{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:48Z","timestamp":1771244988146,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":35,"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_24","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:29Z","timestamp":1771243169000},"page":"335-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SeViMatch: A Detector-Based Image Matching Framework with\u00a0Semantic-Visual Fusion"],"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\/0009-0003-3508-4646","authenticated-orcid":false,"given":"Nan","family":"Chen","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\/0009-0002-4333-5591","authenticated-orcid":false,"given":"Jiayi","family":"Lyu","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":"24_CR1","doi-asserted-by":"crossref","unstructured":"Balntas, V., Lenc, K., Vedaldi, A., Mikolajczyk, K.: Hpatches: a benchmark and evaluation of handcrafted and learned local descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5173\u20135182 (2017)","DOI":"10.1109\/CVPR.2017.410"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Barroso-Laguna, A., Mikolajczyk, K.: Key. net: Keypoint detection by handcrafted and learned CNN filters revisited. IEEE Trans. Patt. Anal. Mach. Intell. 45(1), 698\u2013711 (2022)","DOI":"10.1109\/TPAMI.2022.3145820"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Cao, B., Araujo, A., Sim, J.: Unifying deep local and global features for image search. In: European Conference On Computer Vision, pp. 726\u2013743. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: richly-annotated 3d reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"24_CR5","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TIP.2022.3231135","volume":"32","author":"Y Deng","year":"2022","unstructured":"Deng, Y., Ma, J.: Redfeat: Recoupling detection and description for multimodal feature learning. IEEE Trans. Image Process. 32, 591\u2013602 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR6","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":"24_CR7","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., et al.: D2-net: a trainable CNN for joint description and detection of local features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8092\u20138101 (2019)","DOI":"10.1109\/CVPR.2019.00828"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Gleize, P., Wang, W., Feiszli, M.: Silk: simple learned keypoints. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22499\u201322508 (2023)","DOI":"10.1109\/ICCV51070.2023.02056"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"He, Y., et al.: Darkfeat: noise-robust feature detector and descriptor for extremely low-light raw images. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 826\u2013834 (2023)","DOI":"10.1609\/aaai.v37i1.25161"},{"key":"24_CR10","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":"24_CR11","doi-asserted-by":"crossref","unstructured":"Kanakis, M., Maurer, S., Spallanzani, M., Chhatkuli, A., Van\u00a0Gool, L.: Zippypoint: fast interest point detection, description, and matching through mixed precision discretization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6114\u20136123 (2023)","DOI":"10.1109\/CVPRW59228.2023.00651"},{"key":"24_CR12","unstructured":"Kingma, D.P.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"24_CR13","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":"24_CR14","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, L., Liu, L., Ran, Q., Xu, K., Guo, Y.: Decoupling makes weakly supervised local feature better. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15838\u201315848 (2022)","DOI":"10.1109\/CVPR52688.2022.01538"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: Megadepth: learning single-view depth prediction from internet photos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2041\u20132050 (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"24_CR16","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":"24_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Z., Shen, T., Zhou, L., Zhang, J., Yao, Y., Li, S., Fang, T., Quan, L.: Contextdesc: local descriptor augmentation with cross-modality context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2527\u20132536 (2019)","DOI":"10.1109\/CVPR.2019.00263"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Aslfeat: learning local features of accurate shape and localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6589\u20136598 (2020)","DOI":"10.1109\/CVPR42600.2020.00662"},{"issue":"5","key":"24_CR19","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: Orb-slam: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"24_CR20","unstructured":"Paszke, A.: Pytorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)"},{"key":"24_CR21","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":"24_CR22","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":"24_CR23","unstructured":"Revaud, J., De\u00a0Souza, C., Humenberger, M., Weinzaepfel, P.: R2d2: reliable and repeatable detector and descriptor. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"24_CR24","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":"24_CR25","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12716\u201312725 (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Sattler, T., Weyand, T., Leibe, B., Kobbelt, L.: Image retrieval for image-based localization revisited. In: BMVC. vol.\u00a01, p.\u00a04 (2012)","DOI":"10.5244\/C.26.76"},{"key":"24_CR27","doi-asserted-by":"publisher","first-page":"2776","DOI":"10.1109\/TIP.2023.3274482","volume":"32","author":"X Shen","year":"2023","unstructured":"Shen, X., Hu, Q., Li, X., Wang, C.: A detector-oblivious multi-arm network for keypoint matching. IEEE Trans. Image Process. 32, 2776\u20132785 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR28","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":"24_CR29","unstructured":"Wang, C., Zhang, G., Cheng, Z., Zhou, W.: Rethinking low-level features for interest point detection and description. In: Proceedings of the Asian Conference on Computer Vision, pp. 2059\u20132074 (2022)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Xue, F., Budvytis, I., Cipolla, R.: Sfd2: semantic-guided feature detection and description. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5206\u20135216 (2023)","DOI":"10.1109\/CVPR52729.2023.00504"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhao, X.: Mesa: matching everything by segmenting anything. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20217\u201320226 (2024)","DOI":"10.1109\/CVPR52733.2024.01911"},{"issue":"4","key":"24_CR32","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1007\/s11263-020-01399-8","volume":"129","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Sattler, T., Scaramuzza, D.: Reference pose generation for long-term visual localization via learned features and view synthesis. Int. J. Comput. Vision 129(4), 821\u2013844 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"24_CR33","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":"24_CR34","doi-asserted-by":"publisher","first-page":"3101","DOI":"10.1109\/TMM.2022.3155927","volume":"25","author":"X Zhao","year":"2022","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)","journal-title":"IEEE Trans. Multimedia"},{"key":"24_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113350","volume":"316","author":"F Zheng","year":"2025","unstructured":"Zheng, F., Cao, C., Zhang, Z., Sun, T., Zhang, J., Zhao, L.: Ada-matcher: a deep detector-based local feature matcher with adaptive weight sharing. Knowl.-Based Syst. 316, 113350 (2025)","journal-title":"Knowl.-Based Syst."}],"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_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:37Z","timestamp":1771243177000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_24","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"}}]}}