{"list":"other","total":83,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"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":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","created":"2015-06-07","cited_by_count":362},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"1908.05436","title":"Learning Trajectory Dependencies for Human Motion Prediction","created":"2019-08-15","cited_by_count":246},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"2003.01460","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","created":"2020-03-03","cited_by_count":195},{"id":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"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":"2007.11755","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","created":"2020-07-23","cited_by_count":165},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"2103.04559","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","created":"2021-03-08","cited_by_count":143},{"id":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"1805.00655","title":"Convolutional Sequence to Sequence Model for Human Dynamics","created":"2018-05-02","cited_by_count":115},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112},{"id":"1610.00527","title":"Video Pixel Networks","created":"2016-10-03","cited_by_count":108},{"id":"1904.12165","title":"Improved Conditional VRNNs for Video Prediction","created":"2019-04-27","cited_by_count":104},{"id":"1903.02330","title":"Self-Supervised Learning of 3D Human Pose using Multi-view Geometry","created":"2019-03-06","cited_by_count":98},{"id":"1811.07490","title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","created":"2018-11-19","cited_by_count":92},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"1704.05831","title":"Learning to Generate Long-term Future via Hierarchical Prediction","created":"2017-04-19","cited_by_count":88},{"id":"1705.00053","title":"The Pose Knows: Video Forecasting by Generating Pose Futures","created":"2017-04-28","cited_by_count":88},{"id":"1804.05653","title":"Neural Kinematic Networks for Unsupervised Motion Retargetting","created":"2018-04-16","cited_by_count":88},{"id":"1809.03036","title":"A Neural Temporal Model for Human Motion Prediction","created":"2018-09-09","cited_by_count":87},{"id":"1808.04545","title":"MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics","created":"2018-08-14","cited_by_count":86},{"id":"1901.03416","title":"Preventing Posterior Collapse with delta-VAEs","created":"2019-01-10","cited_by_count":86},{"id":"1809.01995","title":"Dense Pose Transfer","created":"2018-09-06","cited_by_count":83},{"id":"1801.02753","title":"SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis","created":"2018-01-09","cited_by_count":81},{"id":"2007.09278","title":"XingGAN for Person Image Generation","created":"2020-07-17","cited_by_count":81},{"id":"1807.11152","title":"Pose Guided Human Video Generation","created":"2018-07-30","cited_by_count":67},{"id":"2003.07581","title":"Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild","created":"2020-03-17","cited_by_count":66},{"id":"2011.14679","title":"CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild","created":"2020-11-30","cited_by_count":65},{"id":"2103.09479","title":"Disentangled Cycle Consistency for Highly-realistic Virtual Try-On","created":"2021-03-17","cited_by_count":62},{"id":"1807.09755","title":"Flow-Grounded Spatial-Temporal Video Prediction from Still Images","created":"2018-07-25","cited_by_count":55},{"id":"2104.07021","title":"Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing","created":"2021-04-14","cited_by_count":54},{"id":"2012.03796","title":"Pose-Guided Human Animation from a Single Image in the Wild","created":"2020-12-07","cited_by_count":53},{"id":"1711.08682","title":"Deep Video Generation, Prediction and Completion of Human Action Sequences","created":"2017-11-23","cited_by_count":52},{"id":"2104.04029","title":"TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild","created":"2021-04-08","cited_by_count":52},{"id":"1909.11081","title":"Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation","created":"2019-09-24","cited_by_count":51},{"id":"1806.04768","title":"Hierarchical Long-term Video Prediction without Supervision","created":"2018-06-12","cited_by_count":50},{"id":"2104.07995","title":"Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation","created":"2021-04-16","cited_by_count":47},{"id":"1905.01680","title":"Learning Character-Agnostic Motion for Motion Retargeting in 2D","created":"2019-05-05","cited_by_count":45},{"id":"1712.00311","title":"Folded Recurrent Neural Networks for Future Video Prediction","created":"2017-12-01","cited_by_count":44},{"id":"1909.03449","title":"Imitation Learning for Human Pose Prediction","created":"2019-09-08","cited_by_count":44},{"id":"2105.03136","title":"Interpretable Social Anchors for Human Trajectory Forecasting in Crowds","created":"2021-05-07","cited_by_count":44},{"id":"2107.14202","title":"Human Trajectory Prediction via Counterfactual Analysis","created":"2021-07-29","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":"2003.14401","title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting","created":"2020-03-31","cited_by_count":36},{"id":"1902.07367","title":"Human Motion Prediction via Learning Local Structure Representations and Temporal Dependencies","created":"2019-02-20","cited_by_count":34},{"id":"2012.10974","title":"High-Fidelity Neural Human Motion Transfer from Monocular Video","created":"2020-12-20","cited_by_count":31},{"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":"1802.01873","title":"Every Smile is Unique: Landmark-Guided Diverse Smile Generation","created":"2018-02-06","cited_by_count":23},{"id":"1904.05118","title":"Text Guided Person Image Synthesis","created":"2019-04-10","cited_by_count":22},{"id":"2008.04888","title":"Adversarial Generative Grammars for Human Activity Prediction","created":"2020-08-11","cited_by_count":19},{"id":"2012.01158","title":"Single-Shot Freestyle Dance Reenactment","created":"2020-12-02","cited_by_count":10},{"id":"1908.04015","title":"Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold","created":"2019-08-12","cited_by_count":4},{"id":"2009.08027","title":"DanceIt: Music-inspired Dancing Video Synthesis","created":"2020-09-17","cited_by_count":3}],"next_cursor":null}