{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:12:27Z","timestamp":1785420747628,"version":"3.56.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"17-18","license":[{"start":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T00:00:00Z","timestamp":1578355200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T00:00:00Z","timestamp":1578355200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s11042-019-08572-3","type":"journal-article","created":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T23:02:14Z","timestamp":1578438134000},"page":"11699-11722","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Overview of Research in the field of Video Compression using Deep Neural Networks"],"prefix":"10.1007","volume":"79","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7827-6742","authenticated-orcid":false,"given":"Raz","family":"Birman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoram","family":"Segal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ofer","family":"Hadar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,1,7]]},"reference":[{"key":"8572_CR1","unstructured":"Ball\u2019e J, Laparra V, Simoncelli EP (2017) End-to-end optimized image compression. International Conference on Learning Representations (ICLR)"},{"key":"8572_CR2","unstructured":"R. Birman, Y. Segal, A. D. Malka, O. Hadar (2018) Intra prediction with deep learning. SPIE Optics + Photonics conference, San Diego, California"},{"key":"8572_CR3","unstructured":"Chaabouni S, Benois-Pineau J, Hadar O, Amar CB (2016) Deep learning for saliency prediction in natural video. arXiv preprint arXiv:1604.08010"},{"key":"8572_CR4","doi-asserted-by":"crossref","unstructured":"Chen T, Liu H, Shen Q, Yue T, Cao X, Ma Z (2017) DeepCoder: A deep neural network based video compression. IEEE Visual Communications and Image Processing (VCIP), pp. 1\u20134","DOI":"10.1109\/VCIP.2017.8305033"},{"key":"8572_CR5","doi-asserted-by":"crossref","unstructured":"Chen Z, He T, Jin X, Wu F (2019) Learning for video compression. IEEE Transactions on Circuits and Systems for Video Technology","DOI":"10.1109\/TCSVT.2019.2892608"},{"key":"8572_CR6","unstructured":"Cui W, Zhang T, Zhang S, Jiang F, Zuo W, Zhao D (2018) Convolutional neural networks based intra prediction for HEVC. arXiv preprint arXiv:1808.05734"},{"key":"8572_CR7","unstructured":"Goodfellow JI, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial networks. Advances in neural information processing systems (pp. 2672-2680)"},{"key":"8572_CR8","unstructured":"Hadar O, Shleifer A, Mukherjee D, Joshi U, Mazar I, Yuzvinsky M, Tavor N, Itzhak N, Birman R (2017) Novel Modes and Adaptive Block Scanning Order for Intra Prediction in AV1. SPIE Optics + Photonics conference, San Diego, California (USA)"},{"issue":"5786","key":"8572_CR9","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"issue":"8","key":"8572_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"8572_CR11","unstructured":"Hu Y, Yang W, Li M, Liu J (2018) Progressive spatial recurrent neural network for intra prediction. arXiv preprint arXiv:1807.02232"},{"key":"8572_CR12","doi-asserted-by":"crossref","unstructured":"Huo S, Liu D, Wu F, Li H (2018) Convolutional neural network-based motion compensation refinement for video coding. IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1\u20134","DOI":"10.1109\/ISCAS.2018.8351609"},{"key":"8572_CR13","doi-asserted-by":"crossref","unstructured":"Ibrahim EM, Badry E, Abdelsalam AM, Abdalla IL, Sayed M, Shalaby H (2018) Neural networks based fractional pixel motion estimation for HEVC. IEEE International Symposium on Multimedia (ISM), pp. 110\u2013113","DOI":"10.1109\/ISM.2018.00027"},{"issue":"10","key":"8572_CR14","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1109\/TCSVT.2017.2734838","volume":"28","author":"F Jiang","year":"2017","unstructured":"Jiang F, Tao W, Liu S, Ren J, Guo X, Zhao D (2017) An end-to-end compression framework based on convolutional neural networks. IEEE Transact Circ Syst Vid Technol 28(10):3007\u20133018","journal-title":"IEEE Transact Circ Syst Vid Technol"},{"key":"8572_CR15","unstructured":"Johnston N, Vincent D, Minnen D, Covell M, Singh S, Chinen T, Hwang SJ, Shor J, Toderici G (2017) Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks. arXiv preprint arXiv: 1703.10114"},{"key":"8572_CR16","unstructured":"Kin CYS, Coker B (2017) Video compression using recurrent convolutional neural networks. cs231n\/Stanford"},{"key":"8572_CR17","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, pp. 1097\u20131105"},{"key":"8572_CR18","doi-asserted-by":"crossref","unstructured":"Lainema J, Ugur K (2011) Angular intra prediction in high efficiency video coding (HEVC). Multimedia Signal Processing (MMSP), IEEE 13th International Workshop","DOI":"10.1109\/MMSP.2011.6093806"},{"issue":"12","key":"8572_CR19","doi-asserted-by":"publisher","first-page":"1792","DOI":"10.1109\/TCSVT.2012.2221525","volume":"22","author":"J Lainema","year":"2012","unstructured":"Lainema J, Bossen F, Han WJ, Min J, Ugur K (2012) Intra coding of the HEVC standard. IEEE Transact Circ Syst Vid Technol 22(12):1792\u20131801","journal-title":"IEEE Transact Circ Syst Vid Technol"},{"key":"8572_CR20","unstructured":"Larsen ABL, S\u00f8nderby SK, Larochelle H, Winther O (2015) Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv: 1512.09300"},{"key":"8572_CR21","doi-asserted-by":"crossref","unstructured":"Laude T, Ostermann J (2016) Deep learning-based intra prediction mode decision for HEVC. Picture Coding Symposium (PCS), IEEE","DOI":"10.1109\/PCS.2016.7906399"},{"key":"8572_CR22","doi-asserted-by":"crossref","unstructured":"Lee JK, Kim N, Cho S, Kang JW (2018) Convolution neural network based video coding technique using reference video synthesis. Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, pp. 505\u2013508","DOI":"10.23919\/APSIPA.2018.8659611"},{"key":"8572_CR23","unstructured":"Li Honggui, M. Trocan (2018) Deep neural network based single pixel prediction for unified video coding. Neurocomputing 272, pp. 558\u2013570"},{"key":"8572_CR24","doi-asserted-by":"crossref","unstructured":"Li J, Li B, Xu J, Xiong R (2017) Intra prediction using fully connected network for video coding. IEEE International Conference on Image Processing (ICIP), pp. 1\u20135","DOI":"10.1109\/ICIP.2017.8296231"},{"key":"8572_CR25","unstructured":"Li Y, Liu D, Li H, Li L, Wu F, Zhang H, Yang H (2017) Convolutional neural network-based block up-sampling for intra frame coding. IEEE Transactions on Circuits and Systems Video Technology 28, no. 9. pp. 2316\u20132330"},{"key":"8572_CR26","doi-asserted-by":"crossref","unstructured":"Li Y, Li B, Liu D, Chen Z (2017) A convolutional neural network-based approach to rate control in HEVC intra coding. 2017 IEEE Visual Communications Image Processing (VCIP), pp. 1\u20134","DOI":"10.1109\/VCIP.2017.8305050"},{"key":"8572_CR27","doi-asserted-by":"crossref","unstructured":"Lin J, Liu D, Li H, Wu F (2018) Generative adversarial network-based frame extrapolation for video coding. VCIP:pp. 1\u20134.","DOI":"10.1109\/VCIP.2018.8698615"},{"issue":"5","key":"8572_CR28","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1109\/TIP.2018.2882923","volume":"28","author":"J Liu","year":"2019","unstructured":"Liu J, Xia S, Yang W, Li M, Liu D (2019) One-for-all: grouped variation network based fractional interpolation in video coding. IEEE Transact Image Process 28(5):2140\u20132151","journal-title":"IEEE Transact Image Process"},{"key":"8572_CR29","unstructured":"Liu D, Li Y, Lin J, Li H, Wu F (2019) Deep learning-based video coding: a review and a case study. arXiv preprint arXiv:1904.12462"},{"key":"8572_CR30","unstructured":"Lu G, Ouyang W, Xu D, Zhang X, Cai C, Gao Z (2018) DVC: an end-to-end deep video compression framework. arXiv preprint arXiv:1812.00101"},{"key":"8572_CR31","doi-asserted-by":"publisher","unstructured":"Ma S, Zhang X, Jia C, Zhao Z, Wang S, Wang S (2019) Image and video compression with neural networks: A review. IEEE Transact Circ Syst Vid Technol. https:\/\/doi.org\/10.1109\/TCSVT.2019.2910119","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"8572_CR32","unstructured":"Mathieu M, Couprie C, LeCun Y (2015) Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440"},{"key":"8572_CR33","doi-asserted-by":"crossref","unstructured":"Mukherjee D, Su H, Bankoski J, Converse A, Han J, Liu Z, Xu Y (2015) An overview of new video coding tools under consideration for VP10: the successor to VP9. In\u00a0Applications of Digital Image Processing XXXVIII, vol. 9599, p. 95991E. International Society for Optics and Photonics.","DOI":"10.1117\/12.2191104"},{"key":"8572_CR34","unstructured":"Oord AVD, Kalchbrenner N, Kavukcuoglu K (2017) Pixel recurrent neural networks. International Conference on Machine Learning (ICML)"},{"key":"8572_CR35","doi-asserted-by":"crossref","unstructured":"Santurkar S, Budden D, Shavit N (2018) Generative compression. Picture coding symposium (PCS). IEEE, pp. 258\u2013262","DOI":"10.1109\/PCS.2018.8456298"},{"key":"8572_CR36","doi-asserted-by":"crossref","unstructured":"Schiopu I, Liu Y, Munteanu A (2018) CNN-based Prediction for Lossless Coding of Photographic Images\u201d. in IEEE Picture Coding Symposium (PCS) (pp. 16\u201320)","DOI":"10.1109\/PCS.2018.8456311"},{"key":"8572_CR37","doi-asserted-by":"crossref","unstructured":"Selimovi\u0107 A, Meden B, Peer P, Hladnik A (2018) Analysis of Content-Aware Image Compression with VGG16. 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI). IEEE, pp. 1\u20137","DOI":"10.1109\/IWOBI.2018.8464188"},{"issue":"6","key":"8572_CR38","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1109\/TCSVT.2011.2130390","volume":"21","author":"M Shen","year":"2011","unstructured":"Shen M, Xue P, Wang C (2011) Down-sampling based video coding using super-resolution technique. IEEE Transact Circ Syst Vid Technol 21(6):755\u2013765","journal-title":"IEEE Transact Circ Syst Vid Technol"},{"key":"8572_CR39","unstructured":"Srivastava N, Mansimov E, Salakhudinov R (2015) Unsupervised learning of video representations using lstms. International conference on machine learning, pp. 843\u2013852"},{"key":"8572_CR40","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1155\/2014\/716020","volume":"2014","author":"H Su","year":"2014","unstructured":"Su H, Wen M, Wu N, Ren J, Zhang C (2014) Efficient Parallel Video Processing Techniques on GPU: From Framework to Implementation. Sci World J 2014, Article ID 716020:19. https:\/\/doi.org\/10.1155\/2014\/716020","journal-title":"Sci World J"},{"issue":"12","key":"8572_CR41","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"Sullivan GJ, Ohm J, Han W-J, Wiegand T (2012) Overview of the high efficiency video coding (hevc) standard. IEEE Transact Circ Syst Vid Technol 22(12):1649\u20131668","journal-title":"IEEE Transact Circ Syst Vid Technol"},{"key":"8572_CR42","doi-asserted-by":"crossref","unstructured":"Takahashi K, Naemura T, Tanaka M (2011) Rate-distortion analysis of super-resolution image\/video decoding. IEEE International Conference on Image Processing. IEEE, pp. 1629\u20131632","DOI":"10.1109\/ICIP.2011.6115764"},{"key":"8572_CR43","doi-asserted-by":"crossref","unstructured":"Toderici G, Vincent D, Johnston N, Jin Hwang S, Minnen D, Shor J, Covell M (2017) Full resolution image compression with recurrent neural networks. IEEE Conference on Computer Vision Pattern Recognition, pp. 5306\u20135314","DOI":"10.1109\/CVPR.2017.577"},{"key":"8572_CR44","doi-asserted-by":"crossref","unstructured":"Wang Y, Fan X, Jia C, Zhao D, Gao W (2018) Neural network based inter prediction for HEVC. IEEE International Conference on Multimedia and Expo (ICME) (pp. 1\u20136)","DOI":"10.1109\/ICME.2018.8486600"},{"key":"8572_CR45","unstructured":"Wu CY, Singhal N, Krahenbuhl P (2018) Video compression through image interpolation. Proceedings of the European Conference on Computer Vision (ECCV), pp. 416\u2013431"},{"key":"8572_CR46","unstructured":"Xingjian SHI, Chen Z, Wang H, Yeung DY, Wong WK, Woo WC (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Advances in neural information processing systems, pp. 802\u2013810"},{"key":"8572_CR47","doi-asserted-by":"crossref","unstructured":"Yan N, Liu D, Li B, Li H, Xu T, Wu F (2018) Convolutional neural network-based invertible half-pixel interpolation filter for video coding. IEEE International Conference on Image Processing (ICIP), pp. 201\u2013205","DOI":"10.1109\/ICIP.2018.8451286"},{"key":"8572_CR48","doi-asserted-by":"crossref","unstructured":"Zhang H, Song L, Luo Z, Yang X (2017) Learning a convolutional neural network for fractional interpolation in HEVC inter coding. IEEE Visual Communications and Image Processing (VCIP), pp. 1\u20134","DOI":"10.1109\/VCIP.2017.8305152"},{"key":"8572_CR49","unstructured":"Zhao Z, Wang S, Zhang X, Ma S, Yang J (2018) CNN-based bi-directional motion compensation for high efficiency video coding, IEEE International Symposium on Circuits and Systems (ISCAS),pp. 1\u20134"},{"key":"8572_CR50","doi-asserted-by":"crossref","unstructured":"Zhu S, Liu C, Xu Z (2019) High-definition video compression system based on perception guidance of salient information of a convolutional neural network and HEVC compression domain. IEEE Transactions on Circuits and Systems for Video Technology","DOI":"10.1109\/TCSVT.2019.2911396"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08572-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-08572-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08572-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T01:07:57Z","timestamp":1609895277000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-08572-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,7]]},"references-count":50,"journal-issue":{"issue":"17-18","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["8572"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-08572-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,7]]},"assertion":[{"value":"21 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}