{"list":"other","total":65,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"1512.09300","title":"Autoencoding beyond pixels using a learned similarity metric","created":"2015-12-31","cited_by_count":407},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","created":"2015-06-07","cited_by_count":362},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2004.04572","title":"ARCH: Animatable Reconstruction of Clothed Humans","created":"2020-04-08","cited_by_count":257},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1803.04758","title":"Video Based Reconstruction of 3D People Models","created":"2018-03-13","cited_by_count":238},{"id":"2007.03858","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","created":"2020-07-08","cited_by_count":231},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"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":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"2005.05732","title":"Skeleton-Aware Networks for Deep Motion Retargeting","created":"2020-05-12","cited_by_count":124},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"1910.09070","title":"Structured Prediction Helps 3D Human Motion Modelling","created":"2019-10-20","cited_by_count":96},{"id":"1703.04454","title":"Detailed, accurate, human shape estimation from clothed 3D scan sequences","created":"2017-03-13","cited_by_count":89},{"id":"1804.05653","title":"Neural Kinematic Networks for Unsupervised Motion Retargetting","created":"2018-04-16","cited_by_count":88},{"id":"1808.04545","title":"MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics","created":"2018-08-14","cited_by_count":86},{"id":"1702.08139","title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","created":"2017-02-27","cited_by_count":81},{"id":"2006.06119","title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","created":"2020-06-11","cited_by_count":81},{"id":"1908.07117","title":"360-Degree Textures of People in Clothing from a Single Image","created":"2019-08-20","cited_by_count":75},{"id":"1706.00400","title":"Learning Disentangled Representations with Semi-Supervised Deep Generative Models","created":"2017-06-01","cited_by_count":72},{"id":"1807.11152","title":"Pose Guided Human Video Generation","created":"2018-07-30","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":"1705.06400","title":"Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks","created":"2017-05-18","cited_by_count":61},{"id":"1812.02246","title":"Photo Wake-Up: 3D Character Animation from a Single Photo","created":"2018-12-05","cited_by_count":60},{"id":"2004.00542","title":"Future Video Synthesis with Object Motion Prediction","created":"2020-04-01","cited_by_count":57},{"id":"2004.01255","title":"Guided Variational Autoencoder for Disentanglement Learning","created":"2020-04-02","cited_by_count":57},{"id":"1711.08682","title":"Deep Video Generation, Prediction and Completion of Human Action Sequences","created":"2017-11-23","cited_by_count":52},{"id":"2007.06843","title":"Socially and Contextually Aware Human Motion and Pose Forecasting","created":"2020-07-14","cited_by_count":51},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"1912.10150","title":"Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions","created":"2019-12-21","cited_by_count":46},{"id":"1901.07677","title":"Modeling Human Motion with Quaternion-based Neural Networks","created":"2019-01-21","cited_by_count":45},{"id":"1812.00452","title":"Disentangling Propagation and Generation for Video Prediction","created":"2018-12-02","cited_by_count":44},{"id":"1612.05877","title":"Deep Learning on Lie Groups for Skeleton-based Action Recognition","created":"2016-12-18","cited_by_count":42},{"id":"1910.02027","title":"Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction","created":"2019-10-04","cited_by_count":36},{"id":"1708.05980","title":"Attentive Semantic Video Generation using Captions","created":"2017-08-20","cited_by_count":28},{"id":"1601.01006","title":"Space-Time Representation of People Based on 3D Skeletal Data: A Review","created":"2016-01-05","cited_by_count":24},{"id":"1803.08085","title":"Probabilistic Video Generation using Holistic Attribute Control","created":"2018-03-21","cited_by_count":24},{"id":"2008.10162","title":"Hierarchical Style-based Networks for Motion Synthesis","created":"2020-08-24","cited_by_count":23},{"id":"2006.03630","title":"SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images","created":"2020-06-05","cited_by_count":16},{"id":"1910.04742","title":"MetaPix: Few-Shot Video Retargeting","created":"2019-10-10","cited_by_count":13},{"id":"2007.08397","title":"Controllable Image Synthesis via SegVAE","created":"2020-07-16","cited_by_count":13},{"id":"1904.02912","title":"Point-to-Point Video Generation","created":"2019-04-05","cited_by_count":11},{"id":"1609.03773","title":"Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups","created":"2016-09-13","cited_by_count":10},{"id":"1910.06699","title":"Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models","created":"2019-10-12","cited_by_count":6}],"next_cursor":null}