{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:49:31Z","timestamp":1786981771652,"version":"build-2736575974"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106012"],"award-info":[{"award-number":["62020106012"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332008"],"award-info":[{"award-number":["62332008"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106089"],"award-info":[{"award-number":["62106089"]}],"id":[{"id":"10.13039\/100014718","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":[[2026,5]]},"DOI":"10.1007\/s11263-026-02793-4","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T11:11:42Z","timestamp":1776078702000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Color Information Driven Collaborative Training of Dual Task Parallel Network for Visible and Thermal Infrared Image Fusion and Saliency Object Detection"],"prefix":"10.1007","volume":"134","author":[{"given":"Zeyang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Awais","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"issue":"12","key":"2793_CR1","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":"2793_CR2","doi-asserted-by":"publisher","unstructured":"Bao, L., Zhou, X., Zheng, B., Cong, R., Yin, H., Zhang, J., & Yan, C. (2025). Ifenet: Interaction, fusion, and enhancement network for v-d-t salient object detection. IEEE Transactions on Image Processing,34, 483\u2013494. https:\/\/doi.org\/10.1109\/TIP.2025.3527372","DOI":"10.1109\/TIP.2025.3527372"},{"key":"2793_CR3","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TIP.2025.3527372","volume":"34","author":"L Bao","year":"2025","unstructured":"Bao, L., Zhou, X., Zheng, B., Cong, R., Yin, H., Zhang, J., & Yan, C. (2025). Ifenet: Interaction, fusion, and enhancement network for v-d-t salient object detection. IEEE Transactions on Image Processing, 34, 483\u2013494. https:\/\/doi.org\/10.1109\/TIP.2025.3527372","journal-title":"IEEE Transactions on Image Processing"},{"key":"2793_CR4","doi-asserted-by":"crossref","unstructured":"Brazil, G., Kumar, A., Straub, J., Ravi, N., Johnson, J., & Gkioxari, G. (2023). Omni3D: A large benchmark and model for 3D object detection in the wild. In: CVPR, Vancouver, Canada. IEEE.","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"2793_CR5","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.inffus.2022.11.010","volume":"92","author":"C Cheng","year":"2023","unstructured":"Cheng, C., Xu, T., & Wu, X.-J. (2023). Mufusion: A general unsupervised image fusion network based on memory unit. Information Fusion, 92, 80\u201392.","journal-title":"Information Fusion"},{"key":"2793_CR6","doi-asserted-by":"publisher","first-page":"3041","DOI":"10.1007\/s11263-024-02266-6","volume":"133","author":"C Cheng","year":"2025","unstructured":"Cheng, C., Xu, T., Wu, X.-J., Li, H., Li, X., & Kittler, J. (2025). Fusionbooster: A unified image fusion boosting paradigm. International Journal of Computer Vision, 133, 3041\u20133058.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"2793_CR7","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.inffus.2005.10.001","volume":"8","author":"H Chen","year":"2007","unstructured":"Chen, H., & Varshney, P. K. (2007). A human perception inspired quality metric for image fusion based on regional information. Information fusion, 8(2), 193\u2013207.","journal-title":"Information fusion"},{"key":"2793_CR8","doi-asserted-by":"publisher","unstructured":"Cui, F., Zhou, X., Bao, L., Wan, B., Shi, R., Chen, Q., & Zhang, J. (2025). Multi-modal feature integration network for visible-depth-thermal salient object detection. Engineering Applications of Artificial Intelligence 152, 110734. https:\/\/doi.org\/10.1016\/j.engappai.2025.110734","DOI":"10.1016\/j.engappai.2025.110734"},{"key":"2793_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929."},{"key":"2793_CR10","doi-asserted-by":"publisher","unstructured":"Fan, D.-P., Gong, C., Cao, Y., Ren, B., Cheng, M.-M., & Borji, A. (2018). Enhanced-alignment measure for binary foreground map evaluation. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. https:\/\/doi.org\/10.24963\/ijcai.2018\/97.","DOI":"10.24963\/ijcai.2018\/97"},{"key":"2793_CR11","doi-asserted-by":"publisher","unstructured":"Gao, W., Liao, G., Ma, S., Li, G., Liang, Y., & Lin, W. (2022). Unified information fusion network for multi-modal rgb-d and rgb-t salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 2091\u20132106. https:\/\/doi.org\/10.1109\/tcsvt.2021.3082939","DOI":"10.1109\/tcsvt.2021.3082939"},{"key":"2793_CR12","doi-asserted-by":"crossref","unstructured":"Guo, M.-H., Lu, C.-Z., Hou, Q., Liu, Z., Cheng, M.-M., & Hu, S.-m. (2022). Segnext: Rethinking convolutional attention design for semantic segmentation. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol. 35, pp. 1140\u20131156. Curran Associates Inc, (2022). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/08050f40fff41616ccfc3080e60a301a-Paper-Conference.pdf.","DOI":"10.52202\/068431-0084"},{"key":"2793_CR13","doi-asserted-by":"publisher","unstructured":"Huang, S.-C., Le, T.-H., & Jaw, D.-W. (2020). Dsnet: Joint semantic learning for object detection in inclement weather conditions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1. https:\/\/doi.org\/10.1109\/tpami.2020.2977911","DOI":"10.1109\/tpami.2020.2977911"},{"key":"2793_CR14","doi-asserted-by":"publisher","unstructured":"Huo, F., Zhu, X., Zhang, L., Liu, Q., & Shu, Y. (2022). Efficient context-guided stacked refinement network for rgb-t salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 3111\u20133124. https:\/\/doi.org\/10.1109\/tcsvt.2021.3102268","DOI":"10.1109\/tcsvt.2021.3102268"},{"issue":"5","key":"2793_CR15","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TCSVT.2021.3102268","volume":"32","author":"F Huo","year":"2022","unstructured":"Huo, F., Zhu, X., Zhang, L., Liu, Q., & Shu, Y. (2022). Efficient context-guided stacked refinement network for rgb-t salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 32(5), 3111\u20133124. https:\/\/doi.org\/10.1109\/TCSVT.2021.3102268","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"8","key":"2793_CR16","doi-asserted-by":"publisher","first-page":"3067","DOI":"10.1007\/S11263-024-02020-Y","volume":"132","author":"X Hu","year":"2024","unstructured":"Hu, X., Sun, F., Sun, J., Wang, F., & Li, H. (2024). Cross-modal fusion and progressive decoding network for RGB-D salient object detection. Int. J. Comput. Vis., 132(8), 3067\u20133085. https:\/\/doi.org\/10.1007\/S11263-024-02020-Y","journal-title":"Int. J. Comput. Vis."},{"issue":"8","key":"2793_CR17","doi-asserted-by":"publisher","first-page":"3067","DOI":"10.1007\/s11263-024-02020-y","volume":"132","author":"X Hu","year":"2024","unstructured":"Hu, X., Sun, F., Sun, J., Wang, F., & Li, H. (2024). Cross-modal fusion and progressive decoding network for rgb-d salient object detection. International Journal of Computer Vision, 132(8), 3067\u20133085.","journal-title":"International Journal of Computer Vision"},{"key":"2793_CR18","doi-asserted-by":"publisher","unstructured":"Jia, X., Zhu, C., Li, M., Tang, W., & Zhou, W. (2021). Llvip: A visible-infrared paired dataset for low-light vision. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW). https:\/\/doi.org\/10.1109\/iccvw54120.2021.00389","DOI":"10.1109\/iccvw54120.2021.00389"},{"key":"2793_CR19","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., & Ye, J.C. (2022). Diffusionclip: Text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2426\u20132435.","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"2793_CR20","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv: Learning."},{"key":"2793_CR21","unstructured":"Li, H., & Wu, X.-J. (2018). Infrared and visible image fusion using latent low-rank representation. arXiv preprint arXiv:1804.08992."},{"key":"2793_CR22","doi-asserted-by":"crossref","unstructured":"Liang, P., Jiang, J., Liu, X., & Ma, J. (2022). Fusion from decomposition: A self-supervised decomposition approach for image fusion. In: European Conference on Computer Vision (ECCV).","DOI":"10.1007\/978-3-031-19797-0_41"},{"key":"2793_CR23","doi-asserted-by":"publisher","unstructured":"Liang, Y., Qin, G., Sun, M., Qin, J., Yan, J., & Zhang, Z. (2022). Multi-modal interactive attention and dual progressive decoding network for rgb-d\/t salient object detection. Neurocomputing, 132\u2013145. https:\/\/doi.org\/10.1016\/j.neucom.2022.03.029.","DOI":"10.1016\/j.neucom.2022.03.029"},{"issue":"11","key":"2793_CR24","doi-asserted-by":"publisher","first-page":"5173","DOI":"10.1007\/s11263-024-02051-5","volume":"132","author":"J Lin","year":"2024","unstructured":"Lin, J., Zhu, L., Shen, J., Fu, H., Zhang, Q., & Wang, L. (2024). Vidsod-100: A new dataset and a baseline model for rgb-d video salient object detection. International Journal of Computer Vision, 132(11), 5173\u20135191.","journal-title":"International Journal of Computer Vision"},{"key":"2793_CR25","doi-asserted-by":"publisher","unstructured":"Liu, Y., Li, C., Dong, X., Li, L., Zhang, D., Xu, S., & Han, J. (2025). Seamless detection: Unifying salient object detection and camouflaged object detection. Expert Systems with Applications 274, 126912. https:\/\/doi.org\/10.1016\/j.eswa.2025.126912","DOI":"10.1016\/j.eswa.2025.126912"},{"key":"2793_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., Wu, G., Ma, L., Liu, R., Zhong, W., Luo, Z., & Fan, X. (2023). Multi-interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation. In: International Conference on Computer Vision.","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"2793_CR27","doi-asserted-by":"publisher","unstructured":"Liu, N., Zhang, N., Wan, K., Shao, L., & Han, J. (2021). Visual saliency transformer. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). https:\/\/doi.org\/10.1109\/iccv48922.2021.00468.","DOI":"10.1109\/iccv48922.2021.00468"},{"key":"2793_CR28","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.inffus.2016.12.001","volume":"36","author":"Y Liu","year":"2017","unstructured":"Liu, Y., Chen, X., Peng, H., & Wang, Z. (2017). Multi-focus image fusion with a deep convolutional neural network. Information Fusion, 36, 191\u2013207.","journal-title":"Information Fusion"},{"issue":"7","key":"2793_CR29","doi-asserted-by":"publisher","first-page":"4483","DOI":"10.1007\/s11263-025-02393-8","volume":"133","author":"Y Liu","year":"2025","unstructured":"Liu, Y., Li, C., Xu, S., & Han, J. (2025). Part-whole relational fusion towards multi-modal scene understanding. International Journal of Computer Vision, 133(7), 4483\u20134503.","journal-title":"International Journal of Computer Vision"},{"issue":"5","key":"2793_CR30","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2019","unstructured":"Li, H., & Wu, X.-J. (2019). Densefuse: A fusion approach to infrared and visible images. IEEE Transactions on Image Processing, 28(5), 2614\u20132623.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2793_CR31","doi-asserted-by":"publisher","first-page":"4733","DOI":"10.1109\/TIP.2020.2975984","volume":"29","author":"H Li","year":"2020","unstructured":"Li, H., Wu, X.-J., & Kittler, J. (2020). Mdlatlrr: A novel decomposition method for infrared and visible image fusion. IEEE Transactions on Image Processing, 29, 4733\u20134746.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2793_CR32","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.inffus.2019.07.005","volume":"54","author":"J Ma","year":"2020","unstructured":"Ma, J., Liang, P., Yu, W., Chen, C., Guo, X., Wu, J., & Jiang, J. (2020). Infrared and visible image fusion via detail preserving adversarial learning. Information Fusion, 54, 85\u201398.","journal-title":"Information Fusion"},{"key":"2793_CR33","first-page":"1","volume":"70","author":"J Ma","year":"2021","unstructured":"Ma, J., Tang, L., Xu, M., Zhang, H., & Xiao, G. (2021). Stdfusionnet: An infrared and visible image fusion network based on salient target detection. IEEE Transactions on Instrumentation and Measurement, 70, 1\u201313.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"11","key":"2793_CR34","doi-asserted-by":"publisher","first-page":"3345","DOI":"10.1109\/TIP.2015.2442920","volume":"24","author":"K Ma","year":"2015","unstructured":"Ma, K., Zeng, K., & Wang, Z. (2015). Perceptual quality assessment for multi-exposure image fusion. IEEE Transactions on Image Processing, 24(11), 3345\u20133356.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2793_CR35","doi-asserted-by":"crossref","unstructured":"Mechrez, R., Talmi, I., & Zelnik-Manor, L. (2018). The contextual loss for image transformation with non-aligned data. In: Proceedings of the European Conference on Computer Vision (ECCV).","DOI":"10.1007\/978-3-030-01264-9_47"},{"key":"2793_CR36","doi-asserted-by":"publisher","unstructured":"Perazzi, F., Krahenbuhl, P., Pritch, Y., & Hornung, A. (2012). Saliency filters: Contrast based filtering for salient region detection. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/cvpr.2012.6247743.","DOI":"10.1109\/cvpr.2012.6247743."},{"key":"2793_CR37","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., Yang, Y.-H., Sakaridis, C., Segu, M., Li, S., Van Gool, L., & Yu, F. (2024). UniDepth: Universal monocular metric depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"2793_CR38","doi-asserted-by":"publisher","unstructured":"Rao, D., Xu, T., & Wu, X.-J. (2023). Tgfuse: An infrared and visible image fusion approach based on transformer and generative adversarial network. IEEE Transactions on Image Processing, 1. https:\/\/doi.org\/10.1109\/TIP.2023.3273451","DOI":"10.1109\/TIP.2023.3273451"},{"key":"2793_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2021.103839","volume":"117","author":"L Ren","year":"2021","unstructured":"Ren, L., Pan, Z., Cao, J., & Liao, J. (2021). Infrared and visible image fusion based on variational auto-encoder and infrared feature compensation. Infrared Physics & Technology, 117, Article 103839.","journal-title":"Infrared Physics & Technology"},{"key":"2793_CR40","doi-asserted-by":"publisher","unstructured":"Tang, L., Yuan, J., & Ma, J. (2022). Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network. Information Fusion,82, 28\u201342. https:\/\/doi.org\/10.1016\/j.inffus.2021.12.004","DOI":"10.1016\/j.inffus.2021.12.004"},{"key":"2793_CR41","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.inffus.2022.10.034","volume":"91","author":"L Tang","year":"2023","unstructured":"Tang, L., Xiang, X., Zhang, H., Gong, M., & Ma, J. (2023). Divfusion: Darkness-free infrared and visible image fusion. Information Fusion, 91, 477\u2013493.","journal-title":"Information Fusion"},{"key":"2793_CR42","doi-asserted-by":"publisher","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. (2022). Piafusion: A progressive infrared and visible image fusion network based on illumination aware. Information Fusion, 83, 79\u201392.","journal-title":"Information Fusion"},{"key":"2793_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101870","volume":"99","author":"L Tang","year":"2023","unstructured":"Tang, L., Zhang, H., Xu, H., & Ma, J. (2023). 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. Information Fusion, 99, Article 101870.","journal-title":"Information Fusion"},{"key":"2793_CR44","doi-asserted-by":"publisher","unstructured":"Tu, Z., Xia, T., Li, C., Lu, Y., & Tang, J. (2019). M3s-nir: Multi-modal multi-scale noise-insensitive ranking for rgb-t saliency detection. In: 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). https:\/\/doi.org\/10.1109\/mipr.2019.00032","DOI":"10.1109\/mipr.2019.00032"},{"key":"2793_CR45","doi-asserted-by":"publisher","unstructured":"Tu, Z., Xia, T., Li, C., Wang, X., Ma, Y., & Tang, J. (2020). Rgb-t image saliency detection via collaborative graph learning. IEEE Transactions on Multimedia, 160\u2013173. https:\/\/doi.org\/10.1109\/tmm.2019.2924578","DOI":"10.1109\/tmm.2019.2924578"},{"key":"2793_CR46","doi-asserted-by":"publisher","first-page":"5678","DOI":"10.1109\/TIP.2021.3087412","volume":"30","author":"Z Tu","year":"2021","unstructured":"Tu, Z., Li, Z., Li, C., Lang, Y., & Tang, J. (2021). Multi-interactive dual-decoder for rgb-thermal salient object detection. IEEE Transactions on Image Processing, 30, 5678\u20135691. https:\/\/doi.org\/10.1109\/TIP.2021.3087412","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"2793_CR47","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1109\/TMM.2019.2924578","volume":"22","author":"Z Tu","year":"2019","unstructured":"Tu, Z., Xia, T., Li, C., Wang, X., Ma, Y., & Tang, J. (2019). Rgb-t image saliency detection via collaborative graph learning. IEEE Transactions on Multimedia, 22(1), 160\u2013173.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2793_CR48","volume-title":"Attention is all you need","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Neural Information Processing Systems: Neural Information Processing Systems."},{"key":"2793_CR49","doi-asserted-by":"publisher","unstructured":"Wang, G., Li, C., Ma, Y., Zheng, A., Tang, J., & Luo, B. (2018). RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and a Novel Approach, pp. 359\u2013369. https:\/\/doi.org\/10.1007\/978-981-13-1702-6_36","DOI":"10.1007\/978-981-13-1702-6_36"},{"key":"2793_CR50","doi-asserted-by":"publisher","unstructured":"Wang, L., Li, D., Zhu, Y., Tian, L., & Shan, Y. (2020). Dual super-resolution learning for semantic segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00383.","DOI":"10.1109\/cvpr42600.2020.00383"},{"key":"2793_CR51","doi-asserted-by":"publisher","unstructured":"Wang, D., Liu, J., Liu, R., & Fan, X. (2023). An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection. Information Fusion 98, 101828. https:\/\/doi.org\/10.1016\/j.inffus.2023.101828.","DOI":"10.1016\/j.inffus.2023.101828"},{"key":"2793_CR52","doi-asserted-by":"publisher","unstructured":"Wang, W., Zhang, L., Pun, C.-M., & Xie, J.-C. (2023). Boosting face recognition performance with synthetic data and limited real data. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10097133","DOI":"10.1109\/ICASSP49357.2023.10097133"},{"key":"2793_CR53","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/978-981-13-1702-6_36","volume-title":"Image and Graphics Technologies and Applications","author":"G Wang","year":"2018","unstructured":"Wang, G., Li, C., Ma, Y., Zheng, A., Tang, J., & Luo, B. (2018). Rgb-t saliency detection benchmark: Dataset, baselines, analysis and a novel approach. In Y. Wang, Z. Jiang, & Y. Peng (Eds.), Image and Graphics Technologies and Applications (pp. 359\u2013369). Singapore: Springer."},{"key":"2793_CR54","doi-asserted-by":"publisher","unstructured":"Xu, H., Ma, J., Jiang, J., Guo, X., & Ling, H. (2022). U2fusion: A unified unsupervised image fusion network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 502\u2013518. https:\/\/doi.org\/10.1109\/tpami.2020.3012548.","DOI":"10.1109\/tpami.2020.3012548"},{"issue":"10","key":"2793_CR55","doi-asserted-by":"publisher","first-page":"12148","DOI":"10.1109\/TPAMI.2023.3283682","volume":"45","author":"H Xu","year":"2023","unstructured":"Xu, H., Yuan, J., & Ma, J. (2023). Murf: Mutually reinforcing multi-modal image registration and fusion. IEEE transactions on pattern analysis and machine intelligence, 45(10), 12148\u201312166.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"4","key":"2793_CR56","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1049\/el:20000267","volume":"36","author":"C Xydeas","year":"2000","unstructured":"Xydeas, C., & Petrovic, V. (2000). Objective image fusion performance measure. Electronics letters, 36(4), 308\u2013309.","journal-title":"Electronics letters"},{"key":"2793_CR57","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., & Zhao, H. (2024). Depth anything: Unleashing the power of large-scale unlabeled data. In: CVPR.","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"2793_CR58","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., & Zhao, H. (2024). Depth anything v2. arXiv:2406.09414."},{"key":"2793_CR59","doi-asserted-by":"crossref","unstructured":"Yi, X., Xu, H., Zhang, H., Tang, L., & Ma, J. (2024). Text-if: Leveraging semantic text guidance for degradation-aware and interactive image fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 27026\u201327035.","DOI":"10.1109\/CVPR52733.2024.02552"},{"key":"2793_CR60","doi-asserted-by":"publisher","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F.E.H., Feng, J., & Yan, S. (2021). Tokens-to-token vit: Training vision transformers from scratch on imagenet. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). https:\/\/doi.org\/10.1109\/iccv48922.2021.00060.","DOI":"10.1109\/iccv48922.2021.00060"},{"key":"2793_CR61","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Huang, N., Yao, L., Zhang, D., Shan, C., & Han, J. (2020). Rgb-t salient object detection via fusing multi-level cnn features. IEEE Transactions on Image Processing, 3321\u20133335. https:\/\/doi.org\/10.1109\/tip.2019.2959253","DOI":"10.1109\/tip.2019.2959253"},{"key":"2793_CR62","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Huang, N., Yao, L., Zhang, D., Shan, C., & Han, J. (2020). Rgb-t salient object detection via fusing multi-level cnn features. IEEE Transactions on Image Processing, 3321\u20133335. https:\/\/doi.org\/10.1109\/tip.2019.2959253","DOI":"10.1109\/tip.2019.2959253"},{"key":"2793_CR63","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Li, H., Xu, T., Wu, X.-J., & Fu, Y. (2024). Guidefuse: A novel guided auto-encoder fusion network for infrared and visible images. IEEE Transactions on Instrumentation and Measurement 73, 1\u201311. https:\/\/doi.org\/10.1109\/TIM.2023.3306537","DOI":"10.1109\/TIM.2023.3306537"},{"key":"2793_CR64","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Li, H., Xu, T., Wu, X.-J., & Fu, Y. (2024). Guidefuse: A novel guided auto-encoder fusion network for infrared and visible images. IEEE Transactions on Instrumentation and Measurement,73, 1\u201311. https:\/\/doi.org\/10.1109\/TIM.2023.3306537","DOI":"10.1109\/TIM.2023.3306537"},{"key":"2793_CR65","doi-asserted-by":"publisher","unstructured":"Zhang, H., Xu, H., Tian, X., Jiang, J., & Ma, J. (2021). Image fusion meets deep learning: A survey and perspective. Information Fusion 76, 323\u2013336. https:\/\/doi.org\/10.1016\/j.inffus.2021.06.008.","DOI":"10.1016\/j.inffus.2021.06.008"},{"key":"2793_CR66","doi-asserted-by":"publisher","first-page":"12797","DOI":"10.1609\/aaai.v34i07.6975","volume":"34","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Xu, H., Xiao, Y., Guo, X., & Ma, J. (2020). Rethinking the image fusion: A fast unified image fusion network based on proportional maintenance of gradient and intensity. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12797\u201312804.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"12","key":"2793_CR67","doi-asserted-by":"publisher","first-page":"12437","DOI":"10.1109\/TCSVT.2024.3437685","volume":"34","author":"X Zheng","year":"2024","unstructured":"Zheng, X., Li, Z., Liu, D., Zhou, X., & Shan, C. (2024). Spatial attention-guided light field salient object detection network with implicit neural representation. IEEE Transactions on Circuits and Systems for Video Technology, 34(12), 12437\u201312449. https:\/\/doi.org\/10.1109\/TCSVT.2024.3437685","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"5","key":"2793_CR68","doi-asserted-by":"publisher","first-page":"6477","DOI":"10.1109\/TITS.2025.3528064","volume":"26","author":"X Zhou","year":"2025","unstructured":"Zhou, X., Wu, X., Bao, L., Yin, H., Jiang, Q., & Zhang, J. (2025). Agfnet: Adaptive gated fusion network for rgb-t semantic segmentation. IEEE Transactions on Intelligent Transportation Systems, 26(5), 6477\u20136492. https:\/\/doi.org\/10.1109\/TITS.2025.3528064","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"2793_CR69","doi-asserted-by":"crossref","unstructured":"Zhou, W., Zhu, Y., Lei, J., Yang, R., & Yu, L. (2023). Lsnet: Lightweight spatial boosting network for detecting salient objects in rgb-thermal images. IEEE Transactions on Image Processing,32, 1329\u20131340.","DOI":"10.1109\/TIP.2023.3242775"},{"key":"2793_CR70","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., & Lu, H. (2023). Visual prompt multi-modal tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9516\u20139526.","DOI":"10.1109\/CVPR52729.2023.00918"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02793-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02793-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02793-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T08:46:11Z","timestamp":1779525971000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02793-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":70,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["2793"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02793-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"5 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"227"}}