{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:25:56Z","timestamp":1765308356517,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62172290 and No.62472297"],"award-info":[{"award-number":["No.62172290 and No.62472297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["No.2024ZHCG0007"],"award-info":[{"award-number":["No.2024ZHCG0007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755091","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"3468-3476","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FlowTrack: Integrating Adjacent-Frame Motion Tracking and Adaptive Prediction for Robust Semi-Supervised VOS"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4518-8938","authenticated-orcid":false,"given":"Duolin","family":"Wang","sequence":"first","affiliation":[{"name":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7177-0975","authenticated-orcid":false,"given":"Guanyu","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3181-2699","authenticated-orcid":false,"given":"Yanli","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00130"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00304"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00551"},{"key":"e_1_3_2_2_7_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Cheng Ho Kei","year":"2021","unstructured":"Ho Kei Cheng, Yu-Wing Tai, and Chi-Keung Tang. 2021b. Rethinking space-time networks with improved memory coverage for efficient video object segmentation. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"Segment and track anything. arXiv preprint arXiv:2305.06558","author":"Cheng Yangming","year":"2023","unstructured":"Yangming Cheng, Liulei Li, Yuanyou Xu, Xiaodi Li, Zongxin Yang, Wenguan Wang, and Yi Yang. 2023a. Segment and track anything. arXiv preprint arXiv:2305.06558 (2023)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3219230"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_4"},{"key":"e_1_3_2_2_12_1","first-page":"29914","article-title":"Segment anything in high quality","volume":"36","author":"Ke Lei","year":"2023","unstructured":"Lei Ke, Mingqiao Ye, Martin Danelljan, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu, et al., 2023. Segment anything in high quality. Advances in Neural Information Processing Systems, Vol. 36 (2023), 29914-29934.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00142"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00614"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_27"},{"key":"e_1_3_2_2_17_1","volume-title":"Video object segmentation without temporal information","author":"Maninis K-K","year":"2018","unstructured":"K-K Maninis, Sergi Caelles, Yuhua Chen, Jordi Pont-Tuset, Laura Leal-Taix\u00e9, Daniel Cremers, and Luc Van Gool. 2018. Video object segmentation without temporal information. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 6 (2018), 1515-1530."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_2_2_20_1","volume-title":"Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels","author":"Seong Hongje","year":"2022","unstructured":"Hongje Seong, Junhyuk Hyun, and Euntai Kim. 2022. Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels. IEEE transactions on pattern analysis and machine intelligence, Vol. 45, 2 (2022), 2595-2612."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109399"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"e_1_3_2_2_23_1","volume-title":"Online adaptation of convolutional neural networks for video object segmentation. arXiv preprint arXiv:1706.09364","author":"Voigtlaender Paul","year":"2017","unstructured":"Paul Voigtlaender and Bastian Leibe. 2017. Online adaptation of convolutional neural networks for video object segmentation. arXiv preprint arXiv:1706.09364 (2017)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00408"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20200"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00893"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00224"},{"key":"e_1_3_2_2_29_1","volume-title":"Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968","author":"Yang Jinyu","year":"2023","unstructured":"Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, and Feng Zheng. 2023. Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)."},{"key":"e_1_3_2_2_30_1","volume-title":"Associating objects with scalable transformers for video object segmentation. arXiv preprint arXiv:2203.11442","author":"Yang Zongxin","year":"2022","unstructured":"Zongxin Yang, Jiaxu Miao, Xiaohan Wang, Yunchao Wei, and Yi Yang. 2022. Associating objects with scalable transformers for video object segmentation. arXiv preprint arXiv:2203.11442, Vol. 3 (2022)."},{"key":"e_1_3_2_2_31_1","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume":"34","author":"Yang Zongxin","year":"2021","unstructured":"Zongxin Yang, Yunchao Wei, and Yi Yang. 2021. Associating objects with transformers for video object segmentation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 2491-2502.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","first-page":"36324","article-title":"Decoupling features in hierarchical propagation for video object segmentation","volume":"35","author":"Yang Zongxin","year":"2022","unstructured":"Zongxin Yang and Yi Yang. 2022. Decoupling features in hierarchical propagation for video object segmentation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36324-36336.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_33_1","volume-title":"Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048","author":"Zhang Renrui","year":"2023","unstructured":"Renrui Zhang, Zhengkai Jiang, Ziyu Guo, Shilin Yan, Junting Pan, Xianzheng Ma, Hao Dong, Peng Gao, and Hongsheng Li. 2023a. Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048 (2023)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00223"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:21:27Z","timestamp":1765308087000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":34,"alternative-id":["10.1145\/3746027.3755091","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755091","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}