{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:23:55Z","timestamp":1743006235852,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463075"},{"type":"electronic","value":"9783031463082"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46308-2_6","type":"book-chapter","created":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:01:24Z","timestamp":1698602484000},"page":"66-78","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Incorporating Global Correlation and Local Aggregation for Efficient Visual Localization"],"prefix":"10.1007","author":[{"given":"Dong","family":"Xie","sequence":"first","affiliation":[]},{"given":"Jianfeng","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Zhenbo","family":"Song","sequence":"additional","affiliation":[]},{"given":"Xuanzhu","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Computer Vision \u2013 ECCV 2006","author":"H Bay","year":"2006","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404\u2013417. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_32"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Brachmann, E., et al.: DSAC-differentiable RANSAC for camera localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6684\u20136692 (2017)","DOI":"10.1109\/CVPR.2017.267"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Learning less is more-6D camera localization via 3D surface regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4654\u20134662 (2018)","DOI":"10.1109\/CVPR.2018.00489"},{"issue":"4","key":"6_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_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":"6_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"6_CR8","unstructured":"Fan, H., Zhou, Y., Li, A., Gao, S., Li, J., Guo, Y.: Visual localization using semantic segmentation and depth prediction. arXiv preprint arXiv:2005.11922 (2020)"},{"issue":"6","key":"6_CR9","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":"6_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Y., Hugonot, J., Fua, P., Salzmann, M.: Segmentation-driven 6D object pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3385\u20133394 (2019)","DOI":"10.1109\/CVPR.2019.00350"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: VS-Net: voting with segmentation for visual localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6101\u20136111 (2021)","DOI":"10.1109\/CVPR46437.2021.00604"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Larsson, M., Stenborg, E., Toft, C., Hammarstrand, L., Sattler, T., Kahl, F.: Fine-grained segmentation networks: self-supervised segmentation for improved long-term visual localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 31\u201341 (2019)","DOI":"10.1109\/ICCV.2019.00012"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, S., Zhao, Y., Verbeek, J., Kannala, J.: Hierarchical scene coordinate classification and regression for visual localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11983\u201311992 (2020)","DOI":"10.1109\/CVPR42600.2020.01200"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"6_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":"6_CR17","unstructured":"Mehta, S., Rastegari, M.: Separable self-attention for mobile vision transformers. arXiv preprint arXiv:2206.02680 (2022)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., et al.: KinectFusion: real-time dense surface mapping and tracking. In: 2011 10th IEEE International Symposium on Mixed and Augmented Reality, pp. 127\u2013136. IEEE (2011)","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: PVNet: pixel-wise voting network for 6DoF pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4561\u20134570 (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, 5\u20139 October 2015, Proceedings, Part III 18, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"6_CR21","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":"6_CR22","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"6_CR23","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":"6_CR24","doi-asserted-by":"crossref","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Fast image-based localization using direct 2D-to-3D matching. In: 2011 International Conference on Computer Vision, pp. 667\u2013674. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126302"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Improving image-based localization by active correspondence search. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) Computer Vision-ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, 7\u201313 October 2012, Proceedings, Part I 12, vol. 7572, pp. 752\u2013765. Springer, Cham (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_54","DOI":"10.1007\/978-3-642-33718-5_54"},{"issue":"9","key":"6_CR26","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TPAMI.2016.2611662","volume":"39","author":"T Sattler","year":"2016","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Efficient & effective prioritized matching for large-scale image-based localization. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1744\u20131756 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR27","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"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2930\u20132937 (2013)","DOI":"10.1109\/CVPR.2013.377"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Stenborg, E., Toft, C., Hammarstrand, L.: Long-term visual localization using semantically segmented images. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6484\u20136490. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463150"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Valentin, J., Nie\u00dfner, M., Shotton, J., Fitzgibbon, A., Izadi, S., Torr, P.H.: Exploiting uncertainty in regression forests for accurate camera relocalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4400\u20134408 (2015)","DOI":"10.1109\/CVPR.2015.7299069"},{"key":"6_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR32","unstructured":"Wu, C.: VisualSFM: a visual structure from motion system (2011). http:\/\/www.cs.washington.edu\/homes\/ccwu\/vsfm"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"6_CR34","unstructured":"Xu, Y., et al.: SelfVoxeLO: self-supervised lidar odometry with voxel-based deep neural networks. In: Conference on Robot Learning, pp. 115\u2013125. PMLR (2021)"},{"key":"6_CR35","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"6_CR36","unstructured":"Yu, X., Zhuang, Z., Koniusz, P., Li, H.: 6DoF object pose estimation via differentiable proxy voting loss. arXiv preprint arXiv:2002.03923 (2020)"},{"key":"6_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-642-15555-0_31","volume-title":"Computer Vision \u2013 ECCV 2010","author":"G Zhang","year":"2010","unstructured":"Zhang, G., Dong, Z., Jia, J., Wong, T.-T., Bao, H.: Efficient non-consecutive feature tracking for structure-from-motion. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 422\u2013435. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_31"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zhong, Z., et al.: Squeeze-and-attention networks for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13065\u201313074 (2020)","DOI":"10.1109\/CVPR42600.2020.01308"},{"key":"6_CR39","unstructured":"Zhou, G., Bescos, B., Dymczyk, M., Pfeiffer, M., Neira, J., Siegwart, R.: Dynamic objects segmentation for visual localization in urban environments. arXiv preprint arXiv:1807.02996 (2018)"},{"key":"6_CR40","unstructured":"Zhu, S., et al.: Parallel structure from motion from local increment to global averaging. arXiv preprint arXiv:1702.08601 (2017)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Liu, J., Nie, Q., Liu, Y., Wang, C.: NeRF-Loc: visual localization with conditional neural radiance field. CoRR abs\/2304.07979 (2023)","DOI":"10.1109\/ICRA48891.2023.10161420"},{"key":"6_CR42","doi-asserted-by":"publisher","unstructured":"Zhou, Q., Agostinho, S., Osep, A., Leal-Taix e, L.: Is geometry enough for matching in visual localization? In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022\u201317th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part X. LNCS, vol. 13670, pp. 407\u2013425. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_24","DOI":"10.1007\/978-3-031-20080-9_24"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46308-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T18:02:14Z","timestamp":1698602534000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46308-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463075","9783031463082"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46308-2_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.cn\/","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":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","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":"166","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":"41% - 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)"}}]}}