{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T11:37:55Z","timestamp":1767872275180,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557011","type":"print"},{"value":"9789819557028","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5702-8_1","type":"book-chapter","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:28:58Z","timestamp":1767860938000},"page":"3-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DRLHomo: Disentangled Representation Learning for\u00a0Cross-Modal Homography Estimation"],"prefix":"10.1007","author":[{"given":"Tianming","family":"Li","sequence":"first","affiliation":[]},{"given":"Zhen","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jianqiao","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Yaonan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Arar, M., Ginger, Y., Danon, D., Bermano, A.H., Cohen-Or, D.: Unsupervised multi-modal image registration via geometry preserving image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13410\u201313419 (2020)","DOI":"10.1109\/CVPR42600.2020.01342"},{"key":"1_CR2","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1023\/B:VISI.0000011205.11775.fd","volume":"56","author":"S Baker","year":"2004","unstructured":"Baker, S., Matthews, I.: Lucas-Kanade 20 years on: a unifying framework. Int. J. Comput. Vis. 56, 221\u2013255 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Barath, D., Matas, J., Noskova, J.: MAGSAC: marginalizing sample consensus. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10197\u201310205 (2019)","DOI":"10.1109\/CVPR.2019.01044"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., Gool, L.V.: SURF: speeded up robust features. Eur. Conf. Comput. Vis. (2006)","DOI":"10.1007\/11744023_32"},{"key":"1_CR5","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Cao, S.Y., Hu, J., Sheng, Z., Shen, H.L.: Iterative deep homography estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1879\u20131888 (2022)","DOI":"10.1109\/CVPR52688.2022.00192"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Cao, S.Y., et al.: Recurrent homography estimation using homography-guided image warping and focus transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9833\u20139842 (2023)","DOI":"10.1109\/CVPR52729.2023.00948"},{"issue":"1","key":"1_CR8","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s44267-024-00045-y","volume":"2","author":"Z Chen","year":"2024","unstructured":"Chen, Z., Li, K., Li, H., Fu, Z., Zhang, H., Guo, Y.: Metric localization for lunar rovers via cross-view image matching. Vis. Intell. 2(1), 12 (2024)","journal-title":"Vis. Intell."},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Deng, X., Liu, E., Gao, C., Li, S., Gu, S., Xu, M.: CrossHomo: cross-modality and cross-resolution homography estimation. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3366234"},{"key":"1_CR10","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1109\/TIP.2023.3240024","volume":"32","author":"X Deng","year":"2023","unstructured":"Deng, X., Liu, E., Li, S., Duan, Y., Xu, M.: Interpretable multi-modal image registration network based on disentangled convolutional sparse coding. IEEE Trans. Image Process. 32, 1078\u20131091 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR11","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: Deep image homography estimation. arXiv preprint arXiv:1606.03798 (2016)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Ding, J., Li, W., Pei, L., Yang, M., Tian, A., Yuan, B.: Novel pipeline integrating cross-modality and motion model for nearshore multi-object tracking in optical video surveillance. IEEE Trans. Intell. Transp. Syst. (2024)","DOI":"10.1109\/TITS.2024.3373370"},{"key":"1_CR13","doi-asserted-by":"publisher","first-page":"111091","DOI":"10.1016\/j.patcog.2024.111091","volume":"159","author":"J Ding","year":"2025","unstructured":"Ding, J., Li, W., Yang, M., Zhao, Y., Pei, L., Tian, A.: SeaTrack: rethinking observation-centric sort for robust nearshore multiple object tracking. Pattern Recogn. 159, 111091 (2025)","journal-title":"Pattern Recogn."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Erlik\u00a0Nowruzi, F., Laganiere, R., Japkowicz, N.: Homography estimation from image pairs with hierarchical convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 913\u2013920 (2017)","DOI":"10.1109\/ICCVW.2017.111"},{"issue":"1","key":"1_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s44267-024-00035-0","volume":"2","author":"B Fan","year":"2024","unstructured":"Fan, B., Dai, Y., Seo, Y., He, M.: A revisit of the normalized eight-point algorithm and a self-supervised deep solution. Vis. Intell. 2(1), 3 (2024)","journal-title":"Vis. Intell."},{"issue":"6","key":"1_CR16","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Goforth, H., Lucey, S.: GPS-denied UAV localization using pre-existing satellite imagery. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 2974\u20132980. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793558"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press (2003)","DOI":"10.1017\/CBO9780511811685"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and-specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR21","doi-asserted-by":"publisher","first-page":"104209","DOI":"10.1016\/j.cviu.2024.104209","volume":"250","author":"Q Jia","year":"2025","unstructured":"Jia, Q., Feng, X., Zhang, W., Liu, Y., Pu, N., Sebe, N.: Bilevel progressive homography estimation via correlative region-focused transformer. Comput. Vis. Image Underst. 250, 104209 (2025)","journal-title":"Comput. Vis. Image Underst."},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Le, H., Liu, F., Zhang, S., Agarwala, A.: Deep homography estimation for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7652\u20137661 (2020)","DOI":"10.1109\/CVPR42600.2020.00767"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Li, H., Liu, Z., Lyu, Y., Wu, F.: Multimodal image registration for GPS-denied UAV navigation based on disentangled representations. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 1228\u20131234. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161567"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Li, T., Zhu, Q., Zhou, Z., Luo, J., Wang, Y.: Multi-range adaptive perception transformer for iterative homography estimation. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10888932"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., Lu, H., Fu, H., Cao, Z.: Learning to upsample by learning to sample. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6027\u20136037 (2023)","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"1_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"1_CR27","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR28","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"1_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-030-20351-1_19","volume-title":"Information Processing in Medical Imaging","author":"C Qin","year":"2019","unstructured":"Qin, C., Shi, B., Liao, R., Mansi, T., Rueckert, D., Kamen, A.: Unsupervised deformable registration for multi-modal images via disentangled representations. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 249\u2013261. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20351-1_19"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to sift or surf. In: 2011 International Conference on Computer Vision, pp. 2564\u20132571. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Shao, R., Wu, G., Zhou, Y., Fu, Y., Fang, L., Liu, Y.: LocalTrans: a multiscale local transformer network for cross-resolution homography estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14890\u201314899 (2021)","DOI":"10.1109\/ICCV48922.2021.01462"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Smith, L.N., Topin, N.: Super-Convergence: very fast training of neural networks using large learning rates. In: Artificial Intelligence and Machine Learning for Multi-domain Operations Applications, vol. 11006, pp. 369\u2013386. SPIE (2019)","DOI":"10.1117\/12.2520589"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, H., Wu, Z., Zhu, W., et\u00a0al.: Disentangled representation learning. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3420937"},{"key":"1_CR34","unstructured":"Wen, K., Xie, B., Duan, B., Yan, Y.: MambaReg: Mamba-based disentangled convolutional sparse coding for unsupervised deformable multi-modal image registration. arXiv preprint arXiv:2411.01399 (2024)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Xu, H., Ma, J., Yuan, J., Le, Z., Liu, W.: RFNet: unsupervised network for mutually reinforcing multi-modal image registration and fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19679\u201319688 (2022)","DOI":"10.1109\/CVPR52688.2022.01906"},{"issue":"10","key":"1_CR36","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.: MURF: mutually reinforcing multi-modal image registration and fusion. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12148\u201312166 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Yang, D., Huang, S., Kuang, H., Du, Y., Zhang, L.: Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1642\u20131651 (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: SSHNet: Unsupervised cross-modal homography estimation via problem reformulation and split optimization. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 16685\u201316694 (2025)","DOI":"10.1109\/CVPR52734.2025.01555"},{"key":"1_CR39","unstructured":"Zellinger, W., Grubinger, T., Lughofer, E., Natschl\u00e4ger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning. In: International Conference on Learning Representations (2017)"},{"key":"1_CR40","doi-asserted-by":"publisher","unstructured":"Zhang, R., et al.: SCPNet: unsupervised cross-modal homography estimation via intra-modal self-supervised learning. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024, ECCV 2024. LNCS, vol. 15081. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73337-6_26","DOI":"10.1007\/978-3-031-73337-6_26"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, X., Zhang, Z.: PRISE: demystifying deep Lucas-Kanade with strongly star-convex constraints for multimodel image alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13187\u201313197 (2023)","DOI":"10.1109\/CVPR52729.2023.01267"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Huang, X., Zhang, Z.: Deep Lucas-Kanade homography for multimodal image alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15950\u201315959 (2021)","DOI":"10.1109\/CVPR46437.2021.01569"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: 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":"1_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Uncertainty guided deep Lucas-Kanade homography for multimodal image alignment. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3522387"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: A feature disentanglement method for image stitching of printed circuit boards. IEEE Trans. Instrum. Meas. (2025)","DOI":"10.1109\/TIM.2025.3547509"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Zhu, H., et al.: MCNet: rethinking the core ingredients for accurate and efficient homography estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25932\u201325941 (2024)","DOI":"10.1109\/CVPR52733.2024.02450"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5702-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:29:14Z","timestamp":1767860954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5702-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557011","9789819557028"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5702-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}