{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T19:10:08Z","timestamp":1745608208224,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819658145","type":"print"},{"value":"9789819658152","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-5815-2_11","type":"book-chapter","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:42:37Z","timestamp":1745606557000},"page":"201-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Local and\u00a0Global Feature Cross-Attention Multimodal Place Recognition"],"prefix":"10.1007","author":[{"given":"Lu","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaixin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaozhou","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Ali-Bey, A., Chaib-Draa, B., Giguere, P.: Mixvpr: feature mixing for visual place recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2998\u20133007 (2023)","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"11_CR2","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"},{"issue":"3","key":"11_CR3","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). Comput. Vis. Image Underst. 110(3), 346\u2013359 (2008)","journal-title":"Comput. Vis. Image Underst."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Berton, G., Trivigno, G., Caputo, B., Masone, C.: Eigenplaces: training viewpoint robust models for visual place recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11080\u201311090 (2023)","DOI":"10.1109\/ICCV51070.2023.01017"},{"issue":"9","key":"11_CR5","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1177\/0278364915614638","volume":"35","author":"N Carlevaris-Bianco","year":"2015","unstructured":"Carlevaris-Bianco, N., Ushani, A.K., Eustice, R.M.: University of Michigan North Campus long-term vision and lidar dataset. Int. J. Robot. Res. 35(9), 1023\u20131035 (2015)","journal-title":"Int. J. Robot. Res."},{"issue":"4","key":"11_CR6","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1109\/TRO.2022.3150683","volume":"38","author":"D Cattaneo","year":"2022","unstructured":"Cattaneo, D., Vaghi, M., Valada, A.: Lcdnet: deep loop closure detection and point cloud registration for lidar slam. IEEE Trans. Rob. 38(4), 2074\u20132093 (2022)","journal-title":"IEEE Trans. Rob."},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Maffra, F., Sa, I., Chli, M.: Only look once, mining distinctive landmarks from convnet for visual place recognition. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9\u201316. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202131"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol.\u00a01, pp. 886\u2013893. Ieee (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"11_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-030-58548-8_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Du","year":"2020","unstructured":"Du, J., Wang, R., Cremers, D.: DH3D: deep hierarchical 3d descriptors for robust large-scale 6DoF relocalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 744\u2013762. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_43"},{"key":"11_CR10","unstructured":"Facil, J.M., Olid, D., Montesano, L., Civera, J.: Condition-invariant multi-view place recognition. arXiv preprint arXiv:1902.09516 (2019)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Fan, Z., Song, Z., Liu, H., Lu, Z., He, J., Du, X.: Svt-net: super light-weight sparse voxel transformer for large scale place recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 551\u2013560 (2022)","DOI":"10.1609\/aaai.v36i1.19934"},{"issue":"3","key":"11_CR12","doi-asserted-by":"publisher","first-page":"4305","DOI":"10.1109\/LRA.2021.3067633","volume":"6","author":"S Garg","year":"2021","unstructured":"Garg, S., Milford, M.: Seqnet: learning descriptors for sequence-based hierarchical place recognition. IEEE Robot. Autom. Lett. 6(3), 4305\u20134312 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yan, Y., Xu, C., Kong, H.: Hitpr: hierarchical transformer for place recognition in point cloud. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2612\u20132618. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811737"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Komorowski, J.: Minkloc3d: point cloud based large-scale place recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1790\u20131799 (2021)","DOI":"10.1109\/WACV48630.2021.00183"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Komorowski, J., Wysocza\u0144ska, M., Trzcinski, T.: Minkloc++: lidar and monocular image fusion for place recognition. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9533373"},{"issue":"4","key":"11_CR17","doi-asserted-by":"publisher","first-page":"12038","DOI":"10.1109\/LRA.2022.3210880","volume":"7","author":"H Lai","year":"2022","unstructured":"Lai, H., Yin, P., Scherer, S.: Adafusion: visual-lidar fusion with adaptive weights for place recognition. IEEE Robot. Autom. Lett. 7(4), 12038\u201312045 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"11_CR18","unstructured":"Li, Y.J., Gladkova, M., Xia, Y., Wang, R., Cremers, D.: Vxp: voxel-cross-pixel large-scale image-lidar place recognition. arXiv preprint arXiv:2403.14594 (2024)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Seqlpd: Sequence matching enhanced loop-closure detection based on large-scale point cloud description for self-driving vehicles. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1218\u20131223. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8967875"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Lpd-net: 3d point cloud learning for large-scale place recognition and environment analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2831\u20132840 (2019)","DOI":"10.1109\/ICCV.2019.00292"},{"key":"11_CR21","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":"11_CR22","doi-asserted-by":"crossref","unstructured":"Lu, F., Lan, X., Zhang, L., Jiang, D., Wang, Y., Yuan, C.: Cricavpr: cross-image correlation-aware representation learning for visual place recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16772\u201316782 (2024)","DOI":"10.1109\/CVPR52733.2024.01587"},{"key":"11_CR23","unstructured":"Lu, Y., Yang, F., Chen, F., Xie, D.: Pic-net: point cloud and image collaboration network for large-scale place recognition. arXiv preprint arXiv:2008.00658 (2020)"},{"key":"11_CR24","unstructured":"Lun, L., et al.: BEVPlace: learning LiDAR-based place recognition using bird\u2019s eye view images. arXiv preprint arXiv:2302.14325 (2023)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Luo, L., et al.: Bevplace: learning lidar-based place recognition using bird\u2019s eye view images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8700\u20138709 (2023)","DOI":"10.1109\/ICCV51070.2023.00799"},{"issue":"8","key":"11_CR26","doi-asserted-by":"publisher","first-page":"8225","DOI":"10.1109\/TIE.2022.3229385","volume":"70","author":"J Ma","year":"2022","unstructured":"Ma, J., Chen, X., Xu, J., Xiong, G.: Seqot: a spatial-temporal transformer network for place recognition using sequential lidar data. IEEE Trans. Industr. Electron. 70(8), 8225\u20138234 (2022)","journal-title":"IEEE Trans. Industr. Electron."},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Ma, J., Xiong, G., Xu, J., Chen, X.: Cvtnet: a cross-view transformer network for lidar-based place recognition in autonomous driving environments. IEEE Transactions on Industrial Informatics (2023)","DOI":"10.1109\/TII.2023.3313635"},{"issue":"3","key":"11_CR28","doi-asserted-by":"publisher","first-page":"6958","DOI":"10.1109\/LRA.2022.3178797","volume":"7","author":"J Ma","year":"2022","unstructured":"Ma, J., Zhang, J., Xu, J., Ai, R., Gu, W., Chen, X.: Overlaptransformer: an efficient and yaw-angle-invariant transformer network for lidar-based place recognition. IEEE Robot. Autom. Lett. 7(3), 6958\u20136965 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Maddern, W., Pascoe, G., Linegar, C., Newman, P.: 1 Year, 1000km: the oxford robotcar dataset. Int. J. Robot. Res. (IJRR) 36(1), 3\u201315 (2017)","DOI":"10.1177\/0278364916679498"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Pan, Y., Xu, X., Li, W., Cui, Y., Wang, Y., Xiong, R.: Coral: colored structural representation for bi-modal place recognition. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2084\u20132091. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9635839"},{"key":"11_CR31","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"11_CR32","unstructured":"Shubodh, S., Omama, M., Zaidi, H., Parihar, U.S., Krishna, M.: Lip-loc: lidar image pretraining for cross-modal localization. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 948\u2013957 (2024)"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Thalagala, R.G., De\u00a0Silva, O., Jayasiri, A., Gubbels, A., Mann, G.K., Gosine, R.G.: Mun-frl: a visual-inertial-lidar dataset for aerial autonomous navigation and mapping. Int. J. Robot. Res. 02783649241238358 (2024)","DOI":"10.1177\/02783649241238358"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Lee, G.H.: Pointnetvlad: deep point cloud based retrieval for large-scale place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4470\u20134479 (2018)","DOI":"10.1109\/CVPR.2018.00470"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Vidanapathirana, K., Ramezani, M., Moghadam, P., Sridharan, S., Fookes, C.: Logg3d-net: locally guided global descriptor learning for 3d place recognition. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2215\u20132221. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811753"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Xia, Y., et al.: Casspr: cross attention single scan place recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8461\u20138472 (2023)","DOI":"10.1109\/ICCV51070.2023.00777"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Xia, Y., et al.: Soe-net: a self-attention and orientation encoding network for point cloud based place recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11348\u201311357 (2021)","DOI":"10.1109\/CVPR46437.2021.01119"},{"issue":"10","key":"11_CR38","doi-asserted-by":"publisher","first-page":"2870","DOI":"10.3390\/s20102870","volume":"20","author":"S Xie","year":"2020","unstructured":"Xie, S., Pan, C., Peng, Y., Liu, K., Ying, S.: Large-scale place recognition based on camera-lidar fused descriptor. Sensors 20(10), 2870 (2020)","journal-title":"Sensors"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, W., Xiao, C.: Pcan: 3d attention map learning using contextual information for point cloud based retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12436\u201312445 (2019)","DOI":"10.1109\/CVPR.2019.01272"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Xu, J., Xiong, G., Ma, J.: Lcpr: A multi-scale attention-based lidar-camera fusion network for place recognition. IEEE Robotics and Automation Letters (2023)","DOI":"10.1109\/LRA.2023.3346753"}],"container-title":["Lecture Notes in Computer Science","Computational Visual Media"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5815-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T18:42:57Z","timestamp":1745606577000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5815-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819658145","9789819658152"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5815-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Visual Media","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong SAR","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccvm.org\/2025\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}