{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"1908.05932","title":"FSGAN: Subject Agnostic Face Swapping and Reenactment","created":"2019-08-16","cited_by_count":320},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2108.08839","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","created":"2021-08-19","cited_by_count":286},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"1805.11714","title":"Deep Video Portraits","created":"2018-05-29","cited_by_count":267},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"1908.06903","title":"Multi-Garment Net: Learning to Dress 3D People from Images","created":"2019-08-19","cited_by_count":245},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"1807.10550","title":"X2Face: A network for controlling face generation by using images, audio, and pose codes","created":"2018-07-27","cited_by_count":189},{"id":"1801.00055","title":"Deformable GANs for Pose-based Human Image Generation","created":"2017-12-29","cited_by_count":166},{"id":"1807.09251","title":"GANimation: Anatomically-aware Facial Animation from a Single Image","created":"2018-07-24","cited_by_count":161},{"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":"1904.03349","title":"Progressive Pose Attention Transfer for Person Image Generation","created":"2019-04-06","cited_by_count":138},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"id":"2106.04095","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","created":"2021-06-08","cited_by_count":120},{"id":"1910.09139","title":"DwNet: Dense warp-based network for pose-guided human video generation","created":"2019-10-21","cited_by_count":115},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2004.12000","title":"Neural Head Reenactment with Latent Pose Descriptors","created":"2020-04-24","cited_by_count":106},{"id":"1903.11326","title":"Dense Intrinsic Appearance Flow for Human Pose Transfer","created":"2019-03-27","cited_by_count":104},{"id":"2003.00696","title":"Deep Image Spatial Transformation for Person Image Generation","created":"2020-03-02","cited_by_count":100},{"id":"1712.02621","title":"Disentangled Person Image Generation","created":"2017-12-07","cited_by_count":98},{"id":"1804.07739","title":"Synthesizing Images of Humans in Unseen Poses","created":"2018-04-20","cited_by_count":97},{"id":"1911.08139","title":"MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets","created":"2019-11-19","cited_by_count":90},{"id":"1809.01995","title":"Dense Pose Transfer","created":"2018-09-06","cited_by_count":83},{"id":"1903.06946","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","created":"2019-03-16","cited_by_count":67},{"id":"2103.04023","title":"PISE: Person Image Synthesis and Editing with Decoupled GAN","created":"2021-03-06","cited_by_count":62},{"id":"2101.04104","title":"Neural Re-Rendering of Humans from a Single Image","created":"2021-01-11","cited_by_count":59},{"id":"2012.03796","title":"Pose-Guided Human Animation from a Single Image in the Wild","created":"2020-12-07","cited_by_count":53},{"id":"1902.08900","title":"3D Guided Fine-Grained Face Manipulation","created":"2019-02-24","cited_by_count":45},{"id":"2109.07001","title":"ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors","created":"2021-09-14","cited_by_count":35},{"id":"2204.05018","title":"Structure-Aware Motion Transfer with Deformable Anchor Model","created":"2022-04-11","cited_by_count":34},{"id":"2011.04439","title":"FACEGAN: Facial Attribute Controllable rEenactment GAN","created":"2020-11-09","cited_by_count":32},{"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":"2103.14338","title":"Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling","created":"2021-03-26","cited_by_count":21},{"id":"2004.03142","title":"Human Motion Transfer from Poses in the Wild","created":"2020-04-07","cited_by_count":17},{"id":"2008.06843","title":"Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision","created":"2020-08-16","cited_by_count":12},{"id":"2102.03984","title":"One-shot Face Reenactment Using Appearance Adaptive Normalization","created":"2021-02-08","cited_by_count":12},{"id":"2106.05897","title":"Unsupervised Co-part Segmentation through Assembly","created":"2021-06-10","cited_by_count":12},{"id":"2106.07771","title":"Flow Guided Transformable Bottleneck Networks for Motion Retargeting","created":"2021-06-14","cited_by_count":12},{"id":"2012.08976","title":"C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer","created":"2020-12-16","cited_by_count":11},{"id":"1901.02284","title":"Unpaired Pose Guided Human Image Generation","created":"2019-01-08","cited_by_count":8},{"id":"2109.10057","title":"LOTR: Face Landmark Localization Using Localization Transformer","created":"2021-09-21","cited_by_count":6},{"id":"2112.13647","title":"Move As You Like: Image Animation in E-Commerce Scenario","created":"2021-12-19","cited_by_count":4}],"next_cursor":null}