{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:22:04Z","timestamp":1771950124223,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695347","type":"print"},{"value":"9783030695354","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_25","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"403-419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["MLIFeat: Multi-level Information Fusion Based Deep Local Features"],"prefix":"10.1007","author":[{"given":"Yuyang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinge","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shibiao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"25_CR2","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, 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"25_CR3","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R., Tard\u00f3s, J.D.: Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras. IEEE Trans. Rob. 33, 1255\u20131262 (2017)","journal-title":"IEEE Trans. Rob."},{"key":"25_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Forster, C., Pizzoli, M., Scaramuzza, D.: Svo: fast semi-direct monocular visual odometry. In: IEEE International Conference on Robotics and Automation (ICRA), vol. 2014, pp. 15\u201322. IEEE (2014)","DOI":"10.1109\/ICRA.2014.6906584"},{"key":"25_CR6","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","volume":"40","author":"J Engel","year":"2017","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40, 611\u2013625 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Sattler, T., et al.: Benchmarking 6dof outdoor visual localization in changing conditions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8601\u20138610 (2018)","DOI":"10.1109\/CVPR.2018.00897"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Taira, H., et al.: Inloc: indoor visual localization with dense matching and view synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7199\u20137209 (2018)","DOI":"10.1109\/CVPR.2018.00752"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Wang, X., Hua, Y., Kodirov, E., Hu, G., Garnier, R., Robertson, N.M.: Ranked list loss for deep metric learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5207\u20135216 (2019)","DOI":"10.1109\/CVPR.2019.00535"},{"key":"25_CR10","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91\u2013110 (2004)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: Orb: An efficient alternative to sift or surf. In: International Conference on Computer Vision, vol. 2011, pp. 2564\u20132571. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"25_CR12","unstructured":"Alcantarilla, P.F., Bartoli, A., Davison, A.J.: Kaze features. In: European Conference on Computer Vision, Springer (2012) 214\u2013227"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Dong, J., Soatto, S.: Domain-size pooling in local descriptors: Dsp-sift. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5097\u20135106 (2015)","DOI":"10.1109\/CVPR.2015.7299145"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Hardmeier, H., Sattler, T., Pollefeys, M.: Comparative evaluation of hand-crafted and learned local features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1482\u20131491 (2017)","DOI":"10.1109\/CVPR.2017.736"},{"key":"25_CR15","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":"25_CR16","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Sivic, J., Torii, A., Sattler, T.: D2-net: a trainable CNN for joint detection and description of local features. In: CVPR 2019 (2019)","DOI":"10.1109\/CVPR.2019.00828"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Tian, Y., Fan, B., Wu, F.: L2-net: deep learning of discriminative patch descriptor in euclidean space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 661\u2013669 (2017)","DOI":"10.1109\/CVPR.2017.649"},{"key":"25_CR18","unstructured":"Revaud, J., Weinzaepfel, P., De Souza, C., Pion, N., Csurka, G., Cabon, Y., Humenberger, M.: R2d2: Repeatable and reliable detector and descriptor. arXiv preprint arXiv:1906.06195 (2019)"},{"key":"25_CR19","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"},{"key":"25_CR20","unstructured":"Bian, J.W., et al.: An evaluation of feature matchers for fundamental matrix estimation. arXiv preprint arXiv:1908.09474 (2019)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Sattler, T., Weyand, T., Leibe, B., Kobbelt, L.: Image retrieval for image-based localization revisited. In: BMVC (2012)","DOI":"10.5244\/C.26.76"},{"key":"25_CR22","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":"25_CR23","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1023\/A:1008199403446","volume":"37","author":"C Schmid","year":"2000","unstructured":"Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. Int. J. Comput. Vision 37, 151\u2013172 (2000)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR24","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","volume":"27","author":"K Mikolajczyk","year":"2005","unstructured":"Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1615\u20131630 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR25","unstructured":"Mishchuk, A., Mishkin, D., Radenovic, F., Matas, J.: Working hard to know your neighbor\u2019s margins: local descriptor learning loss. In: Advances in Neural Information Processing Systems, pp. 4826\u20134837 (2017)"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Tian, Y., Yu, X., Fan, B., Wu, F., Heijnen, H., Balntas, V.: Sosnet: second order similarity regularization for local descriptor learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11016\u201311025 (2019)","DOI":"10.1109\/CVPR.2019.01127"},{"key":"25_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46466-4_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"KM Yi","year":"2016","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: learned invariant feature transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467\u2013483. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_28"},{"key":"25_CR28","unstructured":"Ono, Y., Trulls, E., Fua, P., Yi, K.M.: Lf-net: learning local features from images. In: Advances in Neural Information Processing Systems, pp. 6234\u20136244 (2018)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Noh, H., Araujo, A., Sim, J., Weyand, T., Han, B.: Large-scale image retrieval with attentive deep local features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3456\u20133465 (2017)","DOI":"10.1109\/ICCV.2017.374"},{"key":"25_CR30","unstructured":"Christiansen, P.H., Kragh, M.F., Brodskiy, Y., Karstoft, H.: Unsuperpoint: End-to-end unsupervised interest point detector and descriptor. arXiv preprint arXiv:1907.04011 (2019)"},{"key":"25_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"25_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR34","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":"25_CR35","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2911\u20132918. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Mishkin, D., Radenovic, F., Matas, J.: Repeatability is not enough: learning affine regions via discriminability. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 284\u2013300 (2018)","DOI":"10.1007\/978-3-030-01240-3_18"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of rgb-d slam systems. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 573\u2013580. IEEE (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"25_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073599","volume":"36","author":"A Knapitsch","year":"2017","unstructured":"Knapitsch, A., Park, J., Zhou, Q.Y., Koltun, V.: Tanks and temples: Benchmarking large-scale scene reconstruction. ACM Trans. Graph. (ToG) 36, 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"25_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/978-3-319-10578-9_5","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K Wilson","year":"2014","unstructured":"Wilson, K., Snavely, N.: Robust global translations with 1DSfM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 61\u201375. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_5"},{"key":"25_CR42","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/TPAMI.2016.2598331","volume":"39","author":"L Sv\u00e4rm","year":"2016","unstructured":"Sv\u00e4rm, L., Enqvist, O., Kahl, F., Oskarsson, M.: City-scale localization for cameras with known vertical direction. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1455\u20131461 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR43","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2016.445"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:59:24Z","timestamp":1614182364000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}