{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T02:06:54Z","timestamp":1768615614212,"version":"3.49.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032144942","type":"print"},{"value":"9783032144959","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-14495-9_25","type":"book-chapter","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T15:22:49Z","timestamp":1768576969000},"page":"329-339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Vector-Quantized Latents for\u00a0Perceptual Low-Resolution Video Compression"],"prefix":"10.1007","author":[{"given":"Manikanta","family":"Kotthapalli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Banafsheh","family":"Rekabdar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,17]]},"reference":[{"issue":"4","key":"25_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3323214","volume":"53","author":"G Lu","year":"2020","unstructured":"Lu, G., et al.: Emerging advances in learned video compression: models, systems and beyond. ACM Comput. Surv. 53(4), 1\u201336 (2020)","journal-title":"ACM Comput. Surv."},{"issue":"7","key":"25_CR2","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1109\/TCSVT.2003.815165","volume":"13","author":"T Wiegand","year":"2003","unstructured":"Wiegand, T., Sullivan, G.J., Bjontegaard, G., Luthra, A.: Overview of the H.264\/AVC video coding standard. IEEE Trans. Circuits Syst. Video Technol. 13(7), 560\u2013576 (2003)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"25_CR3","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"Sullivan, G.J., Ohm, J., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circuits Syst. Video Technol. 22(12), 1649\u20131668 (2012)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Mukherjee, D., Han, J., et al.: An overview of core coding tools in the AV1 video codec. In: Proceedings of the Picture Coding Symposium (PCS) (2018)","DOI":"10.1109\/PCS.2018.8456249"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R., Van Gool, L.: Conditional probability models for deep image compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00462"},{"key":"25_CR6","unstructured":"Ball\u00e9, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, S.J.: Variational image compression with a scale hyperprior. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"25_CR7","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"25_CR8","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"25_CR9","unstructured":"Razavi, A., van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"25_CR10","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"25_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"25_CR13","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"25_CR14","unstructured":"Rippel, O., Bourdev, L.: Real-time adaptive image compression. arXiv preprint arXiv:1705.05823 (2017)"},{"key":"25_CR15","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: DRAW: a recurrent neural network for image generation. In: Advances in Neural Information Processing Systems (NeurIPS) (2015)"},{"key":"25_CR16","unstructured":"Li, J., Li, C., Chen, J., Wang, Y., Kwong, S., Lu, J.: Deep contextual video compression. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021)"},{"issue":"8","key":"25_CR17","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1007\/s11263-018-01144-2","volume":"127","author":"T Xue","year":"2019","unstructured":"Xue, T., Chen, B., Wu, J., Wei, D., Freeman, W.T.: Video enhancement with task-oriented flow. Int. J. Comput. Vision 127(8), 1106\u20131125 (2019). https:\/\/doi.org\/10.1007\/s11263-018-01144-2","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Tschannen, M., Timofte, R., Van Gool, L.: Scale-space flow for end-to-end optimized video compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Guo, Z., Feng, R., Wu, Y., Zhang, Z., Chen, Z.: Learned video compression with feature-level residuals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2020)","DOI":"10.1109\/CVPRW50498.2020.00068"},{"issue":"1","key":"25_CR20","first-page":"123","volume":"32","author":"T Sheng","year":"2022","unstructured":"Sheng, T., Ma, S., Li, X., Li, Y., Gao, Z.: Temporal context-aware learned video compression. IEEE Trans. Circuits Syst. Video Technol. 32(1), 123\u2013145 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Lin, J., Liu, D., Liang, J., Li, H., Wu, F.: Modulated variable-rate deep video compression. In: Proceedings of the Data Compression Conference (DCC) (2021)","DOI":"10.1109\/DCC50243.2021.00058"},{"key":"25_CR22","unstructured":"Choi, J., Choi, K., Park, J., Lee, D., Lee, H., Kim, W.: Variable-rate learned image compression with multi-scale residual VQ. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: Proceedings of the 20th International Conference on Pattern Recognition (ICPR), pp. 2366\u20132369 (2010)","DOI":"10.1109\/ICPR.2010.579"},{"issue":"4","key":"25_CR24","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Jo, Y., Oh, S.W., Kang, J., Kim, S.J.: Deep video super-resolution network using dynamic upsampling filters without explicit motion compensation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00340"},{"key":"25_CR26","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"25_CR27","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"25_CR28","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.D.: Joint autoregressive and hierarchical priors for learned image compression. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"issue":"13","key":"25_CR29","doi-asserted-by":"publisher","first-page":"5573","DOI":"10.3390\/app14135573","volume":"14","author":"R Guo","year":"2024","unstructured":"Guo, R., Liu, J., Chen, X., Liu, D.: Video multi-scale-based end-to-end rate control in deep contextual video compression. Appl. Sci. 14(13), 5573 (2024)","journal-title":"Appl. Sci."},{"key":"25_CR30","unstructured":"Zhu, J., Zhang, X., Tang, L., Jiang, J.: MSNeRV: neural video representation with multi-scale feature fusion. arXiv preprint arXiv:2506.15276 (2025)"},{"key":"25_CR31","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. CRCV-TR-12-01, Center for Research in Computer Vision (CRCV), University of Central Florida (2012)"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-14495-9_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T15:22:53Z","timestamp":1768576973000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-14495-9_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032144942","9783032144959"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-14495-9_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Vegas, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}