{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"1903.08527","title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","created":"2019-03-20","cited_by_count":482},{"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":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382},{"id":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"2312.02069","title":"GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians","created":"2023-12-04","cited_by_count":260},{"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":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"2401.03890","title":"A Survey on 3D Gaussian Splatting","created":"2024-01-08","cited_by_count":224},{"id":"2112.05329","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","created":"2021-12-10","cited_by_count":209},{"id":"2104.08223","title":"MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement","created":"2021-04-16","cited_by_count":190},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","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":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"1803.10404","title":"Lip Movements Generation at a Glance","created":"2018-03-28","cited_by_count":155},{"id":"1906.06337","title":"Realistic Speech-Driven Facial Animation with GANs","created":"2019-06-14","cited_by_count":142},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114},{"id":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"1705.02966","title":"You said that?","created":"2017-05-08","cited_by_count":99},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98},{"id":"2003.00418","title":"Towards Automatic Face-to-Face Translation","created":"2020-03-01","cited_by_count":96},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95},{"id":"2112.02749","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","created":"2021-12-06","cited_by_count":87},{"id":"2310.00434","title":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","created":"2023-09-30","cited_by_count":81},{"id":"2309.11306","title":"FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion","created":"2023-09-20","cited_by_count":78},{"id":"2303.03988","title":"DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video","created":"2023-03-07","cited_by_count":74},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2109.02303","title":"Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation","created":"2021-09-06","cited_by_count":62},{"id":"2203.08534","title":"Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video","created":"2022-03-16","cited_by_count":60},{"id":"2207.11094","title":"Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos","created":"2022-07-22","cited_by_count":50},{"id":"2210.15929","title":"Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training","created":"2022-10-28","cited_by_count":45},{"id":"2401.15687","title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","created":"2024-01-28","cited_by_count":39},{"id":"2401.01207","title":"Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation","created":"2024-01-02","cited_by_count":26},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21},{"id":"2008.10004","title":"Geometry-guided Dense Perspective Network for Speech-Driven Facial Animation","created":"2020-08-23","cited_by_count":19},{"id":"2403.11589","title":"UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling","created":"2024-03-18","cited_by_count":17},{"id":"2305.12734","title":"EMEF: Ensemble Multi-Exposure Image Fusion","created":"2023-05-22","cited_by_count":10}],"next_cursor":null}