{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:45:36Z","timestamp":1785512736790,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFE0205700"],"award-info":[{"award-number":["2021YFE0205700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Research and Development Plan of China Railway","award":["P2023S001"],"award-info":[{"award-number":["P2023S001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276260, 62076235, and 62206290"],"award-info":[{"award-number":["62276260, 62076235, and 62206290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,25]]},"DOI":"10.1145\/3704323.3704359","type":"proceedings-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T08:25:22Z","timestamp":1736238322000},"page":"44-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MSAOT: Enhancing Video Object Segmentation with Memory-Selective Updates and High-Quality Mask Regeneration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9642-4878","authenticated-orcid":false,"given":"Yinglong","family":"Du","sequence":"first","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6063-4601","authenticated-orcid":false,"given":"Yifei","family":"Luo","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5888-8872","authenticated-orcid":false,"given":"Xu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0191-0829","authenticated-orcid":false,"given":"Tao","family":"Yu","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8293-3952","authenticated-orcid":false,"given":"Guibo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,1,7]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102759"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01400"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"e_1_3_3_1_6_2","volume-title":"DMAOT-VOT2023","author":"Cheng Y.","year":"2023","unstructured":"Y. Cheng, Z. Yang, Y. Xu, X. Li, J. Li, Y. Yang, and Y. Zhuang. 2023. DMAOT-VOT2023. https:\/\/github.com\/yamy-cheng\/DMAOT-VOTS2023\/tree\/master Accessed: 2024\/11\/26 11:27:10."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"e_1_3_3_1_8_2","unstructured":"Lei Ke Mingqiao Ye Martin Danelljan Yu-Wing Tai Chi-Keung Tang Fisher Yu et\u00a0al. 2024. Segment anything in high quality. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"e_1_3_3_1_11_2","first-page":"0","volume-title":"Proceedings of the European conference on computer vision (ECCV) workshops","author":"Kristan Matej","year":"2018","unstructured":"Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman Pflugfelder, Luka \u02c7Cehovin\u00a0Zajc, Tomas Vojir, Goutam Bhat, Alan Lukezic, Abdelrahman Eldesokey, et\u00a0al. 2018. The sixth visual object tracking vot2018 challenge results. In Proceedings of the European conference on computer vision (ECCV) workshops. 0\u20130."},{"key":"e_1_3_3_1_12_2","first-page":"1","volume-title":"Proceedings of the IEEE international conference on computer vision workshops","author":"Kristan Matej","year":"2015","unstructured":"Matej Kristan, Jiri Matas, Ales Leonardis, Michael Felsberg, Luka Cehovin, Gustavo Fernandez, Tomas Vojir, Gustav Hager, Georg Nebehay, and Roman Pflugfelder. 2015. The visual object tracking vot2015 challenge results. In Proceedings of the IEEE international conference on computer vision workshops. 1\u201323."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Bo Li Wei Wu Qiang Wang Fangyi Zhang Junliang Xing and Junjie Yan. 2018. SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.11703 (2018).","DOI":"10.1109\/CVPR.2019.00441"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68238-5_43"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9482-0"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.77"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"e_1_3_3_1_19_2","unstructured":"Yunyang Xiong Bala Varadarajan Lemeng Wu Xiaoyu Xiang Fanyi Xiao Chenchen Zhu Xiaoliang Dai Dilin Wang Fei Sun Forrest Iandola et\u00a0al. 2023. Efficientsam: Leveraged masked image pretraining for efficient segment anything. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.00863 (2023)."},{"key":"e_1_3_3_1_20_2","unstructured":"Ning Xu Linjie Yang Yuchen Fan Dingcheng Yue Yuchen Liang Jianchao Yang and Thomas Huang. 2018. Youtube-vos: A large-scale video object segmentation benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1809.03327 (2018)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Tianyang Xu Zhen-Hua Feng Xiao-Jun Wu and Josef Kittler. 2019. Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual object tracking. IEEE Transactions on Image Processing 28 11 (2019) 5596\u20135609.","DOI":"10.1109\/TIP.2019.2919201"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00525"},{"key":"e_1_3_3_1_23_2","unstructured":"Jinyu Yang Mingqi Gao Zhe Li Shang Gao Fangjing Wang and Feng Zheng. 2023. Track Anything: Segment Anything Meets Videos. arxiv:https:\/\/arXiv.org\/abs\/2304.11968\u00a0[cs.CV]"},{"key":"e_1_3_3_1_24_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Yang Zongxin","year":"2021","unstructured":"Zongxin Yang, Yunchao Wei, and Yi Yang. 2021. Associating Objects with Transformers for Video Object Segmentation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_25_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Yang Zongxin","year":"2022","unstructured":"Zongxin Yang and Yi Yang. 2022. Decoupling Features in Hierarchical Propagation for Video Object Segmentation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_26_2","unstructured":"Chaoning Zhang Dongshen Han Yu Qiao Jung\u00a0Uk Kim Sung-Ho Bae Seungkyu Lee and Choong\u00a0Seon Hong. 2023. Faster Segment Anything: Towards Lightweight SAM for Mobile Applications. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.14289 (2023)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"La Zhang Xu Zhao Haohua Du Jian Sun and Jinqiao Wang. 2024. Learning enhancing modality-invariant features for visible-infrared person re-identification. International Journal of Machine Learning and Cybernetics (2024) 1\u201319.","DOI":"10.1007\/s13042-024-02168-6"},{"key":"e_1_3_3_1_28_2","unstructured":"Xu Zhao Wenchao Ding Yongqi An Yinglong Du Tao Yu Min Li Ming Tang and Jinqiao Wang. 2023. Fast segment anything. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.12156 (2023)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28591"},{"key":"e_1_3_3_1_30_2","unstructured":"Jiawen Zhu Zhenyu Chen Zeqi Hao Shijie Chang Lu Zhang Dong Wang Huchuan Lu Bin Luo Jun-Yan He Jin-Peng Lan Hanyuan Chen and Chenyang Li. 2023. Tracking Anything in High Quality. arXiv:arXiv:2307.13974\u00a0[cs.CV]"}],"event":{"name":"ICCPR 2024: 2024 13th International Conference on Computing and Pattern Recognition","location":"Tianjin China","acronym":"ICCPR 2024"},"container-title":["Proceedings of the 2024 13th International Conference on Computing and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704323.3704359","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704323.3704359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:04Z","timestamp":1750295884000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704323.3704359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"references-count":29,"alternative-id":["10.1145\/3704323.3704359","10.1145\/3704323"],"URL":"https:\/\/doi.org\/10.1145\/3704323.3704359","relation":{},"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"2025-01-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}