{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:02:19Z","timestamp":1789718539234,"version":"4.0.1"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","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\/978-3-032-37174-4_4","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:12:14Z","timestamp":1789715534000},"page":"53-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CrossFeat: Bridging Imaging Modalities in\u00a0Feature Descriptor Space"],"prefix":"10.1007","author":[{"given":"Paul","family":"Schneider","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazim","family":"Haouchine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2911\u20132918 (2012)","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: All about VLAD. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1578\u20131585 (2013)","DOI":"10.1109\/CVPR.2013.207"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Barroso-Laguna, A., Riba, E., Ponsa, D., Mikolajczyk, K.: Key.net: keypoint detection by handcrafted and learned CNN filters. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5836\u20135844 (2019)","DOI":"10.1109\/ICCV.2019.00593"},{"issue":"10","key":"4_CR4","doi-asserted-by":"publisher","first-page":"6585","DOI":"10.1109\/TPAMI.2021.3092289","volume":"44","author":"EB Baruch","year":"2021","unstructured":"Baruch, E.B., Keller, Y.: Joint detection and matching of feature points in multimodal images. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6585\u20136593 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"B\u00f6kman, G., Edstedt, J., Felsberg, M., Kahl, F.: Affine steerers for structured keypoint description. In: European Conference on Computer Vision, pp. 449\u2013468. Springer (2024)","DOI":"10.1007\/978-3-031-73016-0_26"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Cavalli, L., Larsson, V., Oswald, M.R., Sattler, T.: Adalam: revisiting handcrafted outlier detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5879\u20135887 (2020)","DOI":"10.1007\/978-3-030-58529-7_45"},{"issue":"7","key":"4_CR7","doi-asserted-by":"publisher","first-page":"1707","DOI":"10.1109\/TBME.2010.2042169","volume":"57","author":"J Chen","year":"2010","unstructured":"Chen, J., Tian, J., Lee, N., Zheng, J., Smith, R.T., Laine, A.F.: A partial intensity invariant feature descriptor for multimodal retinal image registration. IEEE Trans. Biomed. Eng. 57(7), 1707\u20131718 (2010)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: Superpoint: self-supervised interest point detection and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 224\u2013236 (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"4_CR9","unstructured":"Dey, N., et al.: Learning general-purpose biomedical volume representations using randomized synthesis (2024)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Dorent, R., et al.: Unified brain MR-ultrasound synthesis using multi-modal hierarchical representations. In: MICCAI, pp. 448\u2013458. Springer (2023)","DOI":"10.1007\/978-3-031-43999-5_43"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., et al.: D2-net: a trainable CNN for joint detection and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8092\u20138101 (2019)","DOI":"10.1109\/CVPR.2019.00828"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Edstedt, J., Sun, Q., B\u00f6kman, G., Wadenb\u00e4ck, M., Felsberg, M.: Roma: robust dense feature matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19790\u201319800 (2024)","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"4_CR13","unstructured":"Esteves, C., Allen-Blanchette, C., Zhou, X., Daniilidis, K.: Polar transformer networks. In: International Conference on Learning Representations (ICLR) (2018)"},{"issue":"59","key":"4_CR14","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(59), 1\u201335 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"4_CR15","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1109\/LRA.2021.3060707","volume":"6","author":"D Gehrig","year":"2021","unstructured":"Gehrig, D., R\u00fcegg, M., Gehrig, M., Hidalgo-Carri\u00f3, J., Scaramuzza, D.: Combining events and frames using recurrent asynchronous multimodal networks for monocular depth prediction. IEEE Robot. Autom. Lett. 6(2), 2822\u20132829 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"4_CR16","unstructured":"He, X., et al.: Matchanything: universal cross-modality image matching with large-scale pre-training (2025)"},{"issue":"7","key":"4_CR17","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1016\/j.media.2012.05.008","volume":"16","author":"MP Heinrich","year":"2012","unstructured":"Heinrich, M.P., et al.: Mind: modality independent neighbourhood descriptor for multi-modal deformable registration. Med. Image Anal. 16(7), 1423\u20131435 (2012)","journal-title":"Med. Image Anal."},{"key":"4_CR18","unstructured":"Huang, M., et al.: The QXS-SAROPT dataset for deep learning in SAR-optical data fusion. arXiv preprint arXiv:2103.08259 (2021)"},{"key":"4_CR19","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.inffus.2021.02.012","volume":"73","author":"X Jiang","year":"2021","unstructured":"Jiang, X., Ma, J., Xiao, G., Shao, Z., Guo, X.: A review of multimodal image matching: methods and applications. Inf. Fusion 73, 22\u201371 (2021)","journal-title":"Inf. Fusion"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Juvekar, P., et al.: Remind: the brain resection multimodal imaging database. medRxiv (2023)","DOI":"10.1101\/2023.09.14.23295596"},{"key":"4_CR21","unstructured":"Khemakhem, I., Kingma, D., Monti, R., Hyvarinen, A.: Variational autoencoders and nonlinear ICA: a unifying framework. In: International Conference on Artificial Intelligence and Statistics, pp. 2207\u20132217. PMLR (2020)"},{"key":"4_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"4_CR23","unstructured":"Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improved variational inference with inverse autoregressive flow. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Lee, J.A., Liu, P., Cheng, J., Fu, H.: A deep step pattern representation for multimodal retinal image registration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5077\u20135086 (2019)","DOI":"10.1109\/ICCV.2019.00518"},{"key":"4_CR25","volume":"106","author":"X Li","year":"2022","unstructured":"Li, X., et al.: Mcanet: a joint semantic segmentation framework of optical and SAR images for land use classification. Int. J. Appl. Earth Obs. Geoinf. 106, 102638 (2022)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Pollefeys, M.: Lightglue: local feature matching at light speed. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17627\u201317638 (2023)","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Liu, J., Li, X., Wei, Q., Xu, J., Ding, D.: Semi-supervised keypoint detector and descriptor for retinal image matching. In: European Conference on Computer Vision, pp. 593\u2013609. Springer (2022)","DOI":"10.1007\/978-3-031-19803-8_35"},{"key":"4_CR28","unstructured":"Liu, W., et al.: Modality-aware feature matching: a comprehensive review of single-and cross-modality techniques. arXiv preprint arXiv:2507.22791 (2025)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Mind the gap: aligning vision foundation models to image feature matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20313\u201320323 (2025)","DOI":"10.1109\/ICCV51701.2025.01889"},{"key":"4_CR30","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"4_CR31","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. Vision 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Contextdesc: local descriptor augmentation with cross-modality context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2527\u20132536 (2019)","DOI":"10.1109\/CVPR.2019.00263"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Aslfeat: learning local features of accurate shape and localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6589\u20136598 (2020)","DOI":"10.1109\/CVPR42600.2020.00662"},{"issue":"10","key":"4_CR34","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","volume":"34","author":"BH Menze","year":"2014","unstructured":"Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Med. Imaging 34(10), 1993\u20132024 (2014)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Mishchuk, A., Mishkin, D., Matas, J., Perdoch, M.: Repeatability is not enough: learning affine regions via discriminability. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9838\u20139846 (2018)","DOI":"10.1007\/978-3-030-01240-3_18"},{"key":"4_CR36","unstructured":"Mishchuk, A., Mishkin, D., Radenovi\u0107, F., Matas, J.: Working hard to know your neighbor\u2019s margins: local descriptor learning loss. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 4826\u20134837 (2017)"},{"key":"4_CR37","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de\u00a0Vries, H., Dumoulin, V., Courville, A.: Film: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: Learning to match 2D keypoints across preoperative MR and intraoperative ultrasound. In: International Workshop on Advances in Simplifying Medical Ultrasound, pp. 78\u201387. Springer (2024)","DOI":"10.1007\/978-3-031-73647-6_8"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Ren, J., Jiang, X., Li, Z., Liang, D., Zhou, X., Bai, X.: Minima: modality invariant image matching. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23059\u201323068 (2025)","DOI":"10.1109\/CVPR52734.2025.02147"},{"key":"4_CR41","unstructured":"Revaud, J., DeTone, D., Cabon, Y., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: R2D2: reliable and repeatable detector and descriptor. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 12405\u201312415 (2019)"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Santarossa, M., et al.: Medregnet: unsupervised multimodal retinal-image registration with GANs and ranking loss. In: Medical Imaging 2022: Image Processing, vol. 12032, pp. 321\u2013333. SPIE (2022)","DOI":"10.1117\/12.2607653"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: Loftr: detector-free local feature matching with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8922\u20138931 (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Tian, Y., Fan, B., Wu, F.: Sosnet: second order similarity regularization for local descriptor learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11016\u201311025 (2019)","DOI":"10.1109\/CVPR.2019.01127"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Tursynbek, N., Greer, H., Demir, B., Niethammer, M.: Guiding registration with emergent similarity from pre-trained diffusion models. arXiv preprint arXiv:2506.02419 (2025)","DOI":"10.1007\/978-3-032-04965-0_23"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Tuzcuo\u011flu, \u00d6., K\u00f6ksal, A., Sofu, B., Kalkan, S., Alatan, A.A.: Xoftr: cross-modal feature matching transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4275\u20134286 (2024)","DOI":"10.1109\/CVPRW63382.2024.00431"},{"key":"4_CR48","first-page":"14254","volume":"33","author":"M Tyszkiewicz","year":"2020","unstructured":"Tyszkiewicz, M., Fua, P., Trulls, E.: Disk: learning local features with policy gradient. Adv. Neural. Inf. Process. Syst. 33, 14254\u201314265 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Verdie, Y., Yi, K., Fua, P., Lepetit, V.: Tilde: a temporally invariant learned detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5279\u20135288 (2015)","DOI":"10.1109\/CVPR.2015.7299165"},{"key":"4_CR50","unstructured":"Worrall, D., Garbin, S., Turmukhambetov, D., Brostow, G.J.: Steerers: learning equivariant keypoint descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10302\u201310311 (2020)"},{"issue":"7","key":"4_CR51","doi-asserted-by":"publisher","first-page":"3875","DOI":"10.1002\/mp.12268","volume":"44","author":"Y Xiao","year":"2017","unstructured":"Xiao, Y., Fortin, M., Unsg\u00e5rd, G., Rivaz, H., Reinertsen, I.: Re trospective evaluation of cerebral tumors (resect): a clinical database of pre-operative MRI and intra-operative ultrasound in low-grade glioma surgeries. Med. Phys. 44(7), 3875\u20133882 (2017)","journal-title":"Med. Phys."},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: Lift: learned invariant feature transform. In: European Conference on Computer Vision (ECCV), pp. 467\u2013483 (2016)","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Delivering arbitrary-modal semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1136\u20131147 (2023)","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"4_CR54","first-page":"1","volume":"72","author":"X Zhao","year":"2023","unstructured":"Zhao, X., Wu, X., Chen, W., Chen, P.C., Xu, Q., Li, Z.: Aliked: a lighter keypoint and descriptor extraction network via deformable transformation. IEEE Trans. Instrum. Meas. 72, 1\u201316 (2023)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Zuiderveld, K.: Contrast limited adaptive histogram equalization. In: Graphics Gems IV, pp. 474\u2013485. Academic Press (1994)","DOI":"10.1016\/B978-0-12-336156-1.50061-6"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37174-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:12:31Z","timestamp":1789715551000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_4","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":"19 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}