{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:45:37Z","timestamp":1773193537482,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755059","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"12016-12024","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Neural Video Compression with In-Loop Contextual Filtering and Out-of-Loop Reconstruction Enhancement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8138-4186","authenticated-orcid":false,"given":"Yaojun","family":"Wu","sequence":"first","affiliation":[{"name":"Bytedance China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7770-6821","authenticated-orcid":false,"given":"Chaoyi","family":"Lin","sequence":"additional","affiliation":[{"name":"Bytedance China, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5683-909X","authenticated-orcid":false,"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Hohai University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5573-0326","authenticated-orcid":false,"given":"Semih","family":"Esenlik","sequence":"additional","affiliation":[{"name":"Bytedance Inc., San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5961-5163","authenticated-orcid":false,"given":"Zhaobin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4079-1797","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., San Diego, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3463-9211","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance Inc., San Diego, CA, USA"}],"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\/CVPR42600.2020.00853"},{"key":"e_1_3_2_1_2_1","unstructured":"Frank Bossen and et al. 2013. Common test conditions and software reference configurations. In JCTVC-L1100."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_1_4_1","unstructured":"An Chen. 2021. ToFlow: Optical Flow Estimation for Video. https:\/\/github.com\/anchen1011\/toflow"},{"key":"e_1_3_2_1_5_1","first-page":"41","article-title":"An overview of core coding tools in the AV1 video codec. In 2018 picture coding symposium (PCS). IEEE","author":"Chen Yue","year":"2018","unstructured":"Yue Chen, Debargha Murherjee, Jingning Han, Adrian Grange, Yaowu Xu, Zoe Liu, Sarah Parker, Cheng Chen, Hui Su, Urvang Joshi, et al., 2018. An overview of core coding tools in the AV1 video codec. In 2018 picture coding symposium (PCS). IEEE, IEEE, 41-45.","journal-title":"IEEE"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892608"},{"key":"e_1_3_2_1_7_1","unstructured":"M. Coban R.-L. Liao K. Naser J. Str\u00f6m and L. Zhang. 2025. Algorithm Description of Enhanced Compression Model 15 (ECM 15). Technical Report m70646. JVET-AJ2025. https:\/\/jvet-experts.org\/doc_end_user\/current_document.php?id=15003"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00652"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1984.1096143"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221529"},{"key":"e_1_3_2_1_11_1","unstructured":"F. Galpin Y. Li D. Rusanovskyy J. Str\u00f6m and L. Wang. 2019. Description of Algorithms Version 9 and Software Version 11 in Neural Network-Based Video Coding (NNVC). Technical Report. JVET-AJ2019."},{"key":"e_1_3_2_1_12_1","volume-title":"13 VCEG Meeting","author":"Gisle Bjontegaard","year":"2001","unstructured":"Bjontegaard Gisle. 2001. Calculation of Average PSNR Differences between RD curves. In ITU-T SG16\/Q6, 13 VCEG Meeting, Austin, Texas, USA, April 2001."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_12"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00583"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3072297"},{"key":"e_1_3_2_1_16_1","volume-title":"Neural Compression: From Information Theory to Applications-Workshop@ ICLR","author":"Ladune Th\u00e9o","year":"2021","unstructured":"Th\u00e9o Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, and Olivier D\u00e9forges. 2021. Conditional Coding for Flexible Learned Video Compression. In Neural Compression: From Information Theory to Applications-Workshop@ ICLR 2021."},{"key":"e_1_3_2_1_17_1","first-page":"18114","article-title":"Deep contextual video compression","volume":"34","author":"Li Jiahao","year":"2021","unstructured":"Jiahao Li, Bin Li, and Yan Lu. 2021. Deep contextual video compression. Advances in Neural Information Processing Systems, Vol. 34 (2021), 18114-18125.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547845"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00191"},{"key":"e_1_3_2_1_22_1","volume-title":"ICML 2023 Workshop Neural Compression: From Information Theory to Applications. https:\/\/openreview.net\/forum?id=TEcYuwCS6v","author":"Lieberman Kelsey","year":"2023","unstructured":"Kelsey Lieberman, James Diffenderfer, Charles Godfrey, and Bhavya Kailkhura. 2023. Neural Image Compression: Generalization, Robustness, and Spectral Biases. In ICML 2023 Workshop Neural Compression: From Information Theory to Applications. https:\/\/openreview.net\/forum?id=TEcYuwCS6v"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01773"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357375"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3035680"},{"key":"e_1_3_2_1_27_1","volume-title":"Meet Shah, Rui Hu, Pranaab Dhawan, and Raquel Urtasun. 2020c. Conditional entropy coding for efficient video compression. In European Conference on Computer Vision. Springer, 453-468","author":"Liu Jerry","unstructured":"Jerry Liu, Shenlong Wang, Wei-Chiu Ma, Meet Shah, Rui Hu, Pranaab Dhawan, and Raquel Urtasun. 2020c. Conditional entropy coding for efficient video compression. In European Conference on Computer Vision. Springer, 453-468."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"e_1_3_2_1_30_1","volume-title":"Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems","author":"Minnen David","year":"2018","unstructured":"David Minnen, Johannes Ball\u00e9, and George D Toderici. 2018. Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00592"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Ranjan Anurag","unstructured":"Anurag Ranjan and Michael J. Black. 2017. Optical Flow Estimation using a Spatial Pyramid Network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01421"},{"key":"e_1_3_2_1_34_1","unstructured":"Tong Shao Jay N. Shingala Ajay Shyam Peng Yin Arjun Arora and Sean McCarthy. 2023. Low Complexity Neural Network-Based In-loop Filtering with Decomposed Split Luma-Chroma Model for Video Compression. In ICML 2023 Workshop Neural Compression: From Information Theory to Applications. https:\/\/openreview.net\/forum?id=ZkkjPbx5KG"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3220421"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00188"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_3_2_1_40_1","volume-title":"Lossy Image Compression with Conditional Diffusion Model. In ICML 2023 Workshop Neural Compression: From Information Theory to Applications. https:\/\/openreview.net\/forum?id=GDIp6mRu5m","author":"Yang Ruihan","year":"2023","unstructured":"Ruihan Yang and Stephan Mandt. 2023. Lossy Image Compression with Conditional Diffusion Model. In ICML 2023 Workshop Neural Compression: From Information Theory to Applications. https:\/\/openreview.net\/forum?id=GDIp6mRu5m"}],"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\/3746027.3755059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:14Z","timestamp":1765339694000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":40,"alternative-id":["10.1145\/3746027.3755059","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755059","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"}}]}}