{"list":"other","total":79,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"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":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"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":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"1711.11586","title":"Toward Multimodal Image-to-Image Translation","created":"2017-11-30","cited_by_count":296},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1808.04730","title":"Analyzing Inverse Problems with Invertible Neural Networks","created":"2018-08-14","cited_by_count":242},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"1602.02644","title":"Generating Images with Perceptual Similarity Metrics based on Deep Networks","created":"2016-02-08","cited_by_count":222},{"id":"2006.14200","title":"SRFlow: Learning the Super-Resolution Space with Normalizing Flow","created":"2020-06-25","cited_by_count":209},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"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":"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":"1803.10967","title":"Context-aware Synthesis for Video Frame Interpolation","created":"2018-03-29","cited_by_count":153},{"id":"1907.02392","title":"Guided Image Generation with Conditional Invertible Neural Networks","created":"2019-07-04","cited_by_count":147},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"1802.07088","title":"i-RevNet: Deep Invertible Networks","created":"2018-02-20","cited_by_count":137},{"id":"1706.02262","title":"InfoVAE: Information Maximizing Variational Autoencoders","created":"2017-06-07","cited_by_count":124},{"id":"2002.09219","title":"Stochastic Latent Residual Video Prediction","created":"2020-02-21","cited_by_count":108},{"id":"2006.10704","title":"Latent Video Transformer","created":"2020-06-18","cited_by_count":106},{"id":"1904.12165","title":"Improved Conditional VRNNs for Video Prediction","created":"2019-04-27","cited_by_count":104},{"id":"1512.00570","title":"Attribute2Image: Conditional Image Generation from Visual Attributes","created":"2015-12-02","cited_by_count":93},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"1709.07592","title":"Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks","created":"2017-09-22","cited_by_count":89},{"id":"1705.00053","title":"The Pose Knows: Video Forecasting by Generating Pose Futures","created":"2017-04-28","cited_by_count":88},{"id":"1903.01434","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","created":"2019-03-04","cited_by_count":74},{"id":"1903.06946","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","created":"2019-03-16","cited_by_count":67},{"id":"1609.09408","title":"Cooperative Training of Descriptor and Generator Networks","created":"2016-09-29","cited_by_count":60},{"id":"2004.00542","title":"Future Video Synthesis with Object Motion Prediction","created":"2020-04-01","cited_by_count":57},{"id":"2004.13166","title":"A Disentangling Invertible Interpretation Network for Explaining Latent Representations","created":"2020-04-27","cited_by_count":57},{"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":"1912.07009","title":"C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds","created":"2019-12-15","cited_by_count":50},{"id":"2010.13821","title":"Wavelet Flow: Fast Training of High Resolution Normalizing Flows","created":"2020-10-26","cited_by_count":33},{"id":"1904.05869","title":"Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning","created":"2019-04-11","cited_by_count":20},{"id":"1812.10587","title":"Learning Dynamic Generator Model by Alternating Back-Propagation Through Time","created":"2018-12-27","cited_by_count":18},{"id":"2008.09655","title":"DeepLandscape: Adversarial Modeling of Landscape Video","created":"2020-08-21","cited_by_count":17},{"id":"1706.06982","title":"Two-Stream Convolutional Networks for Dynamic Texture Synthesis","created":"2017-06-21","cited_by_count":15},{"id":"1910.07192","title":"Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesis","created":"2019-10-16","cited_by_count":15},{"id":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14},{"id":"2008.01777","title":"Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs","created":"2020-08-04","cited_by_count":10},{"id":"1710.00489","title":"SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control","created":"2017-10-02","cited_by_count":7},{"id":"1708.01191","title":"Unsupervised Video Understanding by Reconciliation of Posture Similarities","created":"2017-08-03","cited_by_count":4},{"id":"2012.09237","title":"Unsupervised Behaviour Analysis and Magnification (uBAM) using Deep Learning","created":"2020-12-16","cited_by_count":3}],"next_cursor":null}