{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:51:31Z","timestamp":1765309891365,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"Jiangsu Provincial Science and Technology Major Project","award":["BG2024042"],"award-info":[{"award-number":["BG2024042"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755256","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"3952-3961","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Query Selection Bias in Referring Video Object Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3817-3072","authenticated-orcid":false,"given":"Dingwei","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4543-2179","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing Forestry University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 659-667","author":"Chen Sihan","year":"2024","unstructured":"Sihan Chen, Yadang Chen, Yuhui Zheng, Zhi-Xin Yang, and Enhua Wu. 2024b. A transformer-based adaptive prototype matching network for few-shot semantic segmentation. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 659-667."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547761"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110266"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364056"},{"key":"e_1_3_2_1_7_1","volume-title":"Boosting Video Object Segmentation via Robust and Efficient Memory Network","author":"Chen Yadang","year":"2023","unstructured":"Yadang Chen, Dingwei Zhang, Yuhui Zheng, Zhi-Xin Yang, Enhua Wu, and Haixing Zhao. 2023. Boosting Video Object Segmentation via Robust and Efficient Memory Network. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence.","author":"Dai Longquan","year":"2025","unstructured":"Longquan Dai, He Wang, and Jinhui Tang. 2025a. AccCtr: Accelerating Training-Free Control For Text-to-Image Diffusion Models. In Proceedings of the International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01686"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284979"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"e_1_3_2_1_18_1","volume-title":"Joon-Young Lee, and Seon Joo Kim.","author":"Heo Miran","year":"2022","unstructured":"Miran Heo, Sukjun Hwang, Seoung Wug Oh, Joon-Young Lee, and Seon Joo Kim. 2022. Vita: Video instance segmentation via object token association. Advances in neural information processing systems, Vol. 35 (2022), 23109-23120."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1212303"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00548"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"e_1_3_2_1_22_1","unstructured":"Nikita Karaev Iurii Makarov Jianyuan Wang Natalia Neverova Andrea Vedaldi and Christian Rupprecht. 2024. CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. arxiv."},{"key":"e_1_3_2_1_23_1","first-page":"123","volume-title":"Perth","author":"Khoreva Anna","year":"2019","unstructured":"Anna Khoreva, Anna Rohrbach, and Bernt Schiele. 2019. Video object segmentation with language referring expressions. In Computer Vision-ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2-6, 2018, Revised Selected Papers, Part IV 14. Springer, 123-141."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00311"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02032"},{"key":"e_1_3_2_1_27_1","volume-title":"Clawcranenet: Leveraging object-level relation for text-based video segmentation. arXiv preprint arXiv:2103.10702","author":"Liang Chen","year":"2021","unstructured":"Chen Liang, Yu Wu, Yawei Luo, and Yi Yang. 2021a. Clawcranenet: Leveraging object-level relation for text-based video segmentation. arXiv preprint arXiv:2103.10702 (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation. arXiv preprint arXiv:2106.01061","author":"Liang Chen","year":"2021","unstructured":"Chen Liang, Yu Wu, Tianfei Zhou, Wenguan Wang, Zongxin Yang, Yunchao Wei, and Yi Yang. 2021b. Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation. arXiv preprint arXiv:2106.01061 (2021)."},{"key":"e_1_3_2_1_29_1","first-page":"4761","article-title":"Cross-modal progressive comprehension for referring segmentation","volume":"44","author":"Liu Si","year":"2021","unstructured":"Si Liu, Tianrui Hui, Shaofei Huang, Yunchao Wei, Bo Li, and Guanbin Li. 2021a. Cross-modal progressive comprehension for referring segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 4761-4775.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_30_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_31_1","unstructured":"Ze Liu Jia Ning Yue Cao Yixuan Wei Zheng Zhang Stephen Lin and Han Hu. 2021b. Video Swin Transformer. arXiv:2106.13230 [cs.CV] https:\/\/arxiv.org\/abs\/2106.13230"},{"key":"e_1_3_2_1_32_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Luo Zhuoyan","year":"2024","unstructured":"Zhuoyan Luo, Yicheng Xiao, Yong Liu, Shuyan Li, Yitong Wang, Yansong Tang, Xiu Li, and Yujiu Yang. 2024. Soc: Semantic-assisted object cluster for referring video object segmentation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00061"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"e_1_3_2_1_36_1","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan Zhaoyang Zeng Hao Zhang Feng Li Jie Yang Hongyang Li Qing Jiang and Lei Zhang. 2024. Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks. arXiv:2401.14159 [cs.CV] https:\/\/arxiv.org\/abs\/2401.14159"},{"key":"e_1_3_2_1_37_1","volume-title":"Urvos: Unified referring video object segmentation network with a large-scale benchmark. In Computer Vision-ECCV 2020: 16th European Conference","author":"Seo Seonguk","year":"2020","unstructured":"Seonguk Seo, Joon-Young Lee, and Bohyung Han. 2020. Urvos: Unified referring video object segmentation network with a large-scale benchmark. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XV 16. Springer, 208-223."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3413778"},{"key":"e_1_3_2_1_40_1","volume-title":"Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation","author":"Wang Chunyan","year":"2023","unstructured":"Chunyan Wang, Dong Zhang, Liyan Zhang, and Jinhui Tang. 2023. Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32828"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00240"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28465"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"e_1_3_2_1_50_1","volume-title":"Causal intervention for weakly-supervised semantic segmentation. Advances in neural information processing systems","author":"Zhang Dong","year":"2020","unstructured":"Dong Zhang, Hanwang Zhang, Jinhui Tang, Xian-Sheng Hua, and Qianru Sun. 2020a. Causal intervention for weakly-supervised semantic segmentation. Advances in neural information processing systems, Vol. 33 (2020), 655-666."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01144"}],"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\/3746027.3755256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:48:31Z","timestamp":1765309711000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3755256","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755256","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"}}]}}