{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:23Z","timestamp":1755825023073,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","funder":[{"name":"Jiangsu Provincial Key Laboratory of Network and Information Security","award":["BM2003201"],"award-info":[{"award-number":["BM2003201"]}]},{"DOI":"10.13039\/501100006374","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242024k30022"],"award-info":[{"award-number":["2242024k30022"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"},{"DOI":"10.13039\/501100006374","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2022680"],"award-info":[{"award-number":["BE2022680"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061146001, 62372102, 62232004, 61972083, 62202096, 62072103"],"award-info":[{"award-number":["62061146001, 62372102, 62232004, 61972083, 62202096, 62072103"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733327","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"1886-1893","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Self-Supervised Fine-Grained Video Object Tracking with Dynamic Memory Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3650-5464","authenticated-orcid":false,"given":"Zihan","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9417-9599","authenticated-orcid":false,"given":"Changrui","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4447-7305","authenticated-orcid":false,"given":"Aibo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China and Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0164-2596","authenticated-orcid":false,"given":"Xiaolin","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China and Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_3_1","first-page":"11781","article-title":"Rethinking space-time networks with improved memory coverage for efficient video object segmentation","volume":"34","author":"Cheng Ho Kei","year":"2021","unstructured":"Ho Kei Cheng, Yu-Wing Tai, and Chi-Keung Tang. 2021. Rethinking space-time networks with improved memory coverage for efficient video object segmentation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 11781--11794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"volume-title":"Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Gan Chuang","key":"e_1_3_2_1_5_1","unstructured":"Chuang Gan, Boqing Gong, Kun Liu, Hao Su, and Leonidas J. Guibas. 2018. Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 1--2.","author":"Hu Yuan-Ting","key":"e_1_3_2_1_6_1","unstructured":"Yuan-Ting Hu, Jia-Bin Huang, and Alexander G. Schwing. 2018. VideoMatch: Matching based Video Object Segmentation. In Proceedings of the European Conference on Computer Vision (ECCV). 1--2."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00890"},{"key":"e_1_3_2_1_8_1","volume-title":"Space-time correspondence as a contrastive random walk. Advances in neural information processing systems","author":"Jabri Allan","year":"2020","unstructured":"Allan Jabri, Andrew Owens, and Alexei Efros. 2020. Space-time correspondence as a contrastive random walk. Advances in neural information processing systems, Vol. 33 (2020), 19545--19560."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00109"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00916"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"e_1_3_2_1_14_1","volume-title":"Self-supervised learning for video correspondence flow. arXiv preprint arXiv:1905.00875","author":"Lai Zihang","year":"2019","unstructured":"Zihang Lai and Weidi Xie. 2019. Self-supervised learning for video correspondence flow. arXiv preprint arXiv:1905.00875 (2019), 1--7."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01794"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00852"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00226"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00883"},{"key":"e_1_3_2_1_19_1","first-page":"3430","article-title":"Video object segmentation with adaptive feature bank and uncertain-region refinement","volume":"33","author":"Liang Yongqing","year":"2020","unstructured":"Yongqing Liang, Xin Li, Navid Jafari, and Jim Chen. 2020. Video object segmentation with adaptive feature bank and uncertain-region refinement. Advances in Neural Information Processing Systems, Vol. 33 (2020), 3430--3441.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings, Part III 16","author":"Lu Xiankai","year":"2020","unstructured":"Xiankai Lu, Wenguan Wang, Martin Danelljan, Tianfei Zhou, Jianbing Shen, and Luc Van Gool. 2020. Video object segmentation with episodic graph memory networks. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part III 16. Springer, 661--679."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00770"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.590"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00040"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01707"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00981"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:07:01Z","timestamp":1755749221000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733327"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"alternative-id":["10.1145\/3731715.3733327","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733327","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}