{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:12:27Z","timestamp":1755839547920,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012685"],"award-info":[{"award-number":["2023A1515012685"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","award":["GML-KF-22-28"],"award-info":[{"award-number":["GML-KF-22-28"]}]},{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002230"],"award-info":[{"award-number":["62002230"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592295","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"508-515","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Robust Deep Learning Enhanced Monocular SLAM System for Dynamic Environments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6216-2603","authenticated-orcid":false,"given":"Yaoqing","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7524-5999","authenticated-orcid":false,"given":"Sheng-Hua","family":"Zhong","sequence":"additional","affiliation":[{"name":"Shenzhen University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4499-0023","authenticated-orcid":false,"given":"Shuai","family":"Li","sequence":"additional","affiliation":[{"name":"University of Oulu, Finland and VTT-Technology Research Center of Finland, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4242-4840","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","author":"Badrinarayanan Vijay","year":"2017","unstructured":"Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence 39, 12 (2017), 2481\u20132495."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.410"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2860039"},{"key":"e_1_3_2_1_4_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, 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_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00271"},{"key":"e_1_3_2_1_6_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830 (2016)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965415"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463584"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.601246"},{"key":"e_1_3_2_1_13_1","volume-title":"Computer vision and image understanding 68, 2","author":"Hartley I","year":"1997","unstructured":"Richard\u00a0I Hartley and Peter Sturm. 1997. Triangulation. Computer vision and image understanding 68, 2 (1997), 146\u2013157."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340907"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_19_1","volume-title":"ASD-SLAM: A Novel Adaptive-Scale Descriptor Learning for Visual SLAM. In 2020 IEEE Intelligent Vehicles Symposium (IV). IEEE, 809\u2013816","author":"Ma Taiyuan","year":"2020","unstructured":"Taiyuan Ma, Yafei Wang, Zili Wang, Xulei Liu, and Huimin Zhang. 2020. ASD-SLAM: A Novel Adaptive-Scale Descriptor Learning for Visual SLAM. In 2020 IEEE Intelligent Vehicles Symposium (IV). IEEE, 809\u2013816."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.112"},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"R2d2: Reliable and repeatable detector and descriptor. Advances in neural information processing systems 32","author":"Revaud Jerome","year":"2019","unstructured":"Jerome Revaud, Cesar De\u00a0Souza, Martin Humenberger, and Philippe Weinzaepfel. 2019. R2d2: Reliable and repeatable detector and descriptor. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325044"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.695"},{"key":"e_1_3_2_1_29_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_30_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593691"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197349"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00917"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00115"}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Thessaloniki Greece","acronym":"ICMR '23"},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592295","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:30Z","timestamp":1750178250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":36,"alternative-id":["10.1145\/3591106.3592295","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592295","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}