{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:17:47Z","timestamp":1783210667953,"version":"3.54.6"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024JBZY001"],"award-info":[{"award-number":["2024JBZY001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62331003"],"award-info":[{"award-number":["62331003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62120106009"],"award-info":[{"award-number":["62120106009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302141"],"award-info":[{"award-number":["62302141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114109","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T17:56:58Z","timestamp":1781200618000},"page":"114109","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["You can mask more for extremely low-bitrate image compression"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3812-8803","authenticated-orcid":false,"given":"Anqi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9862-0432","authenticated-orcid":false,"given":"Feng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runmin","family":"Cong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huihui","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114109_b1","series-title":"Image Processing Algorithms and Techniques","first-page":"220","article-title":"Overview of the JPEG (ISOCCITT) still image compression standard","volume":"Vol. 1244","author":"Wallace","year":"1990"},{"issue":"2","key":"10.1016\/j.patcog.2026.114109_b2","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1117\/1.1469618","article-title":"JPEG2000: Image compression fundamentals, standards and practice","volume":"11","author":"Taubman","year":"2002","journal-title":"J. Electron. Imaging"},{"key":"10.1016\/j.patcog.2026.114109_b3","series-title":"BPG image format","author":"Bellard","year":"2015"},{"issue":"9","key":"10.1016\/j.patcog.2026.114109_b4","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1109\/JPROC.2020.3043399","article-title":"Developments in international video coding standardization after avc, with an overview of versatile video coding (vvc)","volume":"109","author":"Bross","year":"2021","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.patcog.2026.114109_b5","unstructured":"J. Ball\u00e9, V. Laparra, E.P. Simoncelli, End-to-end Optimized Image Compression, in: International Conference on Learning Representations, 2017."},{"key":"10.1016\/j.patcog.2026.114109_b6","series-title":"Variational image compression with a scale hyperprior","author":"Ball\u00e9","year":"2018"},{"key":"10.1016\/j.patcog.2026.114109_b7","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume":"31","author":"Minnen","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114109_b8","series-title":"2020 IEEE International Conference on Image Processing","first-page":"3339","article-title":"Channel-wise autoregressive entropy models for learned image compression","author":"Minnen","year":"2020"},{"key":"10.1016\/j.patcog.2026.114109_b9","doi-asserted-by":"crossref","unstructured":"X. Zhu, J. Song, L. Gao, F. Zheng, H.T. Shen, Unified multivariate gaussian mixture for efficient neural image compression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 17612\u201317621.","DOI":"10.1109\/CVPR52688.2022.01709"},{"key":"10.1016\/j.patcog.2026.114109_b10","doi-asserted-by":"crossref","first-page":"3612","DOI":"10.1109\/TIP.2020.2963956","article-title":"Learning a single tucker decomposition network for lossy image compression with multiple bits-per-pixel rates","volume":"29","author":"Cai","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"10.1016\/j.patcog.2026.114109_b11","doi-asserted-by":"crossref","first-page":"3007","DOI":"10.1109\/TCSVT.2017.2734838","article-title":"An end-to-end compression framework based on convolutional neural networks","volume":"28","author":"Jiang","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114109_b12","doi-asserted-by":"crossref","unstructured":"M. Li, W. Zuo, S. Gu, D. Zhao, D. Zhang, Learning convolutional networks for content-weighted image compression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 3214\u20133223.","DOI":"10.1109\/CVPR.2018.00339"},{"key":"10.1016\/j.patcog.2026.114109_b13","doi-asserted-by":"crossref","unstructured":"Z. Cheng, H. Sun, M. Takeuchi, J. Katto, Learning image and video compression through spatial-temporal energy compaction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10071\u201310080.","DOI":"10.1109\/CVPR.2019.01031"},{"key":"10.1016\/j.patcog.2026.114109_b14","unstructured":"J. Lee, S. Cho, S.-K. Beack, Context-adaptive Entropy Model for End-to-end Optimized Image Compression, in: International Conference on Learning Representations, 2019."},{"key":"10.1016\/j.patcog.2026.114109_b15","unstructured":"Y. Qian, M. Lin, X. Sun, Z. Tan, R. Jin, Entroformer: A Transformer-based Entropy Model for Learned Image Compression, in: International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.patcog.2026.114109_b16","doi-asserted-by":"crossref","unstructured":"S. Santurkar, D. Budden, N. Shavit, Generative Compression, in: 2018 Picture Coding Symposium, 2018, pp. 258\u2013262.","DOI":"10.1109\/PCS.2018.8456298"},{"key":"10.1016\/j.patcog.2026.114109_b17","doi-asserted-by":"crossref","first-page":"2809","DOI":"10.1109\/TIP.2022.3159477","article-title":"Conceptual compression via deep structure and texture synthesis","volume":"31","author":"Chang","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114109_b18","doi-asserted-by":"crossref","unstructured":"J. Chang, J. Zhang, Y. Xu, J. Li, S. Ma, W. Gao, Consistency-Contrast Learning for Conceptual Coding, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 2681\u20132690.","DOI":"10.1145\/3503161.3547928"},{"key":"10.1016\/j.patcog.2026.114109_b19","doi-asserted-by":"crossref","unstructured":"K. He, X. Chen, S. Xie, Y. Li, P. Doll\u2019ar, R.B. Girshick, Masked Autoencoders Are Scalable Vision Learners, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15979\u201315988.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.patcog.2026.114109_b20","doi-asserted-by":"crossref","unstructured":"Y. Li, H. Zhang, L. Li, D. Liu, Learned image compression with hierarchical progressive context modeling, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025, pp. 18834\u201318843.","DOI":"10.1109\/ICCV51701.2025.01750"},{"key":"10.1016\/j.patcog.2026.114109_b21","doi-asserted-by":"crossref","unstructured":"J. Lu, L. Zhang, X. Zhou, M. Li, W. Li, S. Gu, Learned image compression with dictionary-based entropy model, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 12850\u201312859.","DOI":"10.1109\/CVPR52734.2025.01199"},{"key":"10.1016\/j.patcog.2026.114109_b22","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.patcog.2026.114109_b23","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.114109_b24","doi-asserted-by":"crossref","unstructured":"H. Chen, Y. Wang, T. Guo, C. Xu, Y. Deng, Z. Liu, S. Ma, C. Xu, C. Xu, W. Gao, Pre-trained image processing transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12299\u201312310.","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"10.1016\/j.patcog.2026.114109_b25","doi-asserted-by":"crossref","unstructured":"S. Zheng, J. Lu, H. Zhao, X. Zhu, Z. Luo, Y. Wang, Y. Fu, J. Feng, T. Xiang, P.H. Torr, et al., Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 6881\u20136890.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"10.1016\/j.patcog.2026.114109_b26","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.patcog.2026.114109_b27","doi-asserted-by":"crossref","unstructured":"Y. Bai, X. Yang, X. Liu, J. Jiang, Y. Wang, X. Ji, W. Gao, Towards end-to-end image compression and analysis with transformers, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, 2022, pp. 104\u2013112.","DOI":"10.1609\/aaai.v36i1.19884"},{"key":"10.1016\/j.patcog.2026.114109_b28","doi-asserted-by":"crossref","unstructured":"R. Zou, C. Song, Z. Zhang, The devil is in the details: Window-based attention for image compression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 17492\u201317501.","DOI":"10.1109\/CVPR52688.2022.01697"},{"key":"10.1016\/j.patcog.2026.114109_b29","doi-asserted-by":"crossref","unstructured":"Y. Xie, K.L. Cheng, Q. Chen, Enhanced Invertible Encoding for Learned Image Compression, in: Proceedings of the ACM International Conference on Multimedia, 2021, pp. 162\u2013170.","DOI":"10.1145\/3474085.3475213"},{"key":"10.1016\/j.patcog.2026.114109_b30","unstructured":"L. Dinh, D. Krueger, Y. Bengio, NICE: Non-linear Independent Components Estimation, in: In Proceedings of the International Conference on Learning Representations Workshops, 2015."},{"key":"10.1016\/j.patcog.2026.114109_b31","doi-asserted-by":"crossref","unstructured":"S. Dash, G. Kumaravelu, V. Naganoor, S.K. Raman, A. Ramesh, H. Lee, Compressnet: Generative compression at extremely low bitrates, in: 2020 IEEE Winter Conference on Applications of Computer Vision, 2020, pp. 2314\u20132322.","DOI":"10.1109\/WACV45572.2020.9093415"},{"key":"10.1016\/j.patcog.2026.114109_b32","first-page":"1","article-title":"Edge-guided hyperspectral image compression with interactive dual attention","volume":"61","author":"Guo","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114109_b33","first-page":"1","article-title":"Edge-guided remote-sensing image compression","volume":"61","author":"Han","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114109_b34","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","first-page":"4171","author":"Devlin","year":"2018"},{"key":"10.1016\/j.patcog.2026.114109_b35","series-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"10.1016\/j.patcog.2026.114109_b36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.patcog.2026.114109_b37","series-title":"Advances in Neural Information Processing Systems","first-page":"1877","article-title":"Language models are few-shot learners","volume":"Vol. 33","author":"Brown","year":"2020"},{"issue":"5","key":"10.1016\/j.patcog.2026.114109_b38","first-page":"2793","article-title":"Reconstructive sequence-graph network for video summarization","volume":"44","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"10.1016\/j.patcog.2026.114109_b39","doi-asserted-by":"crossref","first-page":"2506","DOI":"10.1109\/TPAMI.2023.3336525","article-title":"Contrastive masked autoencoders are stronger vision learners","volume":"46","author":"Huang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114109_b40","doi-asserted-by":"crossref","unstructured":"L. Huang, S. You, M. Zheng, F. Wang, C. Qian, T. Yamasaki, Green Hierarchical Vision Transformer for Masked Image Modeling, in: Thirty-Sixth Conference on Neural Information Processing Systems, 2022.","DOI":"10.52202\/068431-1454"},{"key":"10.1016\/j.patcog.2026.114109_b41","series-title":"Advances in Neural Information Processing Systems","article-title":"MCMAE: Masked convolution meets masked autoencoders","author":"Gao","year":"2022"},{"key":"10.1016\/j.patcog.2026.114109_b42","doi-asserted-by":"crossref","unstructured":"H. Chang, H. Zhang, L. Jiang, C. Liu, W.T. Freeman, MaskGIT: Masked Generative Image Transformer, in: The IEEE Conference on Computer Vision and Pattern Recognition, 2022.","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"10.1016\/j.patcog.2026.114109_b43","doi-asserted-by":"crossref","unstructured":"T. Li, H. Chang, S. Mishra, H. Zhang, D. Katabi, D. Krishnan, Mage: Masked generative encoder to unify representation learning and image synthesis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2142\u20132152.","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"10.1016\/j.patcog.2026.114109_b44","series-title":"Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXIII","first-page":"70","article-title":"Improved masked image generation with token-critic","author":"Lezama","year":"2022"},{"key":"10.1016\/j.patcog.2026.114109_b45","series-title":"Masked autoencoders as image processors","author":"Duan","year":"2023"},{"key":"10.1016\/j.patcog.2026.114109_b46","series-title":"2014 Fifth International Conference on Signal and Image Processing","first-page":"92","article-title":"Patch based image completion for compression application","author":"Yatnalli","year":"2014"},{"key":"10.1016\/j.patcog.2026.114109_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.image.2020.116119","article-title":"BINet: A binary inpainting network for deep patch-based image compression","volume":"92","author":"Nortje","year":"2021","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.patcog.2026.114109_b48","doi-asserted-by":"crossref","unstructured":"M. Tarchouli, S. Pelurson, T. Guionneta, W. Hamidouche, M. Outtas, O. Deforges, Patch-Based Image Coding with End-To-End Learned Codec using Overlapping, in: 12th International Conference on Digital Image Processing and Pattern Recognition, Vol. 12, 2022, pp. 53\u201363.","DOI":"10.5121\/csit.2022.122305"},{"issue":"10","key":"10.1016\/j.patcog.2026.114109_b49","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1109\/TCSVT.2007.903663","article-title":"Image compression with edge-based inpainting","volume":"17","author":"Liu","year":"2007","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114109_b50","doi-asserted-by":"crossref","unstructured":"J. Sun, Z. Xu, H.-Y. Shum, Image super-resolution using gradient profile prior, in: 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1\u20138.","DOI":"10.1109\/CVPR.2008.4587659"},{"key":"10.1016\/j.patcog.2026.114109_b51","unstructured":"E. Jang, S. Gu, B. Poole, Categorical Reparameterization with Gumbel-Softmax, in: International Conference on Learning Representations, 2017."},{"issue":"4","key":"10.1016\/j.patcog.2026.114109_b52","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114109_b53","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"Johnson","year":"2016"},{"key":"10.1016\/j.patcog.2026.114109_b54","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.114109_b55","doi-asserted-by":"crossref","unstructured":"J. Liu, H. Sun, J. Katto, Learned image compression with mixed transformer-cnn architectures, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14388\u201314397.","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"10.1016\/j.patcog.2026.114109_b56","series-title":"European Conference on Computer Vision","first-page":"181","article-title":"Region-adaptive transform with segmentation prior for image compression","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.114109_b57","unstructured":"H. Li, S. Li, W. Dai, C. Li, J. Zou, H. Xiong, Frequency-Aware Transformer for Learned Image Compression, in: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.patcog.2026.114109_b58","doi-asserted-by":"crossref","unstructured":"F. Zeng, H. Tang, Y. Shao, S. Chen, L. Shao, Y. Wang, Mambaic: State space models for high-performance learned image compression, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 18041\u201318050.","DOI":"10.1109\/CVPR52734.2025.01681"},{"key":"10.1016\/j.patcog.2026.114109_b59","doi-asserted-by":"crossref","unstructured":"R. Zhang, P. Isola, A.A. Efros, E. Shechtman, O. Wang, The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"10.1016\/j.patcog.2026.114109_b60","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114109_b61","series-title":"Kodak lossless true color image suite (photocd pcd0992)","author":"Kodak","year":"1993"},{"key":"10.1016\/j.patcog.2026.114109_b62","series-title":"Calculation of average PSNR differences between RD-curves","author":"Bjontegaard","year":"2001"},{"key":"10.1016\/j.patcog.2026.114109_b63","doi-asserted-by":"crossref","unstructured":"W. Zhang, Z. Huang, G. Luo, T. Chen, X. Wang, W. Liu, G. Yu, C. Shen, TopFormer: Token pyramid transformer for mobile semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12083\u201312093.","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"10.1016\/j.patcog.2026.114109_b64","series-title":"International Conference on Machine Learning","first-page":"35624","article-title":"A closer look at self-supervised lightweight vision transformers","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114109_b65","doi-asserted-by":"crossref","unstructured":"C.-H. Lee, Z. Liu, L. Wu, P. Luo, Maskgan: Towards diverse and interactive facial image manipulation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 5549\u20135558.","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"10.1016\/j.patcog.2026.114109_b66","doi-asserted-by":"crossref","unstructured":"K. He, G. Gkioxari, P. Doll\u00e1r, R. Girshick, Mask r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326010745?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326010745?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T23:40:20Z","timestamp":1783208420000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326010745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":66,"alternative-id":["S0031320326010745"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114109","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"You can mask more for extremely low-bitrate image compression","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114109","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114109"}}