{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:46Z","timestamp":1765340086481,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755215","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"7949-7958","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Blind Bitstream-corrupted Video Recovery: A Visual Foundation Model-driven Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6705-7808","authenticated-orcid":false,"given":"Tianyi","family":"Liu","sequence":"first","affiliation":[{"name":"School of EEE, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9859-9573","authenticated-orcid":false,"given":"Kejun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7793-5261","authenticated-orcid":false,"given":"Chen","family":"Cai","sequence":"additional","affiliation":[{"name":"School of EEE, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8659-4724","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Dept. of EEE, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1933-4986","authenticated-orcid":false,"given":"Kim-Hui","family":"Yap","sequence":"additional","affiliation":[{"name":"School of EEE, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4932-0593","authenticated-orcid":false,"given":"Lap-Pui","family":"Chau","sequence":"additional","affiliation":[{"name":"Dept. of EEE, The Hong Kong Polytechnic University, Hong Kong SAR, 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":"JCTVC 7th Meeting: Geneva, CH, 21-30 Nov.","author":"Bross Benjamin","year":"2011","unstructured":"Benjamin Bross. 2011. High efficiency video coding (HEVC) text specification draft6. In JCTVC 7th Meeting: Geneva, CH, 21-30 Nov."},{"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","volume-title":"On the generalization of basicvsr to video deblurring and denoising. arXiv preprint arXiv:2204.05308","author":"Chan Kelvin CK","year":"2022","unstructured":"Kelvin CK Chan, Shangchen Zhou, Xiangyu Xu, and Chen Change Loy. 2022. On the generalization of basicvsr to video deblurring and denoising. arXiv preprint arXiv:2204.05308 (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2909564"},{"volume-title":"Cisco Visual Networking Index: Forecast and Trends","year":"2017","key":"e_1_3_2_1_5_1","unstructured":"Cisco. [n.d.]. Cisco Visual Networking Index: Forecast and Trends, 2017-2022. https:\/\/twiki.cern.ch\/twiki\/pub\/HEPIX\/TechwatchNetwork\/HtwNetworkDocuments\/white-paper-c11-741490.pdf."},{"key":"e_1_3_2_1_6_1","volume-title":"Understanding the impact of video quality on user engagement. ACM SIGCOMM computer communication review","author":"Dobrian Florin","year":"2011","unstructured":"Florin Dobrian, Vyas Sekar, Asad Awan, Ion Stoica, Dilip Joseph, Aditya Ganjam, Jibin Zhan, and Hui Zhang. 2011. Understanding the impact of video quality on user engagement. ACM SIGCOMM computer communication review, Vol. 41, 4 (2011), 362-373."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.73"},{"key":"e_1_3_2_1_8_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_10_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Adaptive mixtures of local experts. Neural computation","author":"Jacobs Robert A","year":"1991","unstructured":"Robert A Jacobs, Michael I Jordan, Steven J Nowlan, and Geoffrey E Hinton. 1991. Adaptive mixtures of local experts. Neural computation, Vol. 3, 1 (1991), 79-87."},{"key":"e_1_3_2_1_12_1","first-page":"375","volume-title":"Tel Aviv","author":"Kang Jaeyeon","year":"2022","unstructured":"Jaeyeon Kang, Seoung Wug Oh, and Seon Joo Kim. 2022. Error compensation framework for flow-guided video inpainting. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XV. Springer, 375-390."},{"key":"e_1_3_2_1_13_1","volume-title":"Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725","author":"Khanam Rahima","year":"2024","unstructured":"Rahima Khanam and Muhammad Hussain. 2024. Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00594"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"e_1_3_2_1_18_1","volume-title":"Vrt: A video restoration transformer","author":"Liang Jingyun","year":"2024","unstructured":"Jingyun Liang, Jiezhang Cao, Yuchen Fan, Kai Zhang, Rakesh Ranjan, Yawei Li, Radu Timofte, and Luc Van Gool. 2024. Vrt: A video restoration transformer. IEEE Transactions on Image Processing (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Toward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset","author":"Lin Liqun","year":"2024","unstructured":"Liqun Lin, Mingxing Wang, Jing Yang, Keke Zhang, and Tiesong Zhao. 2024. Toward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset. IEEE Transactions on Multimedia (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01378"},{"key":"e_1_3_2_1_21_1","first-page":"68420","article-title":"Bitstream-corrupted video recovery: A novel benchmark dataset and method","volume":"36","author":"Liu Tianyi","year":"2023","unstructured":"Tianyi Liu, Kejun Wu, Yi Wang, Wenyang Liu, Kim-Hui Yap, and Lap-Pui Chau. 2023. Bitstream-corrupted video recovery: A novel benchmark dataset and method. Advances in Neural Information Processing Systems, Vol. 36 (2023), 68420-68433.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00347"},{"key":"e_1_3_2_1_24_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"The 2017 DAVIS Challenge on Video Object Segmentation. arXiv:1704.00675","author":"Pont-Tuset Jordi","year":"2017","unstructured":"Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbel\u00e1ez, Alexander Sorkine-Hornung, and Luc Van Gool. 2017. The 2017 DAVIS Challenge on Video Object Segmentation. arXiv:1704.00675 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_27_1","volume-title":"Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Doll\u00e1r, and Christoph Feichtenhofer.","author":"Ravi Nikhila","year":"2024","unstructured":"Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman R\u00e4dle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Doll\u00e1r, and Christoph Feichtenhofer. 2024. SAM 2: Segment Anything in Images and Videos. arXiv preprint arXiv:2408.00714 (2024). https:\/\/arxiv.org\/abs\/2408.00714"},{"key":"e_1_3_2_1_28_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 29441-29454","author":"Ryali Chaitanya","year":"2023","unstructured":"Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, et al., 2023. Hiera: A hierarchical vision transformer without the bells-and-whistles. In International conference on machine learning. PMLR, 29441-29454."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451090"},{"key":"e_1_3_2_1_31_1","volume-title":"IEEE transactions on circuits and systems for video technology","author":"Stockhammer Thomas","year":"2003","unstructured":"Thomas Stockhammer, Miska M Hannuksela, and Thomas Wiegand. 2003. H. 264\/AVC in wireless environments. IEEE transactions on circuits and systems for video technology, Vol. 13, 7 (2003), 657-673."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01510-7"},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 10347-10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347-10357."},{"key":"e_1_3_2_1_34_1","volume-title":"USENIX Security Symposium.","author":"Vasquez Willy R.","year":"2023","unstructured":"Willy R. Vasquez, Stephen Checkoway, and Hovav Shacham. 2023. The Most Dangerous Codec in the World: Finding and Exploiting Vulnerabilities in H.264 Decoders.. In USENIX Security Symposium."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"e_1_3_2_1_36_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600-612."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC55655.2023.00017"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683622"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00384"},{"volume-title":"The 2nd Large-scale Video Object Segmentation Challenge - video object segmentation track","author":"Yang Linjie","key":"e_1_3_2_1_40_1","unstructured":"Linjie Yang, Yuchen Fan, and Ning Xu. 2019. The 2nd Large-scale Video Object Segmentation Challenge - video object segmentation track."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00237"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361010"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00276"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"}],"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\/3746027.3755215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:49Z","timestamp":1765339849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755215"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"alternative-id":["10.1145\/3746027.3755215","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755215","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"}}]}}