{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:37:53Z","timestamp":1777016273682,"version":"3.51.4"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["113-2221-E-A49-073-MY3"],"award-info":[{"award-number":["113-2221-E-A49-073-MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.image.2026.117536","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T17:07:27Z","timestamp":1773680847000},"page":"117536","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Saliency-guided video coding via recurrent learning and perceptual quality assessment"],"prefix":"10.1016","volume":"145","author":[{"given":"Tz-Cheng","family":"Chang","sequence":"first","affiliation":[]},{"given":"Hsu-Feng","family":"Hsiao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.image.2026.117536_b1","series-title":"Cisco visual networking index (vni) complete forecast update, 2017\u20132022","author":"Barnett","year":"2018"},{"issue":"2","key":"10.1016\/j.image.2026.117536_b2","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/0923-5965(92)90019-C","article-title":"The MPEG video compression algorithm","volume":"4","author":"Le Gall","year":"1992","journal-title":"Signal Process., Image Commun."},{"issue":"7","key":"10.1016\/j.image.2026.117536_b3","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1109\/TCSVT.2003.815165","article-title":"Overview of the H. 264\/AVC video coding standard","volume":"13","author":"Wiegand","year":"2003","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"10.1016\/j.image.2026.117536_b4","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","article-title":"Overview of the high efficiency video coding (HEVC) standard","volume":"22","author":"Sullivan","year":"2012","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.image.2026.117536_b5","doi-asserted-by":"crossref","unstructured":"Y.-H. Tsai, M.-Y. Liu, D. Sun, M.-H. Yang, J. Kautz, Learning binary residual representations for domain-specific video streaming, in: Thirty-Second AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.12259"},{"key":"10.1016\/j.image.2026.117536_b6","doi-asserted-by":"crossref","unstructured":"G. Lu, W. Ouyang, D. Xu, X. Zhang, C. Cai, Z. Gao, Dvc: An end-to-end deep video compression framework, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11006\u201311015.","DOI":"10.1109\/CVPR.2019.01126"},{"key":"10.1016\/j.image.2026.117536_b7","doi-asserted-by":"crossref","unstructured":"R. Yang, F. Mentzer, L. Van Gool, R. Timofte, Learning for video compression with hierarchical quality and recurrent enhancement, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 6628\u20136637.","DOI":"10.1109\/CVPR42600.2020.00667"},{"issue":"2","key":"10.1016\/j.image.2026.117536_b8","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1109\/JSTSP.2020.3043590","article-title":"Learning for video compression with recurrent auto-encoder and recurrent probability model","volume":"15","author":"Yang","year":"2020","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.image.2026.117536_b9","doi-asserted-by":"crossref","unstructured":"J. Lin, D. Liu, H. Li, F. Wu, M-LVC: multiple frames prediction for learned video compression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3546\u20133554.","DOI":"10.1109\/CVPR42600.2020.00360"},{"issue":"1","key":"10.1016\/j.image.2026.117536_b10","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TIP.2013.2282897","article-title":"Saliency-aware video compression","volume":"23","author":"Hadizadeh","year":"2013","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"10.1016\/j.image.2026.117536_b11","doi-asserted-by":"crossref","first-page":"7955","DOI":"10.1007\/s00521-022-06895-1","article-title":"Video saliency aware intelligent HD video compression with the improvement of visual quality and the reduction of coding complexity","volume":"34","author":"Zhu","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.image.2026.117536_b12","doi-asserted-by":"crossref","first-page":"62535","DOI":"10.1109\/ACCESS.2023.3286577","article-title":"Visual saliency guided foveated video compression","volume":"11","author":"Zhang","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.image.2026.117536_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109806","article-title":"An efficient perceptual video compression scheme based on deep learning-assisted video saliency and just noticeable distortion","volume":"141","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.image.2026.117536_b14","article-title":"SJ-PVC: An efficient perceptual video compression scheme based on adaptive QP and rate-distortion optimization","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.image.2026.117536_b15","doi-asserted-by":"crossref","unstructured":"Y. Patel, S. Appalaraju, R. Manmatha, Saliency driven perceptual image compression, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 227\u2013236.","DOI":"10.1109\/WACV48630.2021.00027"},{"issue":"1\u20133","key":"10.1016\/j.image.2026.117536_b16","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","article-title":"Determining optical flow","volume":"17","author":"Horn","year":"1981","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.image.2026.117536_b17","series-title":"European conference on computer vision","first-page":"25","article-title":"High accuracy optical flow estimation based on a theory for warping","author":"Brox","year":"2004"},{"key":"10.1016\/j.image.2026.117536_b18","first-page":"310","article-title":"Probability distributions of optical flow","volume":"91","author":"Simoncelli","year":"1991"},{"issue":"1","key":"10.1016\/j.image.2026.117536_b19","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1023\/A:1026501619075","article-title":"Learning low-level vision","volume":"40","author":"Freeman","year":"2000","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2026.117536_b20","series-title":"European Conference on Computer Vision","first-page":"83","article-title":"Learning optical flow","author":"Sun","year":"2008"},{"key":"10.1016\/j.image.2026.117536_b21","doi-asserted-by":"crossref","unstructured":"A. Dosovitskiy, P. Fischer, E. Ilg, P. Hausser, C. Hazirbas, V. Golkov, P. Van Der Smagt, D. Cremers, T. Brox, Flownet: Learning optical flow with convolutional networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 2758\u20132766.","DOI":"10.1109\/ICCV.2015.316"},{"key":"10.1016\/j.image.2026.117536_b22","doi-asserted-by":"crossref","unstructured":"A. Ranjan, M.J. Black, Optical flow estimation using a spatial pyramid network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4161\u20134170.","DOI":"10.1109\/CVPR.2017.291"},{"key":"10.1016\/j.image.2026.117536_b23","doi-asserted-by":"crossref","unstructured":"D. Sun, X. Yang, M.-Y. Liu, J. Kautz, Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8934\u20138943.","DOI":"10.1109\/CVPR.2018.00931"},{"issue":"11","key":"10.1016\/j.image.2026.117536_b24","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","article-title":"A model of saliency-based visual attention for rapid scene analysis","volume":"20","author":"Itti","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.image.2026.117536_b25","first-page":"353","article-title":"Learning to detect a salient object","volume":"33","author":"Liu","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2026.117536_b26","series-title":"International Conference on Computer Vision Systems","first-page":"66","article-title":"Salient region detection and segmentation","author":"Achanta","year":"2008"},{"key":"10.1016\/j.image.2026.117536_b27","doi-asserted-by":"crossref","unstructured":"Q. Hou, M.-M. Cheng, X. Hu, A. Borji, Z. Tu, P.H. Torr, Deeply supervised salient object detection with short connections, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 3203\u20133212.","DOI":"10.1109\/CVPR.2017.563"},{"key":"10.1016\/j.image.2026.117536_b28","series-title":"European Conference on Computer Vision","first-page":"92","article-title":"Rgbd salient object detection: a benchmark and algorithms","author":"Peng","year":"2014"},{"key":"10.1016\/j.image.2026.117536_b29","series-title":"2019 IEEE International Symposium on Circuits and Systems","first-page":"1","article-title":"Saliency detection with multi-contextual models and spatially coherent loss function","author":"Huang","year":"2019"},{"issue":"1","key":"10.1016\/j.image.2026.117536_b30","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/TBC.2022.3204235","article-title":"Attentional feature fusion for end-to-end blind image quality assessment","volume":"69","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Broadcast."},{"issue":"2","key":"10.1016\/j.image.2026.117536_b31","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TBC.2022.3215249","article-title":"An end-to-end blind image quality assessment method using a recurrent network and self-attention","volume":"69","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Broadcast."},{"issue":"1","key":"10.1016\/j.image.2026.117536_b32","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/TBC.2022.3192997","article-title":"Spatiotemporal feature hierarchy-based blind prediction of natural video quality via transfer learning","volume":"69","author":"Xian","year":"2022","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.image.2026.117536_b33","doi-asserted-by":"crossref","first-page":"3075","DOI":"10.1109\/TIP.2024.3390565","article-title":"Graph-represented distribution similarity index for full-reference image quality assessment","volume":"33","author":"Shen","year":"2024","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.image.2026.117536_b34","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1109\/TBC.2024.3353573","article-title":"HDIQA: A hyper debiasing framework for full reference image quality assessment","volume":"70","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.image.2026.117536_b35","doi-asserted-by":"crossref","unstructured":"W. Shen, M. Zhou, Y. Chen, X. Wei, Y. Feng, H. Pu, W. Jia, Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 17990\u201317999.","DOI":"10.1109\/CVPR52734.2025.01676"},{"key":"10.1016\/j.image.2026.117536_b36","first-page":"1","article-title":"Blind image quality assessment: Exploring content fidelity perceptibility via quality adversarial learning","author":"Zhou","year":"2025","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"10.1016\/j.image.2026.117536_b37","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/S1077-2014(02)00116-X","article-title":"Real-time foveation techniques for low bit rate video coding","volume":"9","author":"Sheikh","year":"2003","journal-title":"Real-Time Imaging"},{"issue":"2","key":"10.1016\/j.image.2026.117536_b38","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1147\/rd.282.0135","article-title":"An introduction to arithmetic coding","volume":"28","author":"Langdon","year":"1984","journal-title":"IBM J. Res. Dev."},{"key":"10.1016\/j.image.2026.117536_b39","series-title":"BPG image format","author":"Bellard","year":"2017"},{"key":"10.1016\/j.image.2026.117536_b40","series-title":"End-to-end optimized image compression","author":"Ball\u00e9","year":"2016"},{"key":"10.1016\/j.image.2026.117536_b41","series-title":"International Conference on Intelligent Computing","first-page":"1124","article-title":"Saliency-based image quality assessment criterion","author":"Ma","year":"2008"},{"key":"10.1016\/j.image.2026.117536_b42","series-title":"Toward a practical perceptual video quality metric","author":"Li","year":"2016"},{"key":"10.1016\/j.image.2026.117536_b43","series-title":"Hacking VMAF with video color and contrast distortion","author":"Zvezdakova","year":"2019"},{"key":"10.1016\/j.image.2026.117536_b44","doi-asserted-by":"crossref","first-page":"98512","DOI":"10.1109\/ACCESS.2022.3205622","article-title":"Impact analysis of foveation and depth on the perceptual quality of immersive visual content with fixed viewport","volume":"10","author":"Shen","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.image.2026.117536_b45","unstructured":"J. Gu, H. Cai, C. Dong, J.S. Ren, R. Timofte, Y. Gong, S. Lao, S. Shi, J. Wang, S. Yang, et al., NTIRE 2022 challenge on perceptual image quality assessment, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 951\u2013967."},{"key":"10.1016\/j.image.2026.117536_b46","series-title":"Netflix public dataset","author":"Netflix, Inc.","year":"2023"},{"key":"10.1016\/j.image.2026.117536_b47","series-title":"Methods, metrics and procedures for statistical evaluation, qualification and comparison of objective quality prediction models","author":"ITU-T","year":"2020"},{"issue":"8","key":"10.1016\/j.image.2026.117536_b48","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1007\/s11263-018-01144-2","article-title":"Video enhancement with task-oriented flow","volume":"127","author":"Xue","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2026.117536_b49","doi-asserted-by":"crossref","unstructured":"C. Godard, O. Mac Aodha, G.J. Brostow, Unsupervised monocular depth estimation with left-right consistency, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 270\u2013279.","DOI":"10.1109\/CVPR.2017.699"},{"key":"10.1016\/j.image.2026.117536_b50","series-title":"Common Test Conditions and Software Reference Configurations","author":"Bossen","year":"2013"},{"key":"10.1016\/j.image.2026.117536_b51","doi-asserted-by":"crossref","unstructured":"A. Mercat, M. Viitanen, J. Vanne, UVG dataset: 50\/120fps 4K sequences for video codec analysis and development, in: Proceedings of the 11th ACM Multimedia Systems Conference, 2020, pp. 297\u2013302.","DOI":"10.1145\/3339825.3394937"}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526000597?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596526000597?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T06:45:51Z","timestamp":1777013151000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596526000597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":51,"alternative-id":["S0923596526000597"],"URL":"https:\/\/doi.org\/10.1016\/j.image.2026.117536","relation":{},"ISSN":["0923-5965"],"issn-type":[{"value":"0923-5965","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Saliency-guided video coding via recurrent learning and perceptual quality assessment","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.image.2026.117536","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"117536"}}