{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:54:17Z","timestamp":1740099257394,"version":"3.37.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030057152"},{"type":"electronic","value":"9783030057169"}],"license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-05716-9_43","type":"book-chapter","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T19:17:32Z","timestamp":1544469452000},"page":"532-543","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Adversarial Training for Video Disentangled Representation"],"prefix":"10.1007","author":[{"given":"Renjie","family":"Xie","sequence":"first","affiliation":[]},{"given":"Yuancheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Li","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Qiao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: A deep siamese network for scene detection in broadcast videos. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1199\u20131202. ACM (2015)","DOI":"10.1145\/2733373.2806316"},{"key":"43_CR2","unstructured":"Boureau, Y.l., Cun, Y.L.: Sparse feature learning for deep belief networks. In: Advances in Neural Information Processing Systems, pp. 1185\u20131192 (2008)"},{"key":"43_CR3","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGan: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172\u20132180 (2016)"},{"key":"43_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-319-59081-3_23","volume-title":"Advances in Neural Networks - ISNN 2017","author":"YS Chong","year":"2017","unstructured":"Chong, Y.S., Tay, Y.H.: Abnormal event detection in videos using spatiotemporal autoencoder. In: Cong, F., Leung, A., Wei, Q. (eds.) ISNN 2017, Part II. LNCS, vol. 10262, pp. 189\u2013196. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-59081-3_23"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"issue":"1","key":"43_CR6","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: an overview. IEEE Signal Process. Mag. 35(1), 53\u201365 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"43_CR7","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.cviu.2016.08.005","volume":"152","author":"C Cuevas","year":"2016","unstructured":"Cuevas, C., Y\u00e1\u00f1ez, E.M., Garc\u00eda, N.: Labeled dataset for integral evaluation of moving object detection algorithms: LASIESTA. Comput. Vis. Image Underst. 152, 103\u2013117 (2016)","journal-title":"Comput. Vis. Image Underst."},{"key":"43_CR8","unstructured":"Denton, E.L.: Unsupervised learning of disentangled representations from video. In: Advances in Neural Information Processing Systems, pp. 4414\u20134423 (2017)"},{"key":"43_CR9","unstructured":"Dumoulin, V., et al.: Adversarially learned inference. arXiv preprint arXiv:1606.00704 (2016)"},{"key":"43_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"issue":"5786","key":"43_CR11","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"43_CR12","unstructured":"Hsieh, J.T., Liu, B., Huang, D.A., Fei-Fei, L., Niebles, J.C.: Learning to Decompose and Disentangle Representations for Video Prediction. arXiv preprint arXiv:1806.04166 (2018)"},{"key":"43_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"43_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"43_CR15","unstructured":"Larsen, A.B.L., S\u00f8nderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv:1512.09300 (2015)"},{"key":"43_CR16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neucom.2013.09.055","volume":"139","author":"CY Liou","year":"2014","unstructured":"Liou, C.Y., Cheng, W.C., Liou, J.W., Liou, D.R.: Autoencoder for words. Neurocomputing 139, 84\u201396 (2014)","journal-title":"Neurocomputing"},{"key":"43_CR17","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders. arXiv preprint arXiv:1511.05644 (2015)"},{"key":"43_CR18","unstructured":"Mathieu, M.F., Zhao, J.J., Zhao, J., Ramesh, A., Sprechmann, P., LeCun, Y.: Disentangling factors of variation in deep representation using adversarial training. In: Advances in Neural Information Processing Systems, pp. 5040\u20135048 (2016)"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"McLaughlin, N., Martinez\u00a0del Rincon, J., Miller, P.: Recurrent convolutional network for video-based person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1325\u20131334(2016)","DOI":"10.1109\/CVPR.2016.148"},{"key":"43_CR20","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"43_CR21","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. arXiv preprint arXiv:1412.6604 (2014)"},{"key":"43_CR22","unstructured":"Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems, pp. 3546\u20133554 (2015)"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contractive auto-encoders: Explicit invariance during feature extraction. In: Proceedings of the 28th International Conference on International Conference on Machine Learning, pp. 833\u2013840. Omnipress (2011)","DOI":"10.1007\/978-3-642-23783-6_41"},{"key":"43_CR24","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems. pp. 3856\u20133866 (2017)"},{"key":"43_CR25","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: 2004 Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 3, pp. 32\u201336. IEEE (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"issue":"7","key":"43_CR26","doi-asserted-by":"publisher","first-page":"3210","DOI":"10.1109\/TIP.2018.2814344","volume":"27","author":"J Song","year":"2018","unstructured":"Song, J., Zhang, H., Li, X., Gao, L., Wang, M., Hong, R.: Self-supervised video hashing with hierarchical binary auto-encoder. IEEE Trans. Image Process. 27(7), 3210\u20133221 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"Tran, L., Yin, X., Liu, : X.: Disentangled representation learning GAN for pose-invariant face recognition. In: CVPR, vol. 3, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.141"},{"key":"43_CR28","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. arXiv preprint arXiv:1706.08033 (2017)"},{"key":"43_CR29","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096\u20131103. ACM(2008)","DOI":"10.1145\/1390156.1390294"},{"key":"43_CR30","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Advances in Neural Information Processing Systems, pp. 613\u2013621 (2016)"},{"key":"43_CR31","unstructured":"Yingzhen, L., Mandt, S.: Disentangled sequential autoencoder. In: International Conference on Machine Learning, pp. 5656\u20135665 (2018)"},{"key":"43_CR32","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4353\u20134361 (2015)","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"43_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-10605-2_1","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Zhang","year":"2014","unstructured":"Zhang, J., Shan, S., Kan, M., Chen, X.: Coarse-to-fine auto-encoder networks (CFAN) for real-time face alignment. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part II. LNCS, vol. 8690, pp. 1\u201316. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_1"},{"key":"43_CR34","unstructured":"Zhao, J., Mathieu, M., Goroshin, R., LeCun, Y.: Stacked What-Where Auto-encoders. arXiv:1506.02351 [cs, stat], June 2015"},{"key":"43_CR35","unstructured":"Zhao, J., Mathieu, M., LeCun, Y.: Energy-based generative adversarial network. arXiv preprint arXiv:1609.03126 (2016)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05716-9_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,7]],"date-time":"2022-09-07T23:40:00Z","timestamp":1662594000000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05716-9_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"ISBN":["9783030057152","9783030057169"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05716-9_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"8 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - 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"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}