{"list":"other","total":54,"rows":[{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1908.05932","title":"FSGAN: Subject Agnostic Face Swapping and Reenactment","created":"2019-08-16","cited_by_count":320},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"1804.01523","title":"Stochastic Adversarial Video Prediction","created":"2018-04-04","cited_by_count":173},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"1802.04942","title":"Isolating Sources of Disentanglement in Variational Autoencoders","created":"2018-02-14","cited_by_count":167},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"id":"1807.09251","title":"GANimation: Anatomically-aware Facial Animation from a Single Image","created":"2018-07-24","cited_by_count":161},{"id":"1909.12224","title":"Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis","created":"2019-09-26","cited_by_count":161},{"id":"1803.10404","title":"Lip Movements Generation at a Glance","created":"2018-03-28","cited_by_count":155},{"id":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"1803.02991","title":"Disentangled Sequential Autoencoder","created":"2018-03-08","cited_by_count":120},{"id":"1802.05312","title":"Learning Deep Disentangled Embeddings with the F-Statistic Loss","created":"2018-02-14","cited_by_count":101},{"id":"1705.08841","title":"Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations","created":"2017-05-24","cited_by_count":100},{"id":"1804.07739","title":"Synthesizing Images of Humans in Unseen Poses","created":"2018-04-20","cited_by_count":97},{"id":"1709.07902","title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","created":"2017-09-22","cited_by_count":93},{"id":"1911.12409","title":"PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition","created":"2019-11-27","cited_by_count":91},{"id":"1808.05174","title":"Recycle-GAN: Unsupervised Video Retargeting","created":"2018-08-15","cited_by_count":89},{"id":"1704.05831","title":"Learning to Generate Long-term Future via Hierarchical Prediction","created":"2017-04-19","cited_by_count":88},{"id":"1611.03383","title":"Disentangling factors of variation in deep representations using adversarial training","created":"2016-11-10","cited_by_count":87},{"id":"1807.11079","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","created":"2018-07-29","cited_by_count":85},{"id":"1910.09772","title":"Weakly Supervised Disentanglement with Guarantees","created":"2019-10-22","cited_by_count":82},{"id":"1810.02936","title":"FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification","created":"2018-10-06","cited_by_count":71},{"id":"2008.00820","title":"Generating Visually Aligned Sound from Videos","created":"2020-07-14","cited_by_count":67},{"id":"2005.11437","title":"S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation","created":"2020-05-23","cited_by_count":63},{"id":"1905.01680","title":"Learning Character-Agnostic Motion for Motion Retargeting in 2D","created":"2019-05-05","cited_by_count":45},{"id":"2003.14401","title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting","created":"2020-03-31","cited_by_count":36},{"id":"1904.00129","title":"Dance Dance Generation: Motion Transfer for Internet Videos","created":"2019-03-30","cited_by_count":28},{"id":"1807.09951","title":"Learning to Forecast and Refine Residual Motion for Image-to-Video Generation","created":"2018-07-26","cited_by_count":27},{"id":"1901.07647","title":"Understanding Geometry of Encoder-Decoder CNNs","created":"2019-01-22","cited_by_count":13},{"id":"1911.11294","title":"Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns","created":"2019-11-26","cited_by_count":13},{"id":"2003.09565","title":"Non-Adversarial Video Synthesis with Learned Priors","created":"2020-03-21","cited_by_count":13},{"id":"2007.14184","title":"A Commentary on the Unsupervised Learning of Disentangled Representations","created":"2020-07-28","cited_by_count":13},{"id":"2001.08572","title":"Toward a Controllable Disentanglement Network","created":"2020-01-22","cited_by_count":1}],"next_cursor":null}