{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:34:07Z","timestamp":1778081647751,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Leading Goose R&D Program of Zhejiang Province","award":["2024C01107"],"award-info":[{"award-number":["2024C01107"]}]},{"name":"Leading Goose R&D Program of Zhejiang Province","award":["2024C01101"],"award-info":[{"award-number":["2024C01101"]}]},{"name":"National Key R&D Program of China","award":["2021ZD0109800"],"award-info":[{"award-number":["2021ZD0109800"]}]},{"name":"National Natural Science Foundation of China","award":["61901150"],"award-info":[{"award-number":["61901150"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681354","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"7900-7908","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhanced Screen Content Image Compression: A Synergistic Approach for Structural Fidelity and Text Integrity Preservation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0308-3865","authenticated-orcid":false,"given":"Fangtao","family":"Zhou","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8479-6960","authenticated-orcid":false,"given":"Xiaofeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6841-2257","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Advanced Institute of Information Technology, Peking University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5655-1464","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, hongkong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7500-5584","authenticated-orcid":false,"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7882-9028","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3025-0938","authenticated-orcid":false,"given":"Haibing","family":"Yin","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"e_1_3_2_1_2_1","volume-title":"End-to-end optimized image compression. arXiv preprint arXiv:1611.01704","author":"Ball\u00e9 Johannes","year":"2016","unstructured":"Johannes Ball\u00e9, Valero Laparra, and Eero P Simoncelli. 2016. End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016)."},{"key":"e_1_3_2_1_3_1","volume-title":"Sung Jin Hwang, and Nick Johnston","author":"Ball\u00e9 Johannes","year":"2018","unstructured":"Johannes Ball\u00e9, David Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. 2018. Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"CompressAI: a PyTorch library and evaluation platform for end-to-end compression research. arXiv preprint arXiv:2011.03029","author":"B\u00e9gaint Jean","year":"2020","unstructured":"Jean B\u00e9gaint, Fabien Racap\u00e9, Simon Feltman, and Akshay Pushparaja. 2020. CompressAI: a PyTorch library and evaluation platform for end-to-end compression research. arXiv preprint arXiv:2011.03029 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_6_1","volume-title":"ITU-T VCEG-M33","author":"Bjontegaard Gisle","year":"2001","unstructured":"Gisle Bjontegaard. 2001. Calculation of average PSNR differences between RD-curves. ITU-T VCEG-M33, April, 2001 (2001)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2960869"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","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 41--45.","DOI":"10.1109\/PCS.2018.8456249"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01039"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.839613"},{"key":"e_1_3_2_1_13_1","volume-title":"Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding. arXiv preprint arXiv:1311.2540","author":"Duda Jarek","year":"2013","unstructured":"Jarek Duda. 2013. Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding. arXiv preprint arXiv:1311.2540 (2013)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263099"},{"key":"e_1_3_2_1_15_1","volume-title":"Joint Cross-Component Linear Model For Chroma Intra Prediction. In 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP). 1--5.","author":"Ghaznavi-Youvalari Ramin","year":"2020","unstructured":"Ramin Ghaznavi-Youvalari and Jani Lainema. 2020. Joint Cross-Component Linear Model For Chroma Intra Prediction. In 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP). 1--5."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2711279"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"e_1_3_2_1_19_1","volume-title":"Multi-Task Learning for Screen Content Image Coding. In 2023 IEEE International Symposium on Circuits and Systems (ISCAS). 1--5.","author":"Heris Rashid Zamanshoar","unstructured":"Rashid Zamanshoar Heris and Ivan V. Baji\u0107. 2023. Multi-Task Learning for Screen Content Image Coding. In 2023 IEEE International Symposium on Circuits and Systems (ISCAS). 1--5."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2023.3247953"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3349278"},{"key":"e_1_3_2_1_22_1","volume-title":"Transformer-based Image Compression with Variable Image Quality Objectives. In 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Kao Chia-Hao","unstructured":"Chia-Hao Kao, Yi-Hsin Chen, Cheng Chien, Wei-Chen Chiu, and Wen-Hsiao Peng. 2023. Transformer-based Image Compression with Variable Image Quality Objectives. In 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 1718--1725."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00619"},{"key":"e_1_3_2_1_24_1","volume-title":"Non-local attention optimized deep image compression. arXiv preprint arXiv:1904.09757","author":"Liu Haojie","year":"2019","unstructured":"Haojie Liu, Tong Chen, Peiyao Guo, Qiu Shen, Xun Cao, Yao Wang, and Zhan Ma. 2019. Non-local attention optimized deep image compression. arXiv preprint arXiv:1904.09757 (2019)."},{"key":"e_1_3_2_1_25_1","first-page":"11913","article-title":"High-fidelity generative image compression","volume":"33","author":"Mentzer Fabian","year":"2020","unstructured":"Fabian Mentzer, George D Toderici, Michael Tschannen, and Eirikur Agustsson. 2020. High-fidelity generative image compression. Advances in Neural Information Processing Systems, Vol. 33 (2020), 11913--11924.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_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_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3074312"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2016.2608971"},{"key":"e_1_3_2_1_30_1","volume-title":"Arithmetic coding. IBM Journal of research and development","author":"Rissanen Jorma","year":"1979","unstructured":"Jorma Rissanen and Glen G Langdon. 1979. Arithmetic coding. IBM Journal of research and development, Vol. 23, 2 (1979), 149--162."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01184"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00238"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3152003"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018055"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"e_1_3_2_1_36_1","volume-title":"Transform Skip Inspired End-to-End Compression for Screen Content Image. In 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 3848--3852","author":"Wang Meng","year":"2022","unstructured":"Meng Wang, Kai Zhang, Li Zhang, Yaojun Wu, Yue Li, Junru Li, and Shiqi Wang. 2022. Transform Skip Inspired End-to-End Compression for Screen Content Image. In 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 3848--3852."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018043"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00070"},{"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":"Recent development of AVS video coding standard: AVS3. In 2019 picture coding symposium (PCS)","author":"Zhang Jiaqi","unstructured":"Jiaqi Zhang, Chuanmin Jia, Meng Lei, Shanshe Wang, Siwei Ma, and Wen Gao. 2019. Recent development of AVS video coding standard: AVS3. In 2019 picture coding symposium (PCS). IEEE, 1--5."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM52913.2021.00047"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01697"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681354","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:44Z","timestamp":1750295864000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":43,"alternative-id":["10.1145\/3664647.3681354","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681354","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}