{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T21:23:43Z","timestamp":1789939423491,"version":"4.0.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Dr. Hui Li","award":["62202205"],"award-info":[{"award-number":["62202205"]}]},{"name":"Professor Xiao-Jun Wu","award":["62020106012"],"award-info":[{"award-number":["62020106012"]}]},{"name":"Professor Xiao-Jun Wu","award":["U1836218"],"award-info":[{"award-number":["U1836218"]}]},{"name":"Professor Xiao-Jun Wu","award":["62106089"],"award-info":[{"award-number":["62106089"]}]},{"name":"Professor Josef Kittler","award":["EP\/V002856\/1"],"award-info":[{"award-number":["EP\/V002856\/1"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11263-025-02578-1","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T10:40:27Z","timestamp":1762339227000},"page":"8642-8663","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["SMLNet: A SPD Manifold Learning Network for Infrared and Visible Image Fusion"],"prefix":"10.1007","volume":"133","author":[{"given":"Huan","family":"Kang","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":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyang","family":"Cheng","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":[[2025,11,5]]},"reference":[{"key":"2578_CR1","unstructured":"Brooks, D., Schwander, O., Barbaresco, F., Schneider, J.Y., & Cord, M. (2019). Riemannian batch normalization for spd neural networks. Advances in Neural Information Processing Systems 32."},{"key":"2578_CR2","doi-asserted-by":"publisher","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. (2020). Infrared and visible image fusion based on target-enhanced multiscale transform decomposition. Information Sciences, 508, 64\u201378.","journal-title":"Information Sciences"},{"key":"2578_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), (pp 801\u2013818).","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2578_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Liu, G., Kompella, R.R., Wu, X., & Sebe, N. (2023). Riemannian multiclass logistics regression for spd neural networks. arXiv preprint arXiv:2305.11288.","DOI":"10.1109\/CVPR52733.2024.01617"},{"key":"2578_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, C., Xu, T., Feng, Z., Wu, X., Li, H., Zhang, Z., Atito, S., Awais, M., Kittler, J., and others (2025a) One model for all: Low-level task interaction is a key to task-agnostic image fusion. arXiv preprint arXiv:2502.19854","DOI":"10.1109\/CVPR52734.2025.02617"},{"issue":"5","key":"2578_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(5), 3041\u20133058.","journal-title":"International Journal of Computer Vision."},{"key":"2578_CR7","doi-asserted-by":"publisher","first-page":"102790","DOI":"10.1016\/j.inffus.2024.102790","volume":"117","author":"C Cheng","year":"2025","unstructured":"Cheng, C., Xu, T., Wu, X. J., Li, H., Li, X., Tang, Z., & Kittler, J. (2025). Textfusion: Unveiling the power of textual semantics for controllable image fusion. Information Fusion, 117, 102790.","journal-title":"Information Fusion"},{"key":"2578_CR8","doi-asserted-by":"crossref","unstructured":"Deng, Y., Xu, T., Cheng, C., Wu, X.J., & Kittler, J. (2024). Mmdrfuse: Distilled mini-model with dynamic refresh for multi-modality image fusion. In Proceedings of the 32nd ACM International Conference on Multimedia, (pp 7326\u20137335).","DOI":"10.1145\/3664647.3681085"},{"key":"2578_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. ICLR."},{"key":"2578_CR10","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2578_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Z. &, Van\u00a0Gool, L. (2017). A riemannian network for spd matrix learning. In Proceedings of the AAAI conference on artificial intelligence, vol\u00a031.","DOI":"10.1609\/aaai.v31i1.10866"},{"issue":"5","key":"2578_CR12","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1109\/TIP.2018.2887342","volume":"28","author":"H Li","year":"2018","unstructured":"Li, H., & Wu, X. J. (2018). 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":"2578_CR13","doi-asserted-by":"publisher","first-page":"102147","DOI":"10.1016\/j.inffus.2023.102147","volume":"103","author":"H Li","year":"2024","unstructured":"Li, H., & Wu, X. J. (2024). Crossfuse: A novel cross attention mechanism based infrared and visible image fusion approach. Information Fusion, 103, 102147.","journal-title":"Information Fusion"},{"key":"2578_CR14","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":"2578_CR15","doi-asserted-by":"publisher","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":"9","key":"2578_CR16","doi-asserted-by":"publisher","first-page":"11040","DOI":"10.1109\/TPAMI.2023.3268209","volume":"45","author":"H Li","year":"2023","unstructured":"Li, H., Xu, T., Wu, X. J., Lu, J., & Kittler, J. (2023). Lrrnet: A novel representation learning guided fusion network for infrared and visible images. IEEE Transactions on Pattern Analysis and Machine Intelligence., 45(9), 11040\u201311052.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"2578_CR17","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.ijcce.2020.12.004","volume":"2","author":"Y Li","year":"2021","unstructured":"Li, Y., Zhao, J., Lv, Z., & Li, J. (2021). Medical image fusion method by deep learning. International Journal of Cognitive Computing in Engineering, 2, 21\u201329.","journal-title":"International Journal of Cognitive Computing in Engineering"},{"key":"2578_CR18","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, Springer, (pp 719\u2013735).","DOI":"10.1007\/978-3-031-19797-0_41"},{"key":"2578_CR19","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"},{"key":"2578_CR20","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.inffus.2020.06.013","volume":"64","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Wang, L., Cheng, J., Li, C., & Chen, X. (2020). Multi-focus image fusion: A survey of the state of the art. Information Fusion, 64, 71\u201391.","journal-title":"Information Fusion"},{"key":"2578_CR21","doi-asserted-by":"publisher","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":"2578_CR22","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.inffus.2020.04.006","volume":"62","author":"J Ma","year":"2020","unstructured":"Ma, J., Yu, W., Chen, C., Liang, P., Guo, X., & Jiang, J. (2020). Pan-gan: An unsupervised pan-sharpening method for remote sensing image fusion. Information Fusion, 62, 110\u2013120.","journal-title":"Information Fusion"},{"issue":"7","key":"2578_CR23","doi-asserted-by":"publisher","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. (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":"2578_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, X.S. (2021). Geomnet: A neural network based on riemannian geometries of spd matrix space and cholesky space for 3d skeleton-based interaction recognition. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp 13379\u201313389).","DOI":"10.1109\/ICCV48922.2021.01313"},{"key":"2578_CR25","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1609\/aaai.v36i2.20109","volume":"36","author":"L Qu","year":"2022","unstructured":"Qu, L., Liu, S., Wang, M., & Song, Z. (2022). Transmef: A transformer-based multi-exposure image fusion framework using self-supervised multi-task learning. Proceedings of the AAAI conference on artificial intelligence, 36, 2126\u20132134.","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"2578_CR26","doi-asserted-by":"crossref","unstructured":"Shi, Y., Liu, Y., Cheng, J., Wang, Z.J., & Chen, X. (2024). Vdmufusion: A versatile diffusion model-based unsupervised framework for image fusion. IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2024.3512365"},{"key":"2578_CR27","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"2578_CR28","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2021.12.004","volume":"82","author":"L Tang","year":"2022","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.","journal-title":"Information Fusion"},{"key":"2578_CR29","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":"2578_CR30","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.laa.2022.12.009","volume":"661","author":"Y Thanwerdas","year":"2023","unstructured":"Thanwerdas, Y., & Pennec, X. (2023). O (n)-invariant riemannian metrics on spd matrices. Linear Algebra and its Applications, 661, 163\u2013201.","journal-title":"Linear Algebra and its Applications"},{"issue":"1","key":"2578_CR31","doi-asserted-by":"publisher","first-page":"010901","DOI":"10.1117\/1.OE.51.1.010901","volume":"51","author":"A Toet","year":"2012","unstructured":"Toet, A., & Hogervorst, M. A. (2012). Progress in color night vision. Optical Engineering, 51(1), 010901\u2013010901.","journal-title":"Optical Engineering"},{"key":"2578_CR32","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., & Liao, H.Y.M. (2023a). Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp 7464\u20137475).","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"2578_CR33","doi-asserted-by":"publisher","first-page":"101828","DOI":"10.1016\/j.inffus.2023.101828","volume":"98","author":"D Wang","year":"2023","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.","journal-title":"Information Fusion"},{"key":"2578_CR34","doi-asserted-by":"crossref","unstructured":"Wang, R., Guo, H., Davis, L.S., & Dai, Q. (2012). Covariance discriminative learning: A natural and efficient approach to image set classification. In 2012 IEEE conference on computer vision and pattern recognition, IEEE, (pp 2496\u20132503).","DOI":"10.1109\/CVPR.2012.6247965"},{"key":"2578_CR35","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.neunet.2022.03.012","volume":"151","author":"R Wang","year":"2022","unstructured":"Wang, R., Wu, X. J., Chen, Z., Xu, T., & Kittler, J. (2022). Learning a discriminative spd manifold neural network for image set classification. Neural networks, 151, 94\u2013110.","journal-title":"Neural networks"},{"issue":"5","key":"2578_CR36","doi-asserted-by":"publisher","first-page":"2208","DOI":"10.1109\/TNNLS.2020.3044176","volume":"33","author":"R Wang","year":"2022","unstructured":"Wang, R., Wu, X. J., & Kittler, J. (2022). Symnet: A simple symmetric positive definite manifold deep learning method for image set classification. IEEE Transactions on Neural Networks and Learning Systems, 33(5), 2208\u20132222.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"2578_CR37","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1007\/s11263-023-01924-5","volume":"132","author":"W Wang","year":"2024","unstructured":"Wang, W., Deng, L. J., Ran, R., & Vivone, G. (2024). A general paradigm with detail-preserving conditional invertible network for image fusion. International Journal of Computer Vision, 132(4), 1029\u20131054.","journal-title":"International Journal of Computer Vision"},{"key":"2578_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2578_CR39","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.inffus.2022.09.008","volume":"90","author":"Z Wang","year":"2023","unstructured":"Wang, Z., Ma, Y., & Zhang, Y. (2023). Review of pixel-level remote sensing image fusion based on deep learning. Information Fusion, 90, 36\u201358.","journal-title":"Information Fusion"},{"key":"2578_CR40","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., & Kweon, I.S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), (pp 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2578_CR41","doi-asserted-by":"publisher","first-page":"101835","DOI":"10.1016\/j.inffus.2023.101835","volume":"98","author":"H Xie","year":"2023","unstructured":"Xie, H., Zhang, Y., Qiu, J., Zhai, X., Liu, X., Yang, Y., Zhao, S., Luo, Y., & Zhong, J. (2023). Semantics lead all: Towards unified image registration and fusion from a semantic perspective. Information Fusion, 98, 101835.","journal-title":"Information Fusion"},{"key":"2578_CR42","doi-asserted-by":"publisher","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"},{"issue":"1","key":"2578_CR43","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","volume":"44","author":"H Xu","year":"2020","unstructured":"Xu, H., Ma, J., Jiang, J., Guo, X., & Ling, H. (2020). U2fusion: A unified unsupervised image fusion network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(1), 502\u2013518.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2578_CR44","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.isprsjprs.2020.06.003","volume":"166","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Yue, P., Tapete, D., Jiang, L., Shangguan, B., Huang, L., & Liu, G. (2020). A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 166, 183\u2013200.","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"2578_CR45","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2019). Self-attention generative adversarial networks. In International conference on machine learning, PMLR, (pp 7354\u20137363)."},{"key":"2578_CR46","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.inffus.2021.06.008","volume":"76","author":"H Zhang","year":"2021","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.","journal-title":"Information Fusion"},{"key":"2578_CR47","doi-asserted-by":"publisher","first-page":"107752","DOI":"10.1016\/j.patcog.2020.107752","volume":"113","author":"Q Zhang","year":"2021","unstructured":"Zhang, Q., Wang, F., Luo, Y., & Han, J. (2021). Exploring a unified low rank representation for multi-focus image fusion. Pattern Recognition, 113, 107752.","journal-title":"Pattern Recognition"},{"issue":"8","key":"2578_CR48","doi-asserted-by":"publisher","first-page":"10535","DOI":"10.1109\/TPAMI.2023.3261282","volume":"45","author":"X Zhang","year":"2023","unstructured":"Zhang, X., & Demiris, Y. (2023). Visible and infrared image fusion using deep learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 10535\u201310554.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2578_CR49","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.inffus.2019.07.011","volume":"54","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Liu, Y., Sun, P., Yan, H., Zhao, X., & Zhang, L. (2020). Ifcnn: A general image fusion framework based on convolutional neural network. Information Fusion, 54, 99\u2013118.","journal-title":"Information Fusion"},{"key":"2578_CR50","doi-asserted-by":"publisher","first-page":"102655","DOI":"10.1016\/j.inffus.2024.102655","volume":"114","author":"Z Zhang","year":"2025","unstructured":"Zhang, Z., Li, H., Xu, T., Wu, X. J., & Kittler, J. (2025). Ddbfusion: An unified image decomposition and fusion framework based on dual decomposition and b\u00e9zier curves. Information Fusion, 114, 102655.","journal-title":"Information Fusion"},{"key":"2578_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Bai, H., Zhang, J., Zhang, Y., Xu, S., Lin, Z., Timofte, R., & Van\u00a0Gool, L. (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":"2578_CR52","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. (2023b). Ddfm: denoising diffusion model for multi-modality image fusion. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp 8082\u20138093).","DOI":"10.1109\/ICCV51070.2023.00742"},{"key":"2578_CR53","doi-asserted-by":"crossref","unstructured":"Zhu, X. F., Xu, T., Liu, Z., Tang, Z., Wu, X. J., & Kittler, J. (2024). Unimod1k: Towards a more universal large-scale dataset and benchmark for multi-modal learning. International Journal of Computer Vision, 132(8), 2845\u20132860.","DOI":"10.1007\/s11263-024-01999-8"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02578-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02578-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02578-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:03:24Z","timestamp":1764993804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02578-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":53,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2578"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02578-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]},"assertion":[{"value":"21 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","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":"Conflict of interest"}}]}}