{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:32:29Z","timestamp":1753601549576},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030414030"},{"type":"electronic","value":"9783030414047"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-41404-7_44","type":"book-chapter","created":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T12:02:58Z","timestamp":1582372978000},"page":"625-638","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SSA-GAN: End-to-End Time-Lapse Video Generation with Spatial Self-Attention"],"prefix":"10.1007","author":[{"given":"Daichi","family":"Horita","sequence":"first","affiliation":[]},{"given":"Keiji","family":"Yanai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"key":"44_CR1","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Cai, H., Bai, C., Tai, Y., Tang, C.: Deep video generation, prediction and completion of human action sequences. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01216-8_23"},{"key":"44_CR3","unstructured":"Cheng, X., Dale, C., Liu, J.: Understanding the characteristics of internet short video sharing: Youtube as a case study. In: 2012 IEEE International Symposium on Multimedia (ISM) (2007)"},{"key":"44_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-319-46723-8_49","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2016","author":"\u00d6 \u00c7i\u00e7ek","year":"2016","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424\u2013432. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46723-8_49"},{"key":"44_CR5","unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Proceedings of Neural Information Processing Systems (2016)"},{"key":"44_CR6","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Proceedings of Neural Information Processing Systems (2014)"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"44_CR8","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Proceedings of the Neural Information Processing Systems (2018)"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Proceedings of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"44_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML) (2015)"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"44_CR13","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: Proceedings of the International Conference on Learning Representation (ICLR) (2017)"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Li, F., Niebles, J.C.: Dense-captioning events in videos. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.: Flow-grounded spatial-temporal video prediction from still images. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01240-3_37"},{"key":"44_CR16","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: Proceedings of the International Conference on Learning Representation (ICLR) (2016)"},{"key":"44_CR17","doi-asserted-by":"crossref","unstructured":"Ohnishi, K., Yamamoto, S., Ushiku, Y., Harada, T.: Hierarchical video generation from orthogonal information: optical flow and texture. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.11881"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Pan, P., Xu, Z., Yang, Y., Wu, F., Zhuang, Y.: Hierarchical recurrent neural encoder for video representation with application to captioning. In: Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.117"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"44_CR20","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: Proceedings of the International Conference on Learning Representation (ICLR) (2016)"},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E.: Temporal generative adversarial nets. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.308"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.: Action temporal localization in untrimmed videos via multi-stage CNNs. In: Proceeding of the IEEE Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"44_CR23","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning (ICML) (2015)"},{"key":"44_CR24","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"44_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of Neural Information Processing Systems (2017)"},{"key":"44_CR26","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Proceedings of the Neural Information Processing Systems (2016)"},{"key":"44_CR27","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR) (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"44_CR28","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R.B., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"44_CR29","doi-asserted-by":"crossref","unstructured":"Xiong, W., Luo, W., Ma, L., Liu, W., Luo, J.: Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks. In: Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00251"},{"key":"44_CR30","doi-asserted-by":"crossref","unstructured":"Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., Lin, D.: Pose guided human video generation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"44_CR31","unstructured":"Zhang, H., Goodfellow, I.J., Metaxas, D.N., Odena, A.: Self-attention generative adversarial networks. arXiv:1805.08318 (2018)"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Learning to forecast and refine residual motion for image-to-video generation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01267-0_24"},{"key":"44_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/978-3-319-46484-8_16","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Zhou","year":"2016","unstructured":"Zhou, Y., Berg, T.L.: Learning temporal transformations from time-lapse videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 262\u2013277. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_16"},{"key":"44_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41404-7_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T08:21:55Z","timestamp":1665908515000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41404-7_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030414030","9783030414047"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41404-7_44","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":"23 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2019.org\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"214","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":"125","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":"58% - 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":"2","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":"for ACPR 2019 Workshops volume accepted 17 full papers and 6 short papers","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)"}}]}}