{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T18:44:34Z","timestamp":1747248274433,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030585822"},{"type":"electronic","value":"9783030585839"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58583-9_25","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"410-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A Recurrent Transformer Network for Novel View Action Synthesis"],"prefix":"10.1007","author":[{"given":"Kara Marie","family":"Schatz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erik","family":"Quintanilla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shruti","family":"Vyas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yogesh S.","family":"Rawat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"25_CR1","unstructured":"Ballas, N., Yao, L., Pal, C., Courville, A.: Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432, 2015"},{"key":"25_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01228-1_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Bansal","year":"2018","unstructured":"Bansal, A., Ma, S., Ramanan, D., Sheikh, Y.: Recycle-GAN: unsupervised video retargeting. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 122\u2013138. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_8"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Byeon, W., et al.: ContextVP: fully context-aware video prediction. In: Proceedings of the IEEE CVPR Workshops (2018)","DOI":"10.1007\/978-3-030-01270-0_46"},{"key":"25_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1007\/978-3-030-01216-8_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Cai","year":"2018","unstructured":"Cai, H., Bai, C., Tai, Y.-W., Tang, C.-K.: Deep video generation, prediction and completion of human action sequences. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 374\u2013390. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_23"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5933\u20135942 (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789\u20138797 (2018)","DOI":"10.1109\/CVPR.2018.00916"},{"key":"25_CR8","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Efficient video generation on complex datasets. arXiv preprint arXiv:1907.06571 (2019)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Ali Eslami, S.M., et al.: Neural scene representation and rendering. Science (2018)","DOI":"10.1126\/science.aar6170"},{"key":"25_CR10","unstructured":"Goodfellow, I.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369. IEEE (2010)","DOI":"10.1109\/ICPR.2010.579"},{"key":"25_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1007\/978-3-030-11012-3_30","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"MI Lakhal","year":"2019","unstructured":"Lakhal, M.I., Lanz, O., Cavallaro, A.: Pose guided human image synthesis by view disentanglement and enhanced weighting loss. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 380\u2013394. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_30"},{"key":"25_CR13","unstructured":"Jakab, T., Gupta, A., Bilen, H., Vedaldi, A.: Unsupervised learning of object landmarks through conditional image generation. In: Advances in Neural Information Processing Systems, pp. 4016\u20134027 (2018)"},{"key":"25_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/978-3-030-01270-0_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Jayaraman","year":"2018","unstructured":"Jayaraman, D., Gao, R., Grauman, K.: ShapeCodes: self-supervised feature learning by lifting views to Viewgrids. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 126\u2013144. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_8"},{"key":"25_CR15","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_CR16","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Lakhal, M.I., Lanz, O., Cavallaro, A.: View-LSTM: novel-view video synthesis through view decomposition. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00767"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In IEEE Conference on CVPR (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"25_CR19","unstructured":"Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.: Unsupervised learning of view-invariant action representations. In: Advances in Neural Information Processing Systems (2018)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion GAN for future-flow embedded video prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1744\u20131752 (2017)","DOI":"10.1109\/ICCV.2017.194"},{"key":"25_CR21","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: Advances in Neural Information Processing Systems, pp. 406\u2013416 (2017)"},{"key":"25_CR22","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: ICLR (2016)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Regmi, K., Borji, A.: Cross-view image synthesis using conditional GANs. In: IEEE Conference on CVPR (2018)","DOI":"10.1109\/CVPR.2018.00369"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E., Saito, S.: Temporal generative adversarial nets with singular value clipping. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.308"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Shaham, T.R., Dekel, T., Michaeli, T.: SinGAN: learning a generative model from a single natural image. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4570\u20134580 (2019)","DOI":"10.1109\/ICCV.2019.00467"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.-T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE Conference on CVPR (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: Animating arbitrary objects via deep motion transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2377\u20132386 (2019)","DOI":"10.1109\/CVPR.2019.00248"},{"key":"25_CR28","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: Face2Face: real-time face capture and reenactment of RGB videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2387\u20132395 (2016)","DOI":"10.1109\/CVPR.2016.262"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.-Y., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. arXiv preprint arXiv:1707.04993 (2017)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"25_CR31","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NeurIPS (2016)"},{"key":"25_CR32","unstructured":"Vyas, S., Rawat, Y.S., Shah, M.: Time-aware and view-aware video rendering for unsupervised representation learning. arXiv preprint arXiv:1811.10699 (2018)"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: video forecasting by generating pose futures. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3332\u20133341 (2017)","DOI":"10.1109\/ICCV.2017.361"},{"key":"25_CR34","unstructured":"Wang, T.-C., et al.: Video-to-video synthesis. In: Advances in Neural Information Processing Systems, pp. 1144\u20131156 (2018)"},{"key":"25_CR35","unstructured":"Wang, Y., Gao, Z., Long, M., Wang, J., Yu Philip, S.: PredRNN++: towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In: International Conference on Machine Learning, pp. 5110\u20135119 (2018)"},{"key":"25_CR36","unstructured":"Wang, Y., Jiang, L., Yang, M.-H., Li, L.-J., Long, M., Fei-Fei, L.: Eidetic 3D LSTM: a model for video prediction and beyond. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"25_CR37","unstructured":"Wang, Y., Long, M., Wang, J., Gao, Z., Yu Philip, S.: PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMS. In: Advances in Neural Information Processing Systems, pp. 879\u2013888 (2017)"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Memory in memory: a predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9154\u20139162 (2019)","DOI":"10.1109\/CVPR.2019.00937"},{"key":"25_CR39","doi-asserted-by":"crossref","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)","DOI":"10.1109\/TIP.2003.819861"},{"key":"25_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/978-3-030-01249-6_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yang","year":"2018","unstructured":"Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., Lin, D.: Pose guided human video generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 204\u2013219. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_13"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58583-9_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:07:45Z","timestamp":1731888465000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58583-9_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585822","9783030585839"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58583-9_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"19 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}