{"list":"other","total":62,"rows":[{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"2007.14808","title":"Face2Face: Real-time Face Capture and Reenactment of RGB Videos","created":"2020-07-29","cited_by_count":632},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"2012.04012","title":"Learning an Animatable Detailed 3D Face Model from In-The-Wild Images","created":"2020-12-07","cited_by_count":477},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"1909.01815","title":"3D Morphable Face Models -- Past, Present and Future","created":"2019-09-03","cited_by_count":270},{"id":"1807.10267","title":"Generating 3D faces using Convolutional Mesh Autoencoders","created":"2018-07-26","cited_by_count":268},{"id":"1805.11714","title":"Deep Video Portraits","created":"2018-05-29","cited_by_count":267},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"1801.01615","title":"Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies","created":"2018-01-05","cited_by_count":239},{"id":"2009.09960","title":"Towards Fast, Accurate and Stable 3D Dense Face Alignment","created":"2020-09-21","cited_by_count":219},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213},{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200},{"id":"1803.07835","title":"Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network","created":"2018-03-21","cited_by_count":195},{"id":"2104.08223","title":"MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement","created":"2021-04-16","cited_by_count":190},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"1905.06817","title":"Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision","created":"2019-05-16","cited_by_count":176},{"id":"2204.06607","title":"Towards Metrical Reconstruction of Human Faces","created":"2022-04-13","cited_by_count":166},{"id":"2008.09062","title":"Monocular Expressive Body Regression through Body-Driven Attention","created":"2020-08-20","cited_by_count":155},{"id":"1902.05978","title":"GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction","created":"2019-02-15","cited_by_count":150},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"2104.04638","title":"Pixel Codec Avatars","created":"2021-04-09","cited_by_count":127},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"1803.09179","title":"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces","created":"2018-03-24","cited_by_count":119},{"id":"2206.08343","title":"Realistic One-shot Mesh-based Head Avatars","created":"2022-06-16","cited_by_count":119},{"id":"1612.04904","title":"Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network","created":"2016-12-15","cited_by_count":109},{"id":"2012.02512","title":"ID-Reveal: Identity-aware DeepFake Video Detection","created":"2020-12-04","cited_by_count":97},{"id":"2210.02579","title":"DigiFace-1M: 1 Million Digital Face Images for Face Recognition","created":"2022-10-05","cited_by_count":92},{"id":"2104.03176","title":"On Self-Contact and Human Pose","created":"2021-04-07","cited_by_count":89},{"id":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80},{"id":"2007.12494","title":"Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency","created":"2020-07-24","cited_by_count":78},{"id":"2204.02776","title":"3D face reconstruction with dense landmarks","created":"2022-04-06","cited_by_count":70},{"id":"2209.10510","title":"Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation","created":"2022-09-21","cited_by_count":67},{"id":"2101.10803","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","created":"2021-01-26","cited_by_count":50},{"id":"2104.00340","title":"Reconstructing 3D Human Pose by Watching Humans in the Mirror","created":"2021-04-01","cited_by_count":47},{"id":"2206.04382","title":"CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes","created":"2022-06-09","cited_by_count":41},{"id":"2205.03962","title":"Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation","created":"2022-05-08","cited_by_count":32},{"id":"2008.10247","title":"Monocular Reconstruction of Neural Face Reflectance Fields","created":"2020-08-24","cited_by_count":20},{"id":"2110.00119","title":"HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge","created":"2021-09-30","cited_by_count":17},{"id":"2107.03109","title":"Egocentric Videoconferencing","created":"2021-07-07","cited_by_count":10},{"id":"2208.13717","title":"StableFace: Analyzing and Improving Motion Stability for Talking Face Generation","created":"2022-08-29","cited_by_count":9},{"id":"1503.02330","title":"Fitting 3D Morphable Models using Local Features","created":"2015-03-08","cited_by_count":6},{"id":"2110.07578","title":"Learning Temporal 3D Human Pose Estimation with Pseudo-Labels","created":"2021-10-14","cited_by_count":4}],"next_cursor":null}