{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:32Z","timestamp":1771244972475,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569496","type":"print"},{"value":"9789819569502","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\/978-981-95-6950-2_32","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:13Z","timestamp":1771243153000},"page":"448-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FFMatch: A FilterFormer-Based Network for\u00a0Accurate Multimodal Image Matching"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5555-5236","authenticated-orcid":false,"given":"Yun","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4333-5591","authenticated-orcid":false,"given":"Jiayi","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3230-5653","authenticated-orcid":false,"given":"Junhui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3508-4646","authenticated-orcid":false,"given":"Nan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0568-2637","authenticated-orcid":false,"given":"Zongxiao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8101-8629","authenticated-orcid":false,"given":"Qing","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"32_CR1","doi-asserted-by":"publisher","unstructured":"Alahi, A., Ortiz, R., Vandergheynst, P.: Freak: fast retina keypoint. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 510\u2013517. IEEE (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6247715","DOI":"10.1109\/CVPR.2012.6247715"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Brown, M., S\u00fcsstrunk, S.: Multi-spectral sift for scene category recognition. In: CVPR 2011, pp. 177\u2013184. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995637"},{"key":"32_CR3","doi-asserted-by":"publisher","unstructured":"Dai, K., et al.: DSAP: dynamic sparse attention perception matcher for accurate local feature matching. IEEE Trans. Instrum. Meas. 73, 1\u201316 (2024). https:\/\/doi.org\/10.1109\/TIM.2024.3370781","DOI":"10.1109\/TIM.2024.3370781"},{"key":"32_CR4","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":"32_CR5","doi-asserted-by":"publisher","unstructured":"Di, Y., et al.: UFM: unified feature matching pre-training with multi-modal image assistants. PLoS ONE 20(3), e0319051 (2025). https:\/\/doi.org\/10.1371\/journal.pone.0319051","DOI":"10.1371\/journal.pone.0319051"},{"key":"32_CR6","doi-asserted-by":"publisher","unstructured":"Di, Y., et al.: Femip: detector-free feature matching for multimodal images with policy gradient. Appl. Intell. 53(20), 24068\u201324088 (2023). https:\/\/doi.org\/10.1007\/s10489-023-04659-5","DOI":"10.1007\/s10489-023-04659-5"},{"key":"32_CR7","doi-asserted-by":"publisher","unstructured":"Di, Y., et al.: Mivi: multi-stage feature matching for infrared and visible image. Vis. Comput. 40(3), 1839\u20131851 (2024). https:\/\/doi.org\/10.1007\/s00371-023-02889-9","DOI":"10.1007\/s00371-023-02889-9"},{"key":"32_CR8","doi-asserted-by":"publisher","unstructured":"Giang, K.T., Song, S., Jo, S.: Topicfm: robust and interpretable topic-assisted feature matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2447\u20132455 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i2.25341","DOI":"10.1609\/aaai.v37i2.25341"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Hu, M., Sun, B., Zhang, F., Li, S.: HLDD: hierarchically learned detector and descriptor for robust image matching. IEEE Trans. Image Process. (2025)","DOI":"10.1109\/TIP.2025.3568310"},{"key":"32_CR10","doi-asserted-by":"publisher","unstructured":"Huang, D., et al.: Adaptive assignment for geometry aware local feature matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5425\u20135434 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00525","DOI":"10.1109\/CVPR52729.2023.00525"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Jiao, B., Han, J., Chen, L.: A modified conjugate gradient algorithm with sufficient descent. In: 2011 Fourth International Joint Conference on Computational Sciences and Optimization, pp. 175\u2013177. IEEE (2011)","DOI":"10.1109\/CSO.2011.38"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, R., Li, G., Li, T.H.: SDE2D: semantic-guided discriminability enhancement feature detector and descriptor. IEEE Trans. Multimedia (2024)","DOI":"10.1109\/TMM.2024.3521748"},{"key":"32_CR13","first-page":"17346","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Han, K., Li, S., Prisacariu, V.: Dual-resolution correspondence networks. Adv. Neural. Inf. Process. Syst. 33, 17346\u201317357 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR14","doi-asserted-by":"publisher","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 (2022). https:\/\/doi.org\/10.1016\/j.jag.2021.102638","DOI":"10.1016\/j.jag.2021.102638"},{"key":"32_CR15","doi-asserted-by":"publisher","unstructured":"Liao, Y., et al.: Feature matching and position matching between optical and SAR with local deep feature descriptor. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 15, 448\u2013462 (2022). https:\/\/doi.org\/10.1109\/JSTARS.2021.3134676","DOI":"10.1109\/JSTARS.2021.3134676"},{"key":"32_CR16","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"},{"issue":"2","key":"32_CR17","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(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"32_CR18","doi-asserted-by":"publisher","first-page":"3509","DOI":"10.1109\/TMM.2022.3162115","volume":"25","author":"J Ma","year":"2022","unstructured":"Ma, J., Wang, Y., Fan, A., Xiao, G., Chen, R.: Correspondence attention transformer: a context-sensitive network for two-view correspondence learning. IEEE Trans. Multimedia 25, 3509\u20133524 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"32_CR19","doi-asserted-by":"publisher","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021). https:\/\/doi.org\/10.1145\/3503250","DOI":"10.1145\/3503250"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Potje, G., Cadar, F., Araujo, A., Martins, R., Nascimento, E.R.: Enhancing deformable local features by jointly learning to detect and describe keypoints. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1306\u20131315 (2023)","DOI":"10.1109\/CVPR52729.2023.00132"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Potje, G., Cadar, F., Araujo, A., Martins, R., Nascimento, E.R.: Xfeat: accelerated features for lightweight image matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2682\u20132691 (2024)","DOI":"10.1109\/CVPR52733.2024.00259"},{"key":"32_CR22","doi-asserted-by":"publisher","unstructured":"Schmitt, M., Hughes, L., Qiu, C., Zhu, X.: Sen12ms\u2013a curated dataset of georeferenced multi-spectral sentinel-1\/2 imagery for deep learning and data fusion. arxiv 2019. arXiv preprint arXiv:1906.07789 (2019). https:\/\/doi.org\/10.5194\/isprs-annals-IV-2-W7-153-2019","DOI":"10.5194\/isprs-annals-IV-2-W7-153-2019"},{"key":"32_CR23","doi-asserted-by":"publisher","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.445","DOI":"10.1109\/CVPR.2016.445"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: European Conference on Computer Vision, pp. 746\u2013760. Springer (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"32_CR25","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":"32_CR26","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":"32_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., He, X., Peng, S., Tan, D., Zhou, X.: Efficient loftr: semi-dense local feature matching with sparse-like speed. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21666\u201321675 (2024)","DOI":"10.1109\/CVPR52733.2024.02047"},{"key":"32_CR28","unstructured":"Xiao, L., Yang, X., Lan, X., Wang, Y., Xu, C.: Towards visual grounding: a survey. arXiv preprint arXiv:2412.20206 (2024)"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: Mvsnet: depth inference for unstructured multi-view stereo. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Ye, P., Li, B., Li, Y., Chen, T., Fan, J., Ouyang, W.: b-darts: beta-decay regularization for differentiable architecture search. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10874\u201310883 (2022)","DOI":"10.1109\/CVPR52688.2022.01060"},{"key":"32_CR31","doi-asserted-by":"publisher","unstructured":"Zhao, X., Wu, X., Miao, J., Chen, W., Chen, P.C., Li, Z.: Alike: accurate and lightweight keypoint detection and descriptor extraction. IEEE Trans. Multimedia 25, 3101\u20133112 (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3155927","DOI":"10.1109\/TMM.2022.3155927"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Cheng, X., Zhai, X., Xue, L., Du, S.: Csformer: cross-scale transformer for feature matching. In: 2023 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), pp.\u00a01\u20136. IEEE (2023). https:\/\/api.semanticscholar.org\/CorpusID:269172442","DOI":"10.1109\/ICSMD60522.2023.10490714"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6950-2_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:18Z","timestamp":1771243158000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_32","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":"17 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}