{"list":"other","total":60,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"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":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"1811.02790","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","created":"2018-11-07","cited_by_count":204},{"id":"1804.01523","title":"Stochastic Adversarial Video Prediction","created":"2018-04-04","cited_by_count":173},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","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":"1812.11446","title":"Greedy Layerwise Learning Can Scale to ImageNet","created":"2018-12-29","cited_by_count":115},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"1902.02102","title":"BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling","created":"2019-02-06","cited_by_count":109},{"id":"1610.00527","title":"Video Pixel Networks","created":"2016-10-03","cited_by_count":108},{"id":"2002.09219","title":"Stochastic Latent Residual Video Prediction","created":"2020-02-21","cited_by_count":108},{"id":"1904.12165","title":"Improved Conditional VRNNs for Video Prediction","created":"2019-04-27","cited_by_count":104},{"id":"1911.01655","title":"High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks","created":"2019-11-05","cited_by_count":88},{"id":"1606.07873","title":"An Uncertain Future: Forecasting from Static Images using Variational Autoencoders","created":"2016-06-25","cited_by_count":87},{"id":"1905.11786","title":"Putting An End to End-to-End: Gradient-Isolated Learning of Representations","created":"2019-05-28","cited_by_count":86},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"id":"1708.00284","title":"Dual Motion GAN for Future-Flow Embedded Video Prediction","created":"2017-08-01","cited_by_count":69},{"id":"1804.02808","title":"Latent Space Policies for Hierarchical Reinforcement Learning","created":"2018-04-09","cited_by_count":67},{"id":"1905.09275","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","created":"2019-05-22","cited_by_count":57},{"id":"1702.08658","title":"Towards Deeper Understanding of Variational Autoencoding Models","created":"2017-02-28","cited_by_count":56},{"id":"1903.02749","title":"Deep Visual MPC-Policy Learning for Navigation","created":"2019-03-07","cited_by_count":56},{"id":"1812.10972","title":"Reasoning About Physical Interactions with Object-Oriented Prediction and Planning","created":"2018-12-28","cited_by_count":51},{"id":"1806.04768","title":"Hierarchical Long-term Video Prediction without Supervision","created":"2018-06-12","cited_by_count":50},{"id":"1811.00684","title":"SDCNet: Video Prediction Using Spatially-Displaced Convolution","created":"2018-11-02","cited_by_count":50},{"id":"1606.02378","title":"SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks","created":"2016-06-08","cited_by_count":49},{"id":"1607.02586","title":"Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks","created":"2016-07-09","cited_by_count":46},{"id":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"1908.08522","title":"Compositional Video Prediction","created":"2019-08-22","cited_by_count":43},{"id":"1505.00295","title":"Dense Optical Flow Prediction from a Static Image","created":"2015-05-02","cited_by_count":36},{"id":"1904.05538","title":"Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight","created":"2019-04-11","cited_by_count":34},{"id":"1702.08396","title":"Learning Hierarchical Features from Generative Models","created":"2017-02-27","cited_by_count":27},{"id":"1810.03043","title":"Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning","created":"2018-10-06","cited_by_count":19},{"id":"1701.08435","title":"Transformation-Based Models of Video Sequences","created":"2017-01-29","cited_by_count":16},{"id":"1804.00062","title":"Visual Robot Task Planning","created":"2018-03-30","cited_by_count":11},{"id":"2001.06232","title":"Sideways: Depth-Parallel Training of Video Models","created":"2020-01-17","cited_by_count":9},{"id":"1910.02564","title":"Action-conditioned Benchmarking of Robotic Video Prediction Models: a Comparative Study","created":"2019-10-07","cited_by_count":8},{"id":"1806.08864","title":"VUNet: Dynamic Scene View Synthesis for Traversability Estimation using an RGB Camera","created":"2018-06-22","cited_by_count":7},{"id":"1706.04124","title":"Video Imagination from a Single Image with Transformation Generation","created":"2017-06-13","cited_by_count":5}],"next_cursor":null}