{"list":"other","total":60,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"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":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"1909.01815","title":"3D Morphable Face Models -- Past, Present and Future","created":"2019-09-03","cited_by_count":270},{"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":"1912.05566","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","created":"2019-12-11","cited_by_count":250},{"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":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"1804.03786","title":"Nonlinear 3D Face Morphable Model","created":"2018-04-11","cited_by_count":157},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"2011.14143","title":"i3DMM: Deep Implicit 3D Morphable Model of Human Heads","created":"2020-11-28","cited_by_count":109},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98},{"id":"2004.03458","title":"Learning Formation of Physically-Based Face Attributes","created":"2020-04-02","cited_by_count":94},{"id":"1904.04933","title":"Towards High-fidelity Nonlinear 3D Face Morphable Model","created":"2019-04-09","cited_by_count":91},{"id":"1905.02876","title":"Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation","created":"2019-05-08","cited_by_count":90},{"id":"2207.11243","title":"Multiface: A Dataset for Neural Face Rendering","created":"2022-07-22","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":"2304.03117","title":"DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance","created":"2023-04-01","cited_by_count":80},{"id":"2309.11306","title":"FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion","created":"2023-09-20","cited_by_count":78},{"id":"2305.16225","title":"ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models","created":"2023-05-25","cited_by_count":75},{"id":"2301.00023","title":"Imitator: Personalized Speech-driven 3D Facial Animation","created":"2022-12-30","cited_by_count":74},{"id":"2212.02761","title":"Learning Neural Parametric Head Models","created":"2022-12-06","cited_by_count":73},{"id":"2306.10799","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","created":"2023-06-19","cited_by_count":68},{"id":"2203.14510","title":"ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations","created":"2022-03-28","cited_by_count":64},{"id":"1805.09488","title":"VisemeNet: Audio-Driven Animator-Centric Speech Animation","created":"2018-05-24","cited_by_count":63},{"id":"2203.13694","title":"Implicit Neural Representations for Variable Length Human Motion Generation","created":"2022-03-25","cited_by_count":61},{"id":"2312.12491","title":"StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation","created":"2023-12-19","cited_by_count":58},{"id":"2312.08459","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","created":"2023-12-13","cited_by_count":55},{"id":"1808.09560","title":"On Learning 3D Face Morphable Model from In-the-wild Images","created":"2018-08-28","cited_by_count":54},{"id":"2312.08985","title":"OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers","created":"2023-12-14","cited_by_count":47},{"id":"1701.05360","title":"3D Face Morphable Models \"In-the-Wild\"","created":"2017-01-19","cited_by_count":44},{"id":"2006.09888","title":"Let's Face It: Probabilistic Multi-modal Interlocutor-aware Generation of Facial Gestures in Dyadic Settings","created":"2020-06-11","cited_by_count":36},{"id":"2303.05416","title":"FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning","created":"2023-03-09","cited_by_count":29},{"id":"2305.08296","title":"Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild","created":"2023-05-15","cited_by_count":25},{"id":"2010.00560","title":"Dynamic Facial Asset and Rig Generation from a Single Scan","created":"2020-10-01","cited_by_count":21},{"id":"2202.05592","title":"Video-driven Neural Physically-based Facial Asset for Production","created":"2022-02-11","cited_by_count":17},{"id":"2311.16565","title":"DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser","created":"2023-11-28","cited_by_count":16},{"id":"2112.02214","title":"Joint Audio-Text Model for Expressive Speech-Driven 3D Facial Animation","created":"2021-12-04","cited_by_count":15},{"id":"2312.00870","title":"3DiFACE: Diffusion-based Speech-driven 3D Facial Animation and Editing","created":"2023-12-01","cited_by_count":15},{"id":"2105.02173","title":"Learning Feature Aggregation for Deep 3D Morphable Models","created":"2021-05-05","cited_by_count":13},{"id":"2104.09946","title":"A cappella: Audio-visual Singing Voice Separation","created":"2021-04-20","cited_by_count":12},{"id":"2211.11402","title":"An Implicit Parametric Morphable Dental Model","created":"2022-11-21","cited_by_count":12},{"id":"2310.11295","title":"CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation","created":"2023-10-17","cited_by_count":8}],"next_cursor":null}