{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:45:45Z","timestamp":1740181545450,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T00:00:00Z","timestamp":1655078400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T00:00:00Z","timestamp":1655078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-022-01212-y","type":"journal-article","created":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T18:03:39Z","timestamp":1655143419000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Based Deep Odometry Estimation on Point Clouds"],"prefix":"10.1007","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6984-0062","authenticated-orcid":false,"given":"Prince","family":"Kapoor","sequence":"first","affiliation":[]},{"given":"Farzan Erlik","family":"Nowruzi","sequence":"additional","affiliation":[]},{"given":"Dhanvin","family":"Kolhatkar","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Laganiere","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,13]]},"reference":[{"key":"1212_CR1","doi-asserted-by":"crossref","unstructured":"Hartley R, Zisserman A. Multiple view geometry in computer vision. Cambridge University Press, Cambridge. 2003.","DOI":"10.1017\/CBO9780511811685"},{"key":"1212_CR2","doi-asserted-by":"crossref","unstructured":"Zhang J, Singh SL. Lidar odometry and mapping in real-time. In: Robotics: Science and Systems. 2014.","DOI":"10.15607\/RSS.2014.X.007"},{"key":"1212_CR3","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations. 2015."},{"key":"1212_CR4","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"1212_CR5","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O. Voxelnet: End-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"1212_CR6","unstructured":"Qi CR, Su H, Mo K, Guibas LJ. Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017."},{"key":"1212_CR7","unstructured":"Qi CR, Yi L, Su H, Guibas LJ. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems. 2017."},{"key":"1212_CR8","doi-asserted-by":"crossref","unstructured":"Liu X, Qi CR, Guibas LJ. Flownet3d: Learning scene flow in 3d point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019.","DOI":"10.1109\/CVPR.2019.00062"},{"key":"1212_CR9","doi-asserted-by":"crossref","unstructured":"Nowruzi FE, Kolhatkar D, Kapoor P, Laganiere R. Point cloud based hierarchical deep odometry estimation. 2021. arXiv:2103.03394 [cs.CV]","DOI":"10.5220\/0010442900002932"},{"key":"1212_CR10","doi-asserted-by":"crossref","unstructured":"Mur-Artal R, Montiel JMM, Tardos JD. Orb-slam: a versatile and accurate monocular slam system. IEEE Transactions on Robotics. 2015.","DOI":"10.1109\/TRO.2015.2463671"},{"key":"1212_CR11","doi-asserted-by":"crossref","unstructured":"Engel J, Sch\u00f6ps T, Cremers D. Lsd-slam: Large-scale direct monocular slam. In: European Conference on Computer Vision. 2014; Springer.","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"1212_CR12","doi-asserted-by":"crossref","unstructured":"Chen SW, Nardari GV, Lee ES, Qu C, Liu X, Romero RAF, Kumar V. Sloam: Semantic lidar odometry and mapping for forest inventory. IEEE Robotics and Automation Letters. 2020.","DOI":"10.1109\/LRA.2019.2963823"},{"key":"1212_CR13","doi-asserted-by":"crossref","unstructured":"Chen Z, Jacobson A, S\u00fcnderhauf N, Upcroft B, Liu L, Shen C, Reid I, Milford M. Deep learning features at scale for visual place recognition. In: Robotics and Automation (ICRA), 2017 IEEE International Conference On. 2017; IEEE.","DOI":"10.1109\/ICRA.2017.7989366"},{"key":"1212_CR14","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. 2015.","DOI":"10.1109\/ICCV.2015.336"},{"key":"1212_CR15","doi-asserted-by":"crossref","unstructured":"Brahmbhatt S, Gu J, Kim K, Hays J, Kautz J. Geometry-aware learning of maps for camera localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.","DOI":"10.1109\/CVPR.2018.00277"},{"key":"1212_CR16","doi-asserted-by":"crossref","unstructured":"Wang S, Clark R, Wen H, Trigoni N. Deepvo: Towards end-to-end visual odometry with deep recurrent convolutional neural networks. 2017. arXiv:1709.08429","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"1212_CR17","doi-asserted-by":"crossref","unstructured":"Li Q, Chen S, Wang C, Li X, Wen C, Cheng M, Li J. Lo-net: Deep real-time lidar odometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.","DOI":"10.1109\/CVPR.2019.00867"},{"key":"1212_CR18","doi-asserted-by":"crossref","unstructured":"Cho Y, Kim G, Kim A. Deeplo: Geometry-aware deep lidar odometry. arXiv preprint arXiv:1902.10562. 2019.","DOI":"10.1109\/ICRA40945.2020.9197366"},{"key":"1212_CR19","doi-asserted-by":"crossref","unstructured":"Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T. Flownet 2.0: Evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.","DOI":"10.1109\/CVPR.2017.179"},{"key":"1212_CR20","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention Is All You Need. 2017."},{"key":"1212_CR21","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. 2021."},{"key":"1212_CR22","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S. End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. 2020; Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1212_CR23","doi-asserted-by":"crossref","unstructured":"Strudel R, Garcia R, Laptev I, Schmid C. Segmenter: Transformer for Semantic Segmentation. 2021.","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"1212_CR24","unstructured":"Sharma C, Kapil SR, Chapman D. Person Re-Identification with a Locally Aware Transformer. 2021."},{"key":"1212_CR25","doi-asserted-by":"crossref","unstructured":"Li X, Hou Y, Wang P, Gao Z, Xu M, Li W. Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry. 2020.","DOI":"10.1007\/s00521-020-05545-8"},{"issue":"2","key":"1212_CR26","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"M-H Guo","year":"2021","unstructured":"Guo M-H, Cai J-X, Liu Z-N, Mu T-J, Martin RR, Hu S-M. Pct: Point cloud transformer. Comput Vis Media. 2021;7(2):187\u201399. https:\/\/doi.org\/10.1007\/s41095-021-0229-5.","journal-title":"Comput. Vis. Media"},{"key":"1212_CR27","doi-asserted-by":"crossref","unstructured":"Han X-F, Jin Y-F, Cheng H-X, Xiao G-Q. Dual Transformer for Point Cloud Analysis. 2021.","DOI":"10.1109\/TMM.2022.3198318"},{"key":"1212_CR28","unstructured":"Damirchi H, Khorrambakht R, Taghirad HD. Exploring Self-Attention for Visual Odometry. 2020."},{"key":"1212_CR29","doi-asserted-by":"publisher","unstructured":"Kuo X-Y, Liu C, Lin K-C, Lee C-Y. Dynamic attention-based visual odometry. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2020;pp. 160\u2013169. https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00026.","DOI":"10.1109\/CVPRW50498.2020.00026"},{"key":"1212_CR30","unstructured":"Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN. Convolutional Sequence to Sequence Learning. 2017."},{"key":"1212_CR31","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R. Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016.","DOI":"10.1109\/CVPR.2016.89"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01212-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-022-01212-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01212-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T19:06:09Z","timestamp":1663614369000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-022-01212-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,13]]},"references-count":31,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["1212"],"URL":"https:\/\/doi.org\/10.1007\/s42979-022-01212-y","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2022,6,13]]},"assertion":[{"value":"6 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"333"}}