{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:15:46Z","timestamp":1777655746501,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","funder":[{"name":"The Guangdong Science and Technology Department","award":["2024ZDZX2004"],"award-info":[{"award-number":["2024ZDZX2004"]}]},{"name":"The Guangzhou Industrial Information and Intelligent Key Laboratory Project","award":["2024A03J0628"],"award-info":[{"award-number":["2024A03J0628"]}]},{"name":"Guangdong Provincial Key Lab of Integrated Communication, Sensing and Computation for Ubiquitous Internet of Things","award":["2023B1212010007"],"award-info":[{"award-number":["2023B1212010007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754884","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"7434-7443","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Farther Than Mirror: Explore Pattern-Compensated Depth of Mirror with Temporal Changes for Video Mirror Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2502-3578","authenticated-orcid":false,"given":"Zhaohu","family":"Xing","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8983-2342","authenticated-orcid":false,"given":"Lihao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Cambridge, Cambridge, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8255-2997","authenticated-orcid":false,"given":"Tian","family":"Ye","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6837-886X","authenticated-orcid":false,"given":"Sixiang","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4083-5144","authenticated-orcid":false,"given":"Yijun","family":"Yang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5259-7094","authenticated-orcid":false,"given":"Guang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3871-663X","authenticated-orcid":false,"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou) & The Hong Kong University of Science and Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Principles of optics: electromagnetic theory of propagation, interference and diffraction of light","author":"Born Max","unstructured":"Max Born and Emil Wolf. 2013. Principles of optics: electromagnetic theory of propagation, interference and diffraction of light. Elsevier."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104338"},{"key":"e_1_3_2_1_3_1","volume-title":"Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750091"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00274"},{"key":"e_1_3_2_1_6_1","volume-title":"Mask2former for video instance segmentation. arXiv preprint arXiv:2112.10764","author":"Cheng Bowen","year":"2021","unstructured":"Bowen Cheng, Anwesa Choudhuri, Ishan Misra, Alexander Kirillov, Rohit Girdhar, and Alexander G Schwing. 2021. Mask2former for video instance segmentation. arXiv preprint arXiv:2112.10764 (2021)."},{"key":"e_1_3_2_1_7_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 34 (2021), 11781--11794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.510"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_42"},{"key":"e_1_3_2_1_10_1","volume-title":"Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems 27","author":"Eigen David","year":"2014","unstructured":"David Eigen, Christian Puhrsch, and Rob Fergus. 2014. Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249--256."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/23311916.2019.1632046"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25157"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00488"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1119--1127","author":"Li Bo","year":"2015","unstructured":"Bo Li, Chunhua Shen, Yuchao Dai, Anton Van Den Hengel, and Mingyi He. 2015. Depth and surface normal estimation from monocular images using regression on deep features and hierarchical crfs. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1119--1127."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00737"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01321"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00879"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00375"},{"key":"e_1_3_2_1_21_1","volume-title":"Contrastive registration for unsupervised medical image segmentation","author":"Liu Lihao","year":"2023","unstructured":"Lihao Liu, Angelica I Aviles-Rivero, and Carola-Bibiane Sch\u00f6nlieb. 2023. Contrastive registration for unsupervised medical image segmentation. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Traffic Video Object Detection using Motion Prior. arXiv preprint arXiv:2311.10092","author":"Liu Lihao","year":"2023","unstructured":"Lihao Liu, Yanqi Cheng, Dongdong Chen, Jing He, Pietro Li\u00f2, Carola-Bibiane Sch\u00f6nlieb, and Angelica I Aviles-Rivero. 2023. Traffic Video Object Detection using Motion Prior. arXiv preprint arXiv:2311.10092 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01007"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_25_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00312"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00306"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_34"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00729"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3264883"},{"key":"e_1_3_2_1_33_1","first-page":"3492","article-title":"Mirror detection with the visual chirality cue","volume":"45","author":"Tan Xin","year":"2022","unstructured":"Xin Tan, Jiaying Lin, Ke Xu, Pan Chen, Lizhuang Ma, and Rynson WH Lau. 2022. Mirror detection with the visual chirality cue. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2022), 3492--3504.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_34_1","volume-title":"Video salient object detection via adaptive local-global refinement. arXiv preprint arXiv:2104.14360","author":"Tang Yi","year":"2021","unstructured":"Yi Tang, Yuanman Li, and Guoliang Xing. 2021. Video salient object detection via adaptive local-global refinement. arXiv preprint arXiv:2104.14360 (2021)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01632"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"e_1_3_2_1_37_1","volume-title":"European Conference on Computer Vision. Springer, 70--89","author":"Wu Hongtao","year":"2024","unstructured":"Hongtao Wu, Yijun Yang, Angelica I Aviles-Rivero, Jingjing Ren, Sixiang Chen, Haoyu Chen, and Lei Zhu. 2024. Semi-supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization. In European Conference on Computer Vision. Springer, 70--89."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612001"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680916"},{"key":"e_1_3_2_1_40_1","volume-title":"Pattern-aware transformer: Hierarchical pattern propagation in sequential medical images","author":"Wu Lingyun","year":"2023","unstructured":"Lingyun Wu, Xiang Gao, Zhiqiang Hu, and Shaoting Zhang. 2023. Pattern-aware transformer: Hierarchical pattern propagation in sequential medical images. IEEE Transactions on Medical Imaging (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00069"},{"key":"e_1_3_2_1_42_1","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems 34 (2021), 12077--12090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02372"},{"key":"e_1_3_2_1_44_1","unstructured":"Zhaohu Xing Lihao Liu Tian Ye Sixiang Chen Yijun Yang Guang Liu Xiaojie Xu and Lei Zhu. [n.d.]. Farther Than Mirror: Explore Pattern-Compensated Depth of Mirror with Temporal Changes for Video Mirror Detection. ([n.d.])."},{"key":"e_1_3_2_1_45_1","volume-title":"Diff-UNet: A diffusion embedded network for robust 3D medical image segmentation. Medical Image Analysis","author":"Xing Zhaohu","year":"2025","unstructured":"Zhaohu Xing, Liang Wan, Huazhu Fu, Guang Yang, Yijun Yang, Lequan Yu, Baiying Lei, and Lei Zhu. 2025. Diff-UNet: A diffusion embedded network for robust 3D medical image segmentation. Medical Image Analysis (2025), 103654."},{"key":"e_1_3_2_1_46_1","volume-title":"Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation. arXiv preprint arXiv:2303.10326","author":"Xing Zhaohu","year":"2023","unstructured":"Zhaohu Xing, Liang Wan, Huazhu Fu, Guang Yang, and Lei Zhu. 2023. Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation. arXiv preprint arXiv:2303.10326 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"e_1_3_2_1_48_1","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 140--150","author":"Xing Zhaohu","year":"2022","unstructured":"Zhaohu Xing, Lequan Yu, Liang Wan, Tong Han, and Lei Zhu. 2022. Nested-Former: Nested modality-aware transformer for brain tumor segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 140--150."},{"key":"e_1_3_2_1_49_1","volume-title":"Depth anything: Unleashing the power of large-scale unlabeled data. arXiv preprint arXiv:2401.10891","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth anything: Unleashing the power of large-scale unlabeled data. arXiv preprint arXiv:2401.10891 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00890"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings, Part VI 16","author":"Yuan Yuhui","year":"2020","unstructured":"Yuhui Yuan, Xilin Chen, and Jingdong Wang. 2020. Object-contextual representations for semantic segmentation. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VI 16. Springer, 173--190."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_2_1_55_1","volume-title":"Proceedings, Part II 16","author":"Zhao Xiaoqi","year":"2020","unstructured":"Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, and Lei Zhang. 2020. Suppress and balance: A simple gated network for salient object detection. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part II 16. Springer, 35--51."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:03:06Z","timestamp":1765339386000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754884"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":57,"alternative-id":["10.1145\/3746027.3754884","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754884","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"}}]}}