{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T09:12:03Z","timestamp":1778058723781,"version":"3.51.4"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T00:00:00Z","timestamp":1570492800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T00:00:00Z","timestamp":1570492800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s11263-019-01246-5","type":"journal-article","created":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T08:03:11Z","timestamp":1570521791000},"page":"1378-1397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos"],"prefix":"10.1007","volume":"128","author":[{"given":"C.","family":"Spampinato","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2441-0982","authenticated-orcid":false,"given":"S.","family":"Palazzo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"D\u2019Oro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.","family":"Giordano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,8]]},"reference":[{"key":"1246_CR1","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In ICML."},{"key":"1246_CR2","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., & Krishnan, D. (2017). Unsupervised pixel-level domain adaptation with generative adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2017.18"},{"key":"1246_CR3","doi-asserted-by":"crossref","unstructured":"Brox, T., & Malik, J. (2010). Object segmentation by long term analysis of point trajectories. In ECCV.","DOI":"10.1007\/978-3-642-15555-0_21"},{"key":"1246_CR4","doi-asserted-by":"crossref","unstructured":"Caelles, S., Maninis, K. K., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., & Van Gool, L. (2017). One-shot video object segmentation. In CVPR.","DOI":"10.1109\/CVPR.2017.565"},{"key":"1246_CR5","unstructured":"Denton, E. L., Chintala, S., Szlam, A., & Fergus, R. (2015). Deep generative image models using a Laplacian pyramid of adversarial networks. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, & R. Garnett (Eds.), NIPS."},{"key":"1246_CR6","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., & Efros, A. A. (2015). Unsupervised visual representation learning by context prediction. IEEE.","DOI":"10.1109\/ICCV.2015.167"},{"key":"1246_CR7","doi-asserted-by":"crossref","unstructured":"Faktor, A., & Irani, M. (2014). Video segmentation by non-local consensus voting. In BMVC.","DOI":"10.5244\/C.28.21"},{"key":"1246_CR8","unstructured":"Farneb\u00e4ck, G. (2003). Two-frame motion estimation based on polynomial expansion. In Proceedings of the 13th Scandinavian conference on image analysis (SCIA\u201903) (pp. 363\u2013370). Berlin: Springer."},{"key":"1246_CR9","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Zhang, G., & Shi, J. (2012). Video segmentation by tracing discontinuities in a trajectory embedding. In CVPR.","DOI":"10.1109\/CVPR.2012.6247883"},{"key":"1246_CR10","doi-asserted-by":"crossref","unstructured":"Giordano, D., Murabito, F., Palazzo, S., & Spampinato, C. (2015). Superpixel-based video object segmentation using perceptual organization and location prior. In CVPR.","DOI":"10.1109\/CVPR.2015.7299114"},{"key":"1246_CR11","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al. (2014). Generative adversarial nets. In NIPS."},{"issue":"12","key":"1246_CR12","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick, L., Blank, M., Shechtman, E., Irani, M., & Basri, R. (2007). Actions as space-time shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(12), 2247\u20132253.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1246_CR13","doi-asserted-by":"crossref","unstructured":"Haller, E., & Leordeanu, M. (2017). Unsupervised object segmentation in video by efficient selection of highly probable positive features. In ICCV.","DOI":"10.1109\/ICCV.2017.544"},{"key":"1246_CR14","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., & Satoh, Y. (2018). Can spatiotemporal 3D CNNS retrace the history of 2D CNNS and imagenet? In CVPR.","DOI":"10.1109\/CVPR.2018.00685"},{"key":"1246_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1246_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. In NIPS."},{"key":"1246_CR17","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Y., Poursaeed, O., Hopcroft, J., & Belongie, S. (2017). Stacked generative adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2017.202"},{"key":"1246_CR18","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017). Flownet 2.0: Evolution of optical flow estimation with deep networks. In CVPR."},{"key":"1246_CR19","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 ."},{"key":"1246_CR20","doi-asserted-by":"crossref","unstructured":"Jain, S. D., Xiong, B., & Grauman, K. (2017). Fusionseg: Learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In CVPR.","DOI":"10.1109\/CVPR.2017.228"},{"key":"1246_CR21","unstructured":"Jang, Y., Kim, G., & Song, Y. (2018). Video prediction with appearance and motion conditions. In ICML."},{"key":"1246_CR22","doi-asserted-by":"crossref","unstructured":"Keuper, M., Andres, B., & Brox, T. (2015). Motion trajectory segmentation via minimum cost multicuts. In ICCV.","DOI":"10.1109\/ICCV.2015.374"},{"key":"1246_CR23","doi-asserted-by":"crossref","unstructured":"Koh, Y. J., & Kim, C. (2017). Primary object segmentation in videos based on region augmentation and reduction. In CVPR.","DOI":"10.1109\/CVPR.2017.784"},{"key":"1246_CR24","unstructured":"Lai, W. S., Huang, J. B., & Yang, M. H. (2017). Semi-supervised learning for optical flow with generative adversarial networks. In NIPS."},{"key":"1246_CR25","doi-asserted-by":"crossref","unstructured":"Lee, Y. J., Kim, J., & Grauman, K. (2011). Key-segments for video object segmentation. In ICCV.","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"1246_CR26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1246_CR27","doi-asserted-by":"crossref","unstructured":"Mahasseni, B., Lam, M., & Todorovic, S. (2017). Unsupervised video summarization with adversarial LSTM networks. In CVPR.","DOI":"10.1109\/CVPR.2017.318"},{"issue":"6","key":"1246_CR28","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TPAMI.2018.2838670","volume":"41","author":"KK Maninis","year":"2018","unstructured":"Maninis, K. K., Caelles, S., Chen, Y., Pont-Tuset, J., Leal-Taix\u00e9, L., Cremers, D., et al. (2018). Video object segmentation without temporal information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(6), 1515\u20131530.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1246_CR29","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R. Y., Wang, Z., & Paul\u00a0Smolley, S. (2017). Least squares generative adversarial networks. In ICCV.","DOI":"10.1109\/ICCV.2017.304"},{"key":"1246_CR30","unstructured":"Odena, A. (2016). Semi-supervised learning with generative adversarial networks. arXiv preprint arXiv:1606.01583 ."},{"key":"1246_CR31","doi-asserted-by":"crossref","unstructured":"Ohnishi, K., Yamamoto, S., Ushiku, Y., & Harada, T. (2018). Hierarchical video generation from orthogonal information: Optical flow and texture. In AAAI.","DOI":"10.1609\/aaai.v32i1.11881"},{"key":"1246_CR32","doi-asserted-by":"crossref","unstructured":"Papazoglou, A., & Ferrari, V. (2013). Fast object segmentation in unconstrained video. In ICCV.","DOI":"10.1109\/ICCV.2013.223"},{"key":"1246_CR33","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Khoreva, A., Benenson, R., Schiele, B., & Sorkine-Hornung, A. (2017). Learning video object segmentation from static images. In CVPR.","DOI":"10.1109\/CVPR.2017.372"},{"key":"1246_CR34","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Gool, L. V., Gross, M., & Sorkine-Hornung, A. (2016). A benchmark dataset and evaluation methodology for video object segmentation. In CVPR.","DOI":"10.1109\/CVPR.2016.85"},{"key":"1246_CR35","doi-asserted-by":"crossref","unstructured":"Prest, A., Leistner, C., Civera, J., Schmid, C., & Ferrari, V. (2012). Learning object class detectors from weakly annotated video. In CVPR (pp. 3282\u20133289).","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"1246_CR36","unstructured":"Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. In ICLR."},{"key":"1246_CR37","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Doll\u00e1r, P., Girshick, R. B., Gkioxari, G., & He, K. (2018). Data distillation: Towards omni-supervised learning. In CVPR.","DOI":"10.1109\/CVPR.2018.00433"},{"key":"1246_CR38","unstructured":"Roth, K., Lucchi, A., Nowozin, S., & Hofmann, T. (2017). Stabilizing training of generative adversarial networks through regularization. In NIPS."},{"key":"1246_CR39","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E., & Saito, S. (2017). Temporal generative adversarial nets with singular value clipping. In ICCV.","DOI":"10.1109\/ICCV.2017.308"},{"key":"1246_CR40","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X., et al. (2016). Improved techniques for training gans. In D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, R. Garnett (Eds.), NIPS."},{"key":"1246_CR41","doi-asserted-by":"crossref","unstructured":"Shoemake, K. (1985). Animating rotation with quaternion curves. In SIGGRAPH.","DOI":"10.1145\/325165.325242"},{"key":"1246_CR42","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402 ."},{"key":"1246_CR43","doi-asserted-by":"crossref","unstructured":"Souly, N., Spampinato, C., & Shah, M. (2017). Semi supervised semantic segmentation using generative adversarial network. In ICCV.","DOI":"10.1109\/ICCV.2017.606"},{"key":"1246_CR44","doi-asserted-by":"crossref","unstructured":"Stretcu, O., & Leordeanu, M. (2015). Multiple frames matching for object discovery in video. In BMVC.","DOI":"10.5244\/C.29.186"},{"key":"1246_CR45","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al. (2015). Going deeper with convolutions. In CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1246_CR46","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., & Schmid, C. (2017). Learning motion patterns in videos. In CVPR.","DOI":"10.1109\/CVPR.2017.64"},{"issue":"2","key":"1246_CR47","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/s11263-011-0512-5","volume":"100","author":"D Tsai","year":"2012","unstructured":"Tsai, D., Flagg, M., Nakazawa, A., & Rehg, J. M. (2012). Motion coherent tracking using multi-label MRF optimization. International Journal of Computer Vision, 100(2), 190\u2013202.","journal-title":"International Journal of Computer Vision"},{"key":"1246_CR48","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M. Y., Yang, X., & Kautz, J. (2018). Mocogan: Decomposing motion and content for video generation. In CVPR.","DOI":"10.1109\/CVPR.2018.00165"},{"key":"1246_CR49","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial discriminative domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2017.316"},{"key":"1246_CR50","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., & Lee, H. (2017). Decomposing motion and content for natural video sequence prediction. In ICLR."},{"key":"1246_CR51","unstructured":"Vondrick, C., Pirsiavash, H., & Torralba, A. (2016). Generating videos with scene dynamics. In NIPS."},{"key":"1246_CR52","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., & Murphy, K. (2018). Tracking emerges by colorizing videos. In ECCV.","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"1246_CR53","doi-asserted-by":"crossref","unstructured":"Vondrick, C., & Torralba, A. (2017). Generating the future with adversarial transformers. In CVPR.","DOI":"10.1109\/CVPR.2017.319"},{"key":"1246_CR54","unstructured":"Wang, T. C., Liu, M. Y., Zhu, J. Y., Liu, G., Tao, A., Kautz, J., et al. (2018). Video-to-video synthesis. In NeurIPS."},{"key":"1246_CR55","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J., & Porikli, F. (2015). Saliency-aware geodesic video object segmentation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298961"},{"key":"1246_CR56","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In CVPR.","DOI":"10.1109\/CVPR.2017.634"},{"key":"1246_CR57","doi-asserted-by":"crossref","unstructured":"Yi, Z., Zhang, H., Tan, P., & Gong, M. (2017). Dualgan: Unsupervised dual learning for image-to-image translation. In ICCV.","DOI":"10.1109\/ICCV.2017.310"},{"key":"1246_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., et al. (2017). Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In ICCV.","DOI":"10.1109\/ICCV.2017.629"},{"key":"1246_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In ICCV.","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01246-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01246-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01246-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T05:45:07Z","timestamp":1664603107000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01246-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,8]]},"references-count":59,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["1246"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01246-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,8]]},"assertion":[{"value":"31 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}