{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:01:01Z","timestamp":1775325661548,"version":"3.50.1"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263187","type":"print"},{"value":"9783031263194","type":"electronic"}],"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\/978-3-031-26319-4_8","type":"book-chapter","created":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T06:02:59Z","timestamp":1677823379000},"page":"123-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["CVLNet: Cross-view Semantic Correspondence Learning for\u00a0Video-Based Camera Localization"],"prefix":"10.1007","author":[{"given":"Yujiao","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,4]]},"reference":[{"key":"8_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1007\/978-3-319-46448-0_30","volume-title":"Computer Vision \u2013 ECCV 2016","author":"NN Vo","year":"2016","unstructured":"Vo, N.N., Hays, J.: Localizing and orienting street views using overhead imagery. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 494\u2013509. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_30"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Hu, S., Feng, M., Nguyen, R.M.H., Hee Lee, G.: CVM-Net: cross-view matching network for image-based ground-to-aerial geo-localization. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00758"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H.: Lending orientation to neural networks for cross-view geo-localization. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00577"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Regmi, K., Shah, M.: Bridging the domain gap for ground-to-aerial image matching. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00056"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Cai, S., Guo, Y., Khan, S., Hu, J., Wen, G.: Ground-to-aerial image geo-localization with a hard exemplar reweighting triplet loss. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00848"},{"key":"8_CR6","unstructured":"Shi, Y., Liu, L., Yu, X., Li, H.: Spatial-aware feature aggregation for image based cross-view geo-localization. In: Advances in Neural Information Processing Systems, pp. 10090\u201310100 (2019)"},{"key":"8_CR7","first-page":"11990","volume":"I","author":"Y Shi","year":"2020","unstructured":"Shi, Y., Yu, X., Liu, L., Zhang, T., Li, H.: Optimal feature transport for cross-view image geo-localization. Account. Audit. Account. I, 11990\u201311997 (2020)","journal-title":"Account. Audit. Account."},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yu, X., Campbell, D., Li, H.: Where am I looking at? Joint location and orientation estimation by cross-view matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4064\u20134072 (2020)","DOI":"10.1109\/CVPR42600.2020.00412"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Zhu, S., Yang, T., Chen, C.: Revisiting street-to-aerial view image geo-localization and orientation estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 756\u2013765 (2021)","DOI":"10.1109\/WACV48630.2021.00080"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Toker, A., Zhou, Q., Maximov, M., Leal-Taix\u00e9, L.: Coming down to earth: Satellite-to-street view synthesis for geo-localization. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00642"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Zhu, S., Yang, T., Chen, C.: Vigor: cross-view image geo-localization beyond one-to-one retrieval. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00364"},{"key":"8_CR12","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32, 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"8_CR13","unstructured":"https:\/\/developers.google.com\/maps\/documentation\/maps-static\/overview"},{"key":"8_CR14","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":"8_CR15","doi-asserted-by":"crossref","unstructured":"Kim, H.J., Dunn, E., Frahm, J.M.: Learned contextual feature reweighting for image geo-localization. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3251\u20133260 IEEE (2017)","DOI":"10.1109\/CVPR.2017.346"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H., Dai, Y.: Stochastic attraction-repulsion embedding for large scale image localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2570\u20132579 (2019)","DOI":"10.1109\/ICCV.2019.00266"},{"key":"8_CR17","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":"8_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-58548-8_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Ge","year":"2020","unstructured":"Ge, Y., Wang, H., Zhu, F., Zhao, R., Li, H.: Self-supervising fine-grained region similarities for large-scale image localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 369\u2013386. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_22"},{"key":"8_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/978-3-030-58604-1_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Wan, G., Hou, S., Yu, L., Wang, G., Rui, X., Song, S.: DA4AD: end-to-end deep attention-based visual localization for autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 271\u2013289. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_17"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Castaldo, F., Zamir, A., Angst, R., Palmieri, F., Savarese, S.: Semantic cross-view matching. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 9\u201317 (2015)","DOI":"10.1109\/ICCVW.2015.137"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Belongie, S., Hays, J.: Cross-view image geolocalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2013)","DOI":"10.1109\/CVPR.2013.120"},{"key":"8_CR22","unstructured":"Mousavian, A., Kosecka, J.: Semantic image based geolocation given a map. arXiv preprint arXiv:1609.00278 (2016)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Tian, Y., Chen, C., Shah, M.: Cross-view image matching for geo-localization in urban environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133616 (2017)","DOI":"10.1109\/CVPR.2017.216"},{"key":"8_CR24","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1007\/s11263-019-01186-0","volume":"128","author":"S Hu","year":"2020","unstructured":"Hu, S., Lee, G.H.: Image-based geo-localization using satellite imagery. Int. J. Comput. Vision 128, 1205\u20131219 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Shi, Y., Yu, X., Liu, L., Campbell, D., Koniusz, P., Li, H.: Accurate 3-DOF camera geo-localization via ground-to-satellite image matching. arXiv preprint arXiv:2203.14148 (2022)","DOI":"10.1109\/TPAMI.2022.3189702"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, S., Shah, M., Chen, C.: Transgeo: transformer is all you need for cross-view image geo-localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1162\u20131171 (2022)","DOI":"10.1109\/CVPR52688.2022.00123"},{"key":"8_CR27","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.isprsjprs.2022.03.018","volume":"188","author":"M Elhashash","year":"2022","unstructured":"Elhashash, M., Qin, R.: Cross-view slam solver: global pose estimation of monocular ground-level video frames for 3d reconstruction using a reference 3d model from satellite images. ISPRS J. Photogramm. Remote. Sens. 188, 62\u201374 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"8_CR28","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1109\/TIP.2022.3152046","volume":"31","author":"Y Guo","year":"2022","unstructured":"Guo, Y., Choi, M., Li, K., Boussaid, F., Bennamoun, M.: Soft exemplar highlighting for cross-view image-based geo-localization. IEEE Trans. Image Process. 31, 2094\u20132105 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhai, Q., Huang, R., Cheng, H.: Mutual generative transformer learning for cross-view geo-localization. arXiv preprint arXiv:2203.09135 (2022)","DOI":"10.3390\/rs15092221"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Bloesch, M., Omari, S., Hutter, M., Siegwart, R.: Robust visual inertial odometry using a direct ekf-based approach. In,: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS).pp. 298\u2013304. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353389"},{"key":"8_CR31","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1177\/0278364914554813","volume":"34","author":"S Leutenegger","year":"2015","unstructured":"Leutenegger, S., Lynen, S., Bosse, M., Siegwart, R., Furgale, P.: Keyframe-based visual-inertial odometry using nonlinear optimization. Int. J. Robot. Res. 34, 314\u2013334 (2015)","journal-title":"Int. J. Robot. Res."},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Chien, H.J., Chuang, C.C., Chen, C.Y., Klette, R.: When to use what feature? sift, surf, orb, or a-kaze features for monocular visual odometry. 2016 International Conference on Image and Vision Computing New Zealand (IVCNZ), pp. 1\u20136 (2016)","DOI":"10.1109\/IVCNZ.2016.7804434"},{"key":"8_CR33","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., Leonard, J.J.: Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Trans. Rob. 32, 1309\u20131332 (2016)","journal-title":"IEEE Trans. Rob."},{"key":"8_CR34","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":"8_CR35","doi-asserted-by":"crossref","unstructured":"Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In,: 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. pp. 225\u2013234. IEEE (2007)","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"8_CR36","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":"8_CR37","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":"8_CR38","doi-asserted-by":"crossref","unstructured":"Campos, C., Elvira, R., Rodr\u00edguez, J.J.G., Montiel, J.M., Tard\u00f3s, J.D.: Orb-slam3: an accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Trans. Robot. 37, 1874\u20131890 (2021)","DOI":"10.1109\/TRO.2021.3075644"},{"key":"8_CR39","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/LRA.2017.2653359","volume":"2","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R., Tard\u00f3s, J.D.: Visual-inertial monocular slam with map reuse. IEEE Robot. Autom. Lett. 2, 796\u2013803 (2017)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Wolcott, R.W., Eustice, R.M.: Visual localization within lidar maps for automated urban driving. 2014 IEEE\/RSJ International Conference on Intelligent Robots and System, pp. 176\u2013183 (2014)","DOI":"10.1109\/IROS.2014.6942558"},{"key":"8_CR41","unstructured":"Voodarla, M., Shrivastava, S., Manglani, S., Vora, A., Agarwal, S., Chakravarty, P.: S-BEV: semantic birds-eye view representation for weather and lighting invariant 3-DOF localization (2021)"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Stenborg, E., Toft, C., Hammarstrand, L.: Long-term visual localization using semantically segmented images. In,: IEEE International Conference on Robotics and Automation (ICRA). pp .6484\u20136490. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463150"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Stenborg, E., Sattler, T., Hammarstrand, L.: Using image sequences for long-term visual localization. In: 2020 International Conference on 3D Vision (3DV), pp. 938\u2013948 IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00104"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Vaca-Castano, G., Zamir, A.R., Shah, M.: City scale geo-spatial trajectory estimation of a moving camera. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1186\u20131193 IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247800"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Regmi, K., Shah, M.: Video geo-localization employing geo-temporal feature learning and GPS trajectory smoothing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12126\u201312135 (2021)","DOI":"10.1109\/ICCV48922.2021.01191"},{"key":"8_CR46","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s40903-015-0032-7","volume":"1","author":"K Yousif","year":"2015","unstructured":"Yousif, K., Bab-Hadiashar, A., Hoseinnezhad, R.: An overview to visual odometry and visual slam: applications to mobile robotics. Intell. Ind. Syst. 1, 289\u2013311 (2015)","journal-title":"Intell. Ind. Syst."},{"key":"8_CR47","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/MRA.2011.943233","volume":"18","author":"D Scaramuzza","year":"2011","unstructured":"Scaramuzza, D., Fraundorfer, F.: Visual odometry [tutorial]. IEEE Robot. Autom. Mag. 18, 80\u201392 (2011)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Gao, X., Wang, R., Demmel, N., Cremers, D.: Ldso: direct sparse odometry with loop closure. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2198\u20132204 IEEE (2018)","DOI":"10.1109\/IROS.2018.8593376"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Kasyanov, A., Engelmann, F., St\u00fcckler, J., Leibe, B.: Keyframe-based visual-inertial online slam with relocalization. In,: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6662\u20136669. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206581"},{"key":"8_CR50","unstructured":"Liu, D., Cui, Y., Guo, X., Ding, W., Yang, B., Chen, Y.: Visual localization for autonomous driving: mapping the accurate location in the city maze (2020)"},{"key":"8_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58571-6_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Hou","year":"2020","unstructured":"Hou, Y., Zheng, L., Gould, S.: Multiview Detection with Feature Perspective Transformation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 1\u201318. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_1"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Hou, Y., Zheng, L.: Multiview detection with shadow transformer (and view-coherent data augmentation). In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1673\u20131682 (2021)","DOI":"10.1145\/3474085.3475310"},{"key":"8_CR53","unstructured":"Vora, J., Dutta, S., Jain, K., Karthik, S., Gandhi, V.: Bringing generalization to deep multi-view detection. arXiv preprint arXiv:2109.12227 (2021)"},{"key":"8_CR54","unstructured":"Ma, J., Tong, J., Wang, S., Zhao, W., Zheng, L., Nguyen, C.: Voxelized 3d feature aggregation for multiview detection. arXiv preprint arXiv:2112.03471 (2021)"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lin, W., Chan, A.B.: Cross-view cross-scene multi-view crowd counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 557\u2013567 (2021)","DOI":"10.1109\/CVPR46437.2021.00062"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Chan, A.B.: Wide-area crowd counting via ground-plane density maps and multi-view fusion CNNS. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8297\u20138306 (2019)","DOI":"10.1109\/CVPR.2019.00849"},{"key":"8_CR57","doi-asserted-by":"publisher","first-page":"12837","DOI":"10.1609\/aaai.v34i07.6980","volume":"34","author":"Q Zhang","year":"2020","unstructured":"Zhang, Q., Chan, A.B.: 3d crowd counting via multi-view fusion with 3d gaussian kernels. Proceedings of the AAAI Conference on Artificial Intelligence. 34, 12837\u201312844 (2020)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Chan, A.B.: Wide-area crowd counting: Multi-view fusion networks for counting in large scenes. Int. J. Comput Vis. 130, 1938\u20131960 (2022)","DOI":"10.1007\/s11263-022-01626-4"},{"key":"8_CR59","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Persformer: 3D lane detection via perspective transformer and the openlane benchmark. arXiv preprint arXiv:2203.11089 (2022)","DOI":"10.1007\/978-3-031-19839-7_32"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Shi, Y., Campbell, D.J., Yu, X., Li, H.: Geometry-guided street-view panorama synthesis from satellite imagery. IEEE Trans. Pattern Anal. Mach. Intell. 44, 10009\u201310022(2022)","DOI":"10.1109\/TPAMI.2022.3140750"},{"key":"8_CR61","doi-asserted-by":"crossref","unstructured":"Shi, Y., Li, H.: Beyond cross-view image retrieval: Highly accurate vehicle localization using satellite image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17010\u201317020 (2022)","DOI":"10.1109\/CVPR52688.2022.01650"},{"key":"8_CR62","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":"8_CR63","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"8_CR64","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"8_CR65","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"8_CR67","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8_CR69","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26319-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T05:45:37Z","timestamp":1702014337000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26319-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263187","9783031263194"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26319-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"4 March 2023","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":"Macao","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"3.3","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":"2.6","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":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","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)"}}]}}