse coupled neural networks in nonsubsampled contourlet transform domain. Acta Autom. Sin. 34(12), 1508\u20131514 (2008)","journal-title":"Acta Autom. Sin."},{"key":"3423_CR46","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.infrared.2015.07.003","volume":"72","author":"Wei Gan","year":"2015","unstructured":"Gan, Wei, Xiaohong, Wu., Wei, Wu., Yang, Xiaomin, Ren, Chao, He, Xiaohai, Liu, Kai: Infrared and visible image fusion with the use of multi-scale edge-preserving decomposition and guided image filter. Infrared Phys. Technol. 72, 37\u201351 (2015)","journal-title":"Infrared Phys. Technol."},{"key":"3423_CR47","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: unsupervised video object segmentation with co-attention siamese networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3623\u20133632 (2019)","DOI":"10.1109\/CVPR.2019.00374"},{"key":"3423_CR48","unstructured":"Qin, Z., Han, C., Wang, Q., Nie, X., Yin, Y., Xiankai, L.: Unified 3D segmenter as prototypical classifiers. Adv. Neural Inf. Process. Syst. 36, (2024)"},{"key":"3423_CR49","doi-asserted-by":"crossref","unstructured":"Wu, P., Lu, X., Shen, J., Yin, Y.: Clip fusion with bi-level optimization for human mesh reconstruction from monocular videos. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 105\u2013115, (2023)","DOI":"10.1145\/3581783.3611978"},{"key":"3423_CR50","first-page":"2110","volume":"37","author":"Z Qin","year":"2023","unstructured":"Qin, Z., Xiankai, L., Nie, X., Yin, Y., Shen, J.: Exposing the self-supervised space-time correspondence learning via graph kernels. Proc. AAAI Conf. Artif. Intell. 37, 2110\u20132118 (2023)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"11","key":"3423_CR51","first-page":"7885","volume":"44","author":"L Xiankai","year":"2021","unstructured":"Xiankai, L., Wang, W., Shen, J., Crandall, D.J., Van Gool, L.: Segmenting objects from relational visual data. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7885\u20137897 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"3423_CR52","doi-asserted-by":"crossref","first-page":"6662","DOI":"10.1109\/TCYB.2021.3079311","volume":"52","author":"Bin Sheng","year":"2021","unstructured":"Sheng, Bin, Li, Ping, Ali, Riaz, Philip Chen, C.L.: Improving video temporal consistency via broad learning system. IEEE Trans. Cybern. 52(7), 6662\u20136675 (2021)","journal-title":"IEEE Trans. Cybern."},{"issue":"1","key":"3423_CR53","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1109\/TII.2021.3085669","volume":"18","author":"J Li","year":"2021","unstructured":"Li, J., Chen, J., Sheng, B., Li, P., Yang, P., Feng, D.D., Qi, J.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Ind. Inform. 18(1), 163\u2013173 (2021)","journal-title":"IEEE Trans. Ind. Inform."},{"key":"3423_CR54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116209","author":"Z Xie","year":"2021","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.L.P.: BaGFN: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. (2021). https:\/\/doi.org\/10.1109\/TNNLS.2021.3116209","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"12","key":"3423_CR55","doi-asserted-by":"crossref","first-page":"9645","DOI":"10.1109\/TIM.2020.3005230","volume":"69","author":"H Li","year":"2020","unstructured":"Li, H., Xiao-Jun, W., Durrani, T.: Nestfuse: an infrared and visible image fusion architecture based on nest connection and spatial\/channel attention models. IEEE Trans. Instrum. Meas. 69(12), 9645\u20139656 (2020)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"3423_CR56","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., Xiao-Jun, W., Kittler, J.: Rfn-nest: an end-to-end residual fusion network for infrared and visible images. Inf. Fusion 73, 72\u201386 (2021)","journal-title":"Inf. Fusion"},{"key":"3423_CR57","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.inffus.2022.03.007","volume":"83","author":"L Tang","year":"2022","unstructured":"Tang, L., Yuan, J., Zhang, H., Jiang, X., Ma, J.: Piafusion: a progressive infrared and visible image fusion network based on illumination aware. Inf. Fusion 83, 79\u201392 (2022)","journal-title":"Inf. Fusion"},{"key":"3423_CR58","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., Wei, Y., Liang, P., Li, C., Jiang, J.: Fusiongan: a generative adversarial network for infrared and visible image fusion. Inf. Fusion 48, 11\u201326 (2019)","journal-title":"Inf. Fusion"},{"key":"3423_CR59","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.inffus.2019.07.005","volume":"54","author":"Jiayi Ma","year":"2020","unstructured":"Ma, Jiayi, Liang, Pengwei, Wei, Yu., Chen, Chen, Guo, Xiaojie, Jia, Wu., Jiang, Junjun: Infrared and visible image fusion via detail preserving adversarial learning. Inf. Fusion 54, 85\u201398 (2020)","journal-title":"Inf. Fusion"},{"issue":"1","key":"3423_CR60","first-page":"105","volume":"32","author":"Jinyuan Liu","year":"2021","unstructured":"Liu, Jinyuan, Fan, Xin, Jiang, Ji., Liu, Risheng, Luo, Zhongxuan: Learning a deep multi-scale feature ensemble and an edge-attention guidance for image fusion. IEEE Trans. Circuits Syst. Video Technol. 32(1), 105\u2013119 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3423_CR61","first-page":"1261","volume":"30","author":"Risheng Liu","year":"2020","unstructured":"Liu, Risheng, Liu, Jinyuan, Jiang, Zhiying, Fan, Xin, Luo, Zhongxuan: A bilevel integrated model with data-driven layer ensemble for multi-modality image fusion. IEEE Trans. Image Process. 30, 1261\u20131274 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"3423_CR62","unstructured":"Li, P.: Didfuse: deep image decomposition for infrared and visible image fusion. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 976\u2013976, (2021)"},{"issue":"11","key":"3423_CR63","first-page":"7688","volume":"44","author":"Risheng Liu","year":"2021","unstructured":"Liu, Risheng, Li, Zi., Fan, Xin, Zhao, Chenying, Huang, Hao, Luo, Zhongxuan: Learning deformable image registration from optimization: perspective, modules, bilevel training and beyond. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7688\u20137704 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3423_CR64","doi-asserted-by":"crossref","unstructured":"Liu, R., Liu, Z., Liu, J., Fan, X.: Searching a hierarchically aggregated fusion architecture for fast multi-modality image fusion. In: ACM Multimedia Conference, pp. 1600\u20131608, 2021","DOI":"10.1145\/3474085.3475299"},{"key":"3423_CR65","doi-asserted-by":"crossref","first-page":"1818","DOI":"10.1109\/LSP.2021.3109818","volume":"28","author":"J Liu","year":"2021","unstructured":"Liu, J., Yuhui, W., Huang, Z., Liu, R., Fan, X.: Smoa: searching a modality-oriented architecture for infrared and visible image fusion. IEEE Signal Process. Lett. 28, 1818\u20131822 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"3423_CR66","doi-asserted-by":"crossref","first-page":"1614","DOI":"10.1109\/LSP.2022.3180672","volume":"29","author":"J Liu","year":"2022","unstructured":"Liu, J., Yuhui, W., Guanyao, W., Liu, R., Fan, X.: Learn to search a lightweight architecture for target-aware infrared and visible image fusion. IEEE Signal Process. Lett. 29, 1614\u20131618 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"3423_CR67","first-page":"1","volume":"70","author":"J Ma","year":"2020","unstructured":"Ma, J., Zhang, H., Shao, Z., Liang, P., Han, X.: GANMcC: a generative adversarial network with multiclassification constraints for infrared and visible image fusion. IEEE Trans. Instrum. Meas. 70, 1\u201314 (2020)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"3423_CR68","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1109\/TCI.2021.3119954","volume":"7","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Yuan, J., Tian, X., Ma, J.: GAN-FM: infrared and visible image fusion using GAN with full-scale skip connection and dual Markovian discriminators. IEEE Trans. Comput. Imaging 7, 1134\u20131147 (2021)","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"3423_CR69","first-page":"1","volume":"71","author":"J Li","year":"2022","unstructured":"Li, J., Zhu, J., Li, C., Chen, X., Yang, B.: CGTF: convolution-guided transformer for infrared and visible image fusion. IEEE Trans. Instrum. Meas. 71, 1\u201314 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"3423_CR70","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: IEEE International Conference on Computer Vision, pp. 10012\u201310022, (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"7","key":"3423_CR71","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., Huang, J., Mei, X., Ma, Y.: Swinfusion: cross-domain long-range learning for general image fusion via swin transformer. IEEE\/CAA J. Autom. Sin. 9(7), 1200\u20131217 (2022)","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"3423_CR72","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zhang, Z., Fan, X., Liu, R.: Towards all weather and unobstructed multi-spectral image stitching: algorithm and benchmark. In: ACM International Multimedia Conference, pp. 3783\u20133791, (2022)","DOI":"10.1145\/3503161.3547966"},{"key":"3423_CR73","doi-asserted-by":"crossref","unstructured":"Bian, P., Zheng, Z., Zhang, D., Chen, L., Li, M.: Single image super-resolution via global-context attention networks. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 1794\u20131798. IEEE, (2021)","DOI":"10.1109\/ICIP42928.2021.9506532"},{"key":"3423_CR74","doi-asserted-by":"crossref","unstructured":"Bian, P., Zheng, Z., Zhang, D.: Light-weight multi-channel aggregation network for image super-resolution. In: Pattern Recognition and Computer Vision: 4th Chinese Conference, PRCV 2021, Beijing, China, October 29\u2013November 1, 2021, Proceedings, Part III 4, pp. 287\u2013297. Springer (2021)","DOI":"10.1007\/978-3-030-88010-1_24"},{"key":"3423_CR75","doi-asserted-by":"crossref","unstructured":"Liu, D., Yang, W., Peng, C., Wang, N., Hu, R., Gao, X.: Modality-agnostic augmented multi-collaboration representation for semi-supervised heterogenous face recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4647\u20134656, (2023)","DOI":"10.1145\/3581783.3612355"},{"key":"3423_CR76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304913","author":"D Liu","year":"2023","unstructured":"Liu, D., Zheng, Z., Peng, C., Wang, Y., Wang, N., Gao, X.: Hierarchical forgery classifier on multi-modality face forgery clues. IEEE Trans. Multimed. (2023). https:\/\/doi.org\/10.1109\/TMM.2023.3304913","journal-title":"IEEE Trans. Multimed."},{"issue":"10","key":"3423_CR77","first-page":"5611","volume":"33","author":"Decheng Liu","year":"2021","unstructured":"Liu, Decheng, Gao, Xinbo, Peng, Chunlei, Wang, Nannan, Li, Jie: Heterogeneous face interpretable disentangled representation for joint face recognition and synthesis. IEEE Trans. Neural Netw. Learn. Syst. 33(10), 5611\u20135625 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3423_CR78","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3327666","author":"D Liu","year":"2023","unstructured":"Liu, D., Gao, X., Peng, C., Wang, N., Li, J.: Universal heterogeneous face analysis via multi-domain feature disentanglement. IEEE Trans. Inf. Forensics Secur. (2023). https:\/\/doi.org\/10.1109\/TIFS.2023.3327666","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"3423_CR79","unstructured":"Wang, B., Komatsuzaki, A.: Gpt-j-6b: A 6 billion parameter autoregressive language model (2021)"},{"key":"3423_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, B., Titov, I., Sennrich, R.: Improving deep transformer with depth-scaled initialization and merged attention (2019). arXiv preprint arXiv:1908.11365","DOI":"10.18653\/v1\/D19-1083"},{"key":"3423_CR81","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., et\u00a0al.: Llama: open and efficient foundation language models (2023). arXiv preprint arXiv:2302.13971"},{"key":"3423_CR82","unstructured":"Dong, Y., Cordonnier, J.-B., Loukas, A.: Attention is not all you need: pure attention loses rank doubly exponentially with depth. In: International Conference on Machine Learning, pp. 2793\u20132803. PMLR, (2021)"},{"key":"3423_CR83","first-page":"27198","volume":"35","author":"LAS Noci","year":"2022","unstructured":"Noci, L.A.S., Biggio, L., Orvieto, A., Singh, S.P., Lucchi, A.: Signal propagation in transformers: theoretical perspectives and the role of rank collapse. Adv. Neural Inf. Process. Syst. 35, 27198\u201327211 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3423_CR84","unstructured":"He, B., Martens, J., Zhang, G., Botev, A., Brock, A., Smith, S.L., Teh, Y.W.: Deep Transformers Without Shortcuts: Modifying Self-Attention for Faithful Signal Propagation (2023). arXiv preprint arXiv:2302.10322"},{"key":"3423_CR85","first-page":"19964","volume":"33","author":"S De","year":"2020","unstructured":"De, S., Smith, S.: Batch normalization biases residual blocks towards the identity function in deep networks. Adv. Neural Inf. Process. Syst. 33, 19964\u201319975 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3423_CR86","unstructured":"Noci, L., Li, C., Li, M.B., He, B., Hofmann, T., Maddison, C., Roy, D.M.: The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit (2023). arXiv preprint arXiv:2306.17759"},{"issue":"4","key":"3423_CR87","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"3423_CR88","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., Huang, Z., Wu, G., Liu, R., Zhong, W., Luo, Z.: 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, (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"3423_CR89","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.dib.2017.09.038","volume":"15","author":"A Toet","year":"2017","unstructured":"Toet, A.: The TNO multiband image data collection. Data Brief 15, 249\u2013251 (2017)","journal-title":"Data Brief"},{"key":"3423_CR90","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., Zhang, J., Zhang, Y., Xu, S., Lin, Z., Timofte, R., Van\u00a0Gool, L.: 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, (2023)","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"3423_CR91","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., Zhu, Y., Zhang, J., Xu, S., Zhang, Y., Zhang, K., Meng, D., Timofte, R., Van\u00a0Gool, L.: DDFM: Denoising Diffusion Model for Multi-modality Image Fusion (2023). arXiv preprint arXiv:2303.06840","DOI":"10.1109\/ICCV51070.2023.00742"},{"key":"3423_CR92","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., Wu, G., Ma, L., Liu, R., Zhong, W., Luo, Z., Fan, X.: 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, (2023)","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"3423_CR93","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., Huang, Z., Wu, G., Liu, R., Zhong, W., Luo, Z.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: CVPR, pp 5802\u20135811, (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"issue":"12","key":"3423_CR94","doi-asserted-by":"crossref","first-page":"2959","DOI":"10.1109\/26.477498","volume":"43","author":"AM Eskicioglu","year":"1995","unstructured":"Eskicioglu, A.M., Fisher, P.S.: Image quality measures and their performance. IEEE Trans. Commun. 43(12), 2959\u20132965 (1995)","journal-title":"IEEE Trans. Commun."},{"key":"3423_CR95","doi-asserted-by":"crossref","unstructured":"Roberts, J.W., Van Aardt, J.A., Ahmed, F.B.: Assessment of image fusion procedures using entropy, image quality, and multispectral classification. J. Appl. Remote Sens. 2(1), 023522 (2008)","DOI":"10.1117\/1.2945910"},{"issue":"12","key":"3423_CR96","doi-asserted-by":"crossref","first-page":"1890","DOI":"10.1016\/j.aeue.2015.09.004","volume":"69","author":"V Aslantas","year":"2015","unstructured":"Aslantas, V., Bendes, Emre: A new image quality metric for image fusion: the sum of the correlations of differences. AEU Int. J. Electron. Commun. 69(12), 1890\u20131896 (2015)","journal-title":"AEU Int. J. Electron. Commun."},{"key":"3423_CR97","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., Zhihai, X., Li, Q., Chen, Y.: Detail preserved fusion of visible and infrared images using regional saliency extraction and multi-scale image decomposition. Opt. Commun. 341, 199\u2013209 (2015)","journal-title":"Opt. Commun."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03423-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03423-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03423-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T12:40:02Z","timestamp":1738586402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03423-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":97,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3423"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03423-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,29]]},"assertion":[{"value":"18 April 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled, \u201cSimpliFusion: A Simplified Infrared and Visible Image Fusion Network Based on Transformer Architecture\".","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}