{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:19:59Z","timestamp":1761581999272,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,8,18]],"date-time":"2020-08-18T00:00:00Z","timestamp":1597708800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,18]],"date-time":"2020-08-18T00:00:00Z","timestamp":1597708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"TUB\u0130TAK","award":["217E033"],"award-info":[{"award-number":["217E033"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s11760-020-01751-y","type":"journal-article","created":{"date-parts":[[2020,8,18]],"date-time":"2020-08-18T12:03:12Z","timestamp":1597752192000},"page":"401-410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Can learned frame prediction compete with block motion compensation for video coding?"],"prefix":"10.1007","volume":"15","author":[{"given":"Serkan","family":"Sulun","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1465-8121","authenticated-orcid":false,"given":"A. Murat","family":"Tekalp","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,8,18]]},"reference":[{"key":"1751_CR1","unstructured":"A new image format for the web. https:\/\/developers.google.com\/speed\/webp"},{"key":"1751_CR2","unstructured":"x264: A high performance h.264\/avc encoder. https:\/\/www.videolan.org\/developers\/x264.html (2006)"},{"key":"1751_CR3","unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R.H., Levine, S.: Stochastic variational video prediction. In: International Conference on Learning Representations (ICLR), Vancouver, Canada (2018)"},{"key":"1751_CR4","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling (2018). arXiv:1803.01271.pdf"},{"key":"1751_CR5","unstructured":"Bellard, F.: Better portable graphics. https:\/\/www.bellard.org\/bpg. Last accessed: April 2020"},{"key":"1751_CR6","unstructured":"Bellard, F.: Ffmpeg multimedia system. https:\/\/www.ffmpeg.org\/ [Last accessed: Apr. 2020]"},{"key":"1751_CR7","unstructured":"Bjontegaard, G.: Calculation of average PSNR differences between rd-curves. VCEG-M33 (2001)"},{"issue":"2","key":"1751_CR8","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/TCSVT.2019.2892608","volume":"30","author":"Z Chen","year":"2020","unstructured":"Chen, Z., He, T., Jin, X., Wu, F.: Learning for video compression. IEEE Trans. Circuits Syst. Video Technol. 30(2), 566\u2013576 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1751_CR9","unstructured":"Chintala, S., Denton, E., Arjovsky, M., Mathieu, M.: How to train a GAN? Tips and tricks to make GANs work. https:\/\/github.com\/soumith\/ganhacks (2016)"},{"issue":"7","key":"1751_CR10","first-page":"1843","volume":"30","author":"H Choi","year":"2020","unstructured":"Choi, H., Baji\u0107, I.V.: Deep Frame Prediction for Video Coding. IEEE Trans. Circuits Syst. Video Technol. 30(7), 1843\u20131855 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1751_CR11","volume-title":"Deep Learning with Python","author":"F Chollet","year":"2017","unstructured":"Chollet, F.: Deep Learning with Python. Manning Publications Company, Shelter Island (2017)"},{"key":"1751_CR12","unstructured":"Denton, E., Fergus, R.: Stochastic video generation with a learned prior. In: Proceedings of International Conference on Machine Learning (PMLR), vol. 80, pp. 1174\u20131183 (2018)"},{"key":"1751_CR13","unstructured":"Dosovitskiy, A., Brox, T.: Generating images with perceptual similarity metrics based on deep networks. In: Advances in Neural Information Processing Systems, pp. 658\u2013666 (2016)"},{"key":"1751_CR14","doi-asserted-by":"crossref","unstructured":"Dumas, T., Roumy, A., Guillemot, C.: Autoencoder based image compression: can the learning be quantization independent? In: IEEE ICASSP, Calgary, Canada (2018)","DOI":"10.1109\/ICASSP.2018.8462263"},{"key":"1751_CR15","unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Advances in Neural Information Processing Systems, pp. 64\u201372 (2016)"},{"key":"1751_CR16","doi-asserted-by":"crossref","unstructured":"Huo, S., Liu, D., Wu, F., Li, H.: Convolutional neural network-based motion compensation refinement for video coding. In: IEEE International Symposium on Circuits and Systems (ISCAS), Florence, Italy (2018)","DOI":"10.1109\/ISCAS.2018.8351609"},{"key":"1751_CR17","unstructured":"Kalchbrenner, N., Oord, A.v.d., Simonyan, K., Danihelka, I., Vinyals, O., Graves, A., Kavukcuoglu, K.: Video pixel networks. In: Proceedings of International Conference on Machine Learning (PMLR), vol. 70, pp. 1771\u20131779 (2017)"},{"key":"1751_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Representations Learning (ICLR) (2015)"},{"key":"1751_CR19","unstructured":"Lee, A.X., Zhang, R., Ebert, F., Abbeel, P., Finn, C., Levine, S.: Stochastic adversarial video prediction (2018). arXiv:1804.01523"},{"key":"1751_CR20","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), vol. 1, p. 4 (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"1751_CR21","doi-asserted-by":"crossref","unstructured":"Lin, J., Liu, D., Li, H., Wu, F.: Generative adversarial network-based frame extrapolation for video coding. In: Visual Communications and Image Processing (VCIP) (2018)","DOI":"10.1109\/VCIP.2018.8698615"},{"issue":"2","key":"1751_CR22","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1109\/TIP.2017.2767782","volume":"27","author":"G Lu","year":"2018","unstructured":"Lu, G., Zhang, X., Chen, L., Gao, Z.: Novel integration of frame rate up conversion and HEVC coding based on rate-distortion optimization. IEEE Trans. Image Process. 27(2), 678\u2013691 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"1751_CR23","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: Proceedings of International Conference on Learning Representation (ICLR) (2016)"},{"key":"1751_CR24","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (Poster) (2016)"},{"issue":"1\u20133","key":"1751_CR25","first-page":"1","volume":"10","author":"H Schwarz","year":"2016","unstructured":"Schwarz, H., Wiegand, T.: Video coding: part II of fundamentals of source and video coding. Found. Trends Signal Process. 10(1\u20133), 1\u2013346 (2016)","journal-title":"Found. Trends Signal Process."},{"key":"1751_CR26","unstructured":"Selva Castell\u00f3, J.: A comprehensive survey on deep future frame video prediction. Master\u2019s thesis, Universitat Polit\u00e8cnica de Catalunya (2018)"},{"key":"1751_CR27","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: IEEE Conference on CVPR, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"1751_CR28","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild (2012). arXiv:1212.0402"},{"key":"1751_CR29","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"key":"1751_CR30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, vol. 4, p. 12 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1751_CR31","unstructured":"Timofte, R., et al.: NTIRE 2017 challenge on single image super-resolution: methods and results. In: IEEE Conference Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1110\u20131121 (2017)"},{"key":"1751_CR32","unstructured":"Timofte, R., et al.: NTIRE 2018 challenge on single image super-resolution: methods and results. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 965\u2013976 (2018)"},{"key":"1751_CR33","unstructured":"Van Amersfoort, J., Kannan, A., Ranzato, M., Szlam, A., Tran, D., Chintala, S.: Transformation-based models of video sequences (2017). arXiv:1701.08435"},{"key":"1751_CR34","unstructured":"van den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: Proceedings of International Conference on Machine Learning (ICML), vol. 48, pp. 1747\u20131756 (2016)"},{"key":"1751_CR35","unstructured":"Villegas, R., Pathak, A., Kannan, H., Erhan, D., Le, Q.V., Lee, H.: High fidelity video prediction with large stochastic recurrent neural networks. In: Conference on Neural Information Processing Systems (NIPS) (2019)"},{"key":"1751_CR36","unstructured":"Villegas, R., Yang, J., Zou, Y., Sohn, S., Lin, X., Lee, H.: Learning to generate long-term future via hierarchical prediction. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"1751_CR37","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Torralba, A.: Generating the future with adversarial transformers. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.319"},{"key":"1751_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-11021-5_5"},{"key":"1751_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fan, X., Jia, C., Zhao, D., Gao, W.: Neural network based inter prediction for HEVC. In: IEEE International Conference on Multimedia and Expo (2018)","DOI":"10.1109\/ICME.2018.8486600"},{"key":"1751_CR40","unstructured":"Wichers, N., Villegas, R., Erhan, D., Lee, H.: Hierarchical long-term video prediction without supervision. In: Proceedings of International Conference on Machine Learning (PMLR), Stockholm (2018)"},{"key":"1751_CR41","doi-asserted-by":"crossref","unstructured":"Xia, S., Yang, W., Hu, Y., Liu, J.: Deep inter prediction via pixel-wise motion oriented reference generation. In: IEEE International Conference Image Processing (2019)","DOI":"10.1109\/ICIP.2019.8803148"},{"key":"1751_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, L., Wang, S., Zhang, X., Wang, S., Ma, S., Gao, W.: Enhanced CTU-level inter prediction with deep frame rate up-conversion for high efficiency video coding. In: IEEE International Conference on Image Processing (2018)","DOI":"10.1109\/ICIP.2018.8451465"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01751-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-020-01751-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-020-01751-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T21:11:16Z","timestamp":1667855476000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-020-01751-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,18]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,3]]}},"alternative-id":["1751"],"URL":"https:\/\/doi.org\/10.1007\/s11760-020-01751-y","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2020,8,18]]},"assertion":[{"value":"29 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}