{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:10:02Z","timestamp":1755879002355,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T00:00:00Z","timestamp":1716508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Guangdong Technology International Cooperation Project Application","award":["2020A0505100024 and 2021A0505060001"],"award-info":[{"award-number":["2020A0505100024 and 2021A0505060001"]}]},{"name":"Xijiang Innovation Team Project","award":["XJCXTD3-2019-04B"],"award-info":[{"award-number":["XJCXTD3-2019-04B"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62273151, 61873096 and 62073145"],"award-info":[{"award-number":["62273151, 61873096 and 62073145"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Guangdong Basic and Applied Basic Research Foundation","award":["2020A1515011057 and 2021B1515420003"],"award-info":[{"award-number":["2020A1515011057 and 2021B1515420003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,24]]},"DOI":"10.1145\/3670105.3670152","type":"proceedings-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T18:29:36Z","timestamp":1722277776000},"page":"282-286","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-supervised Recurrent Visual Odometry, Depth Estimation, and Instance Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6178-0501","authenticated-orcid":false,"given":"Chujia","family":"Lin","sequence":"first","affiliation":[{"name":"South China University of Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8911-727X","authenticated-orcid":false,"given":"Yiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6275-759X","authenticated-orcid":false,"given":"An","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4166-6864","authenticated-orcid":false,"given":"Hongxia","family":"Gao","sequence":"additional","affiliation":[{"name":"South China University of Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2024,7,29]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432","author":"Ballas Nicolas","year":"2015","unstructured":"Nicolas Ballas, Li Yao, Chris Pal, and Aaron Courville. 2015. Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432 (2015)."},{"key":"e_1_3_2_1_2_1","volume-title":"Unsupervised scale-consistent depth and ego-motion learning from monocular video. Advances in neural information processing systems 32","author":"Bian Jiawang","year":"2019","unstructured":"Jiawang Bian, Zhichao Li, Naiyan Wang, Huangying Zhan, Chunhua Shen, Ming-Ming Cheng, and Ian Reid. 2019. Unsupervised scale-consistent depth and ego-motion learning from monocular video. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01484-6"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"e_1_3_2_1_5_1","volume-title":"MonoSLAM: Real-time single camera SLAM","author":"Davison J","year":"2007","unstructured":"Andrew\u00a0J Davison, Ian\u00a0D Reid, Nicholas\u00a0D Molton, and Olivier Stasse. 2007. MonoSLAM: Real-time single camera SLAM. IEEE transactions on pattern analysis and machine intelligence 29, 6 (2007), 1052\u20131067."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"e_1_3_2_1_7_1","volume-title":"Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems 27","author":"Eigen David","year":"2014","unstructured":"David Eigen, Christian Puhrsch, and Rob Fergus. 2014. Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_8_1","volume-title":"Direct sparse odometry","author":"Engel Jakob","year":"2017","unstructured":"Jakob Engel, Vladlen Koltun, and Daniel Cremers. 2017. Direct sparse odometry. IEEE transactions on pattern analysis and machine intelligence 40, 3 (2017), 611\u2013625."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007546"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461251"},{"key":"e_1_3_2_1_20_1","volume-title":"Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras","author":"Mur-Artal Raul","year":"2017","unstructured":"Raul Mur-Artal and Juan\u00a0D Tard\u00f3s. 2017. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras. IEEE transactions on robotics 33, 5 (2017), 1255\u20131262."},{"key":"e_1_3_2_1_21_1","volume-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems 28","author":"Shi Xingjian","year":"2015","unstructured":"Xingjian Shi, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-Kin Wong, and Wang-chun Woo. 2015. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings, Part II 16","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part II 16. Springer, 402\u2013419."},{"key":"e_1_3_2_1_23_1","volume-title":"Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras. Advances in neural information processing systems 34","author":"Teed Zachary","year":"2021","unstructured":"Zachary Teed and Jia Deng. 2021. Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras. Advances in neural information processing systems 34 (2021), 16558\u201316569."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00043"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"}],"event":{"name":"CNIOT 2024: 2024 5th International Conference on Computing, Networks and Internet of Things","acronym":"CNIOT 2024","location":"Tokyo Japan"},"container-title":["Proceedings of the 2024 5th International Conference on Computing, Networks and Internet of Things"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670105.3670152","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3670105.3670152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:52:45Z","timestamp":1755877965000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670105.3670152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,24]]},"references-count":25,"alternative-id":["10.1145\/3670105.3670152","10.1145\/3670105"],"URL":"https:\/\/doi.org\/10.1145\/3670105.3670152","relation":{},"subject":[],"published":{"date-parts":[[2024,5,24]]},"assertion":[{"value":"2024-07-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}