{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T18:17:57Z","timestamp":1783793877695,"version":"3.55.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012151","type":"print"},{"value":"9783030012168","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01216-8_23","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T15:10:26Z","timestamp":1539011426000},"page":"374-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":83,"title":["Deep Video Generation, Prediction and Completion of Human Action Sequences"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7041-563X","authenticated-orcid":false,"given":"Haoye","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5431-795X","authenticated-orcid":false,"given":"Chunyan","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3148-0380","authenticated-orcid":false,"given":"Yu-Wing","family":"Tai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6495-3685","authenticated-orcid":false,"given":"Chi-Keung","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"23_CR1","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. arXiv e-prints, January 2017"},{"key":"23_CR2","unstructured":"Barratt, S., Sharma, R.: A note on the inception score. arXiv preprint arXiv:1801.01973 (2018)"},{"issue":"5","key":"23_CR3","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1137\/0916069","volume":"16","author":"RH Byrd","year":"1995","unstructured":"Byrd, R.H., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM J. Sci. Comput. 16(5), 1190\u20131208 (1995)","journal-title":"SIAM J. Sci. Comput."},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. arXiv preprint arXiv:1707.09405 (2017)","DOI":"10.1109\/ICCV.2017.168"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Shen, C., Wei, X., Liu, L., Yang, J.: Adversarial posenet: a structure-aware convolutional network for human pose estimation. CoRR abs\/1705.00389 (2017). http:\/\/arxiv.org\/abs\/1705.00389","DOI":"10.1109\/ICCV.2017.137"},{"issue":"2","key":"23_CR7","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2016","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295\u2013307 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Gatys, L., Ecker, A.S., Bethge, M.: Texture synthesis using convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 262\u2013270 (2015)","DOI":"10.1109\/CVPR.2016.265"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"23_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS, pp. 2672\u20132680 (2014). http:\/\/papers.nips.cc\/paper\/5423-generative-adversarial-nets.pdf"},{"key":"23_CR11","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANS. CoRR abs\/1704.00028 (2017). http:\/\/arxiv.org\/abs\/1704.00028"},{"issue":"7","key":"23_CR12","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"23_CR13","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1109\/TPAMI.2006.108","volume":"28","author":"J Jia","year":"2006","unstructured":"Jia, J., Tai, Y.W., Wu, T.P., Tang, C.K.: Video repairing under variable illumination using cyclic motions. IEEE Trans. Pattern Anal. Mach. Intell. 28(5), 832\u2013839 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR14","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":"23_CR15","doi-asserted-by":"crossref","unstructured":"Li, C., Wand, M.: Combining Markov random fields and convolutional neural networks for image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2479\u20132486 (2016)","DOI":"10.1109\/CVPR.2016.272"},{"key":"23_CR16","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. arXiv preprint arXiv:1605.08104 (2016)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. arXiv preprint arXiv:1705.09368 (2017)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Marwah, T., Mittal, G., Balasubramanian, V.N.: Attentive semantic video generation using captions. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1435\u20131443. IEEE (2017)","DOI":"10.1109\/ICCV.2017.159"},{"key":"23_CR19","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. CoRR abs\/1511.05440 (2015). http:\/\/arxiv.org\/abs\/1511.05440"},{"key":"23_CR20","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"23_CR21","unstructured":"Mordvintsev, A., Olah, C., Tyka, M.: Inceptionism: going deeper into neural networks. Google Research Blog, p. 14. Accessed 20 June 2015"},{"key":"23_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Niklaus, S., Mai, L., Liu, F.: Video frame interpolation via adaptive separable convolution. arXiv preprint arXiv:1708.01692 (2017)","DOI":"10.1109\/ICCV.2017.37"},{"issue":"10","key":"23_CR24","doi-asserted-by":"publisher","first-page":"e3","DOI":"10.23915\/distill.00003","volume":"1","author":"A Odena","year":"2016","unstructured":"Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill 1(10), e3 (2016)","journal-title":"Distill"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"P\u00e9rez, P., Gangnet, M., Blake, A.: Poisson image editing. In: ACM Transactions on graphics (TOG), vol. 22, pp. 313\u2013318. ACM (2003)","DOI":"10.1145\/882262.882269"},{"key":"23_CR26","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"23_CR27","first-page":"234","volume-title":"Lecture Notes in Computer Science","author":"Olaf Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. CoRR abs\/1505.04597 (2015). http:\/\/arxiv.org\/abs\/1505.04597"},{"key":"23_CR28","unstructured":"Salimans, T., et al.: Improved techniques for training GANS. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 2234\u20132242. Curran Associates, Inc. (2016). http:\/\/papers.nips.cc\/paper\/6125-improved-techniques-for-training-gans.pdf"},{"key":"23_CR29","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"23_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"23_CR31","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"23_CR32","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"23_CR33","doi-asserted-by":"publisher","unstructured":"Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660. CVPR 2014. IEEE Computer Society, Washington, DC, USA (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.214","DOI":"10.1109\/CVPR.2014.214"},{"key":"23_CR34","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, pp. 3560\u20133569 (2017)"},{"key":"23_CR35","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 613\u2013621. Curran Associates, Inc. (2016). http:\/\/papers.nips.cc\/paper\/6194-generating-videos-with-scene-dynamics.pdf"},{"key":"23_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/978-3-319-46478-7_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Walker","year":"2016","unstructured":"Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: forecasting from static images using variational autoencoders. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 835\u2013851. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_51"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: Video forecasting by generating pose futures. CoRR abs\/1705.00053 (2017). http:\/\/arxiv.org\/abs\/1705.00053","DOI":"10.1109\/ICCV.2017.361"},{"key":"23_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"23_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-319-46493-0_20","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Wang","year":"2016","unstructured":"Wang, X., Gupta, A.: Generative image modeling using style and structure adversarial networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 318\u2013335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_20"},{"issue":"4","key":"23_CR40","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":"23_CR41","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.511"},{"issue":"3","key":"23_CR42","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1109\/TPAMI.2007.60","volume":"29","author":"Y Wexler","year":"2007","unstructured":"Wexler, Y., Shechtman, E., Irani, M.: Space-time completion of video. IEEE Trans. Pattern Anal. Mach. Intell. 29(3), 463\u2013476 (2007). https:\/\/doi.org\/10.1109\/TPAMI.2007.60","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR43","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2016)"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Yan, Y., Xu, J., Ni, B., Yang, X.: Skeleton-aided articulated motion generation. arXiv preprint arXiv:1707.01058 (2017)","DOI":"10.1145\/3123266.3123277"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Yeh, R.A., Chen, C., Lim, T.Y., Schwing, A.G., Hasegawa-Johnson, M., Do, M.N.: Semantic image inpainting with deep generative models. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.728"},{"key":"23_CR46","unstructured":"Zanfir, M., Popa, A.I., Zanfir, A., Sminchisescu, C.: Human appearance transfer"},{"key":"23_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"23_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-319-46454-1_36","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-Y Zhu","year":"2016","unstructured":"Zhu, J.-Y., Kr\u00e4henb\u00fchl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 597\u2013613. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_36"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01216-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:24:19Z","timestamp":1665188659000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}