{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"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":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229},{"id":"1708.01692","title":"Video Frame Interpolation via Adaptive Separable Convolution","created":"2017-08-05","cited_by_count":213},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"1807.07688","title":"Toward Characteristic-Preserving Image-based Virtual Try-On Network","created":"2018-07-20","cited_by_count":192},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"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":"1703.07514","title":"Video Frame Interpolation via Adaptive Convolution","created":"2017-03-22","cited_by_count":158},{"id":"2003.12267","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","created":"2020-03-27","cited_by_count":150},{"id":"1911.00627","title":"Quadratic video interpolation","created":"2019-11-02","cited_by_count":145},{"id":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"1804.04694","title":"A Variational U-Net for Conditional Appearance and Shape Generation","created":"2018-04-12","cited_by_count":124},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"1805.00655","title":"Convolutional Sequence to Sequence Model for Human Dynamics","created":"2018-05-02","cited_by_count":115},{"id":"1812.05478","title":"Human Motion Prediction via Spatio-Temporal Inpainting","created":"2018-12-13","cited_by_count":114},{"id":"1804.07739","title":"Synthesizing Images of Humans in Unseen Poses","created":"2018-04-20","cited_by_count":97},{"id":"1910.09070","title":"Structured Prediction Helps 3D Human Motion Modelling","created":"2019-10-20","cited_by_count":96},{"id":"1804.05653","title":"Neural Kinematic Networks for Unsupervised Motion Retargetting","created":"2018-04-16","cited_by_count":88},{"id":"2010.11531","title":"Convolutional Autoencoders for Human Motion Infilling","created":"2020-10-22","cited_by_count":73},{"id":"1704.02827","title":"Learning Human Motion Models for Long-term Predictions","created":"2017-04-10","cited_by_count":67},{"id":"1807.11152","title":"Pose Guided Human Video Generation","created":"2018-07-30","cited_by_count":67},{"id":"1908.11505","title":"EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera","created":"2019-08-30","cited_by_count":65},{"id":"1810.11610","title":"Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis","created":"2018-10-27","cited_by_count":59},{"id":"1809.10280","title":"Unsupervised Person Image Synthesis in Arbitrary Poses","created":"2018-09-27","cited_by_count":55},{"id":"1604.02703","title":"Synthesizing Training Images for Boosting Human 3D Pose Estimation","created":"2016-04-10","cited_by_count":52},{"id":"1711.08682","title":"Deep Video Generation, Prediction and Completion of Human Action Sequences","created":"2017-11-23","cited_by_count":52},{"id":"1810.02363","title":"Recurrent Transition Networks for Character Locomotion","created":"2018-10-04","cited_by_count":52},{"id":"1905.01680","title":"Learning Character-Agnostic Motion for Motion Retargeting in 2D","created":"2019-05-05","cited_by_count":45},{"id":"2008.12606","title":"Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation","created":"2020-08-27","cited_by_count":43},{"id":"2007.11762","title":"All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling","created":"2020-07-23","cited_by_count":42},{"id":"1603.06041","title":"Learning Image Matching by Simply Watching Video","created":"2016-03-19","cited_by_count":41},{"id":"1705.04098","title":"A Generative Model of People in Clothing","created":"2017-05-11","cited_by_count":37},{"id":"2003.14401","title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting","created":"2020-03-31","cited_by_count":36},{"id":"1904.03379","title":"Unsupervised Person Image Generation with Semantic Parsing Transformation","created":"2019-04-06","cited_by_count":32},{"id":"1704.04886","title":"Multi-View Image Generation from a Single-View","created":"2017-04-17","cited_by_count":27},{"id":"1910.11667","title":"Learning Multi-Human Optical Flow","created":"2019-10-24","cited_by_count":26},{"id":"1909.02641","title":"Deep Iterative Frame Interpolation for Full-frame Video Stabilization","created":"2019-09-05","cited_by_count":23},{"id":"1904.08379","title":"Vid2Game: Controllable Characters Extracted from Real-World Videos","created":"2019-04-17","cited_by_count":18},{"id":"2003.13510","title":"Human Motion Transfer with 3D Constraints and Detail Enhancement","created":"2020-03-30","cited_by_count":14},{"id":"2007.15068","title":"Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild","created":"2020-07-29","cited_by_count":6}],"next_cursor":null}