{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2211.01095","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","created":"2022-11-02","cited_by_count":938},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"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":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"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":"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":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","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":"1703.10580","title":"MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction","created":"2017-03-30","cited_by_count":163},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98},{"id":"1712.02859","title":"Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz","created":"2017-12-07","cited_by_count":91},{"id":"2404.04104","title":"SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis","created":"2024-04-05","cited_by_count":84},{"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":"1812.07603","title":"FML: Face Model Learning from Videos","created":"2018-12-18","cited_by_count":78},{"id":"2309.11306","title":"FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusion","created":"2023-09-20","cited_by_count":78},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"2301.00023","title":"Imitator: Personalized Speech-driven 3D Facial Animation","created":"2022-12-30","cited_by_count":74},{"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":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65},{"id":"1805.09488","title":"VisemeNet: Audio-Driven Animator-Centric Speech Animation","created":"2018-05-24","cited_by_count":63},{"id":"2312.08459","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","created":"2023-12-13","cited_by_count":55},{"id":"2207.11094","title":"Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos","created":"2022-07-22","cited_by_count":50},{"id":"1904.04631","title":"CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion","created":"2019-04-09","cited_by_count":46},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41},{"id":"2312.04466","title":"Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion","created":"2023-12-07","cited_by_count":39},{"id":"2401.15687","title":"Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidance","created":"2024-01-28","cited_by_count":39},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35},{"id":"1711.11293","title":"Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks","created":"2017-11-30","cited_by_count":31},{"id":"2408.00762","title":"UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model","created":"2024-08-01","cited_by_count":30},{"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":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","cited_by_count":28},{"id":"2406.14272","title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","created":"2024-06-20","cited_by_count":28},{"id":"1906.06301","title":"Video-Driven Speech Reconstruction using Generative Adversarial Networks","created":"2019-06-14","cited_by_count":25},{"id":"2010.11672","title":"CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion","created":"2020-10-22","cited_by_count":25},{"id":"2403.10942","title":"ScanTalk: 3D Talking Heads from Unregistered Scans","created":"2024-03-16","cited_by_count":24},{"id":"2306.03258","title":"LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading","created":"2023-06-05","cited_by_count":22},{"id":"2308.07787","title":"DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding","created":"2023-08-15","cited_by_count":22},{"id":"2302.08841","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","created":"2023-02-17","cited_by_count":21},{"id":"2004.02541","title":"Vocoder-Based Speech Synthesis from Silent Videos","created":"2020-04-06","cited_by_count":20},{"id":"2011.07340","title":"Speech Prediction in Silent Videos using Variational Autoencoders","created":"2020-11-14","cited_by_count":18},{"id":"2312.10877","title":"Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation","created":"2023-12-18","cited_by_count":16},{"id":"2311.18168","title":"Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications","created":"2023-11-30","cited_by_count":15},{"id":"2409.01113","title":"KMTalk: Speech-Driven 3D Facial Animation with Key Motion Embedding","created":"2024-09-02","cited_by_count":14},{"id":"2403.12886","title":"EmoVOCA: Speech-Driven Emotional 3D Talking Heads","created":"2024-03-19","cited_by_count":13},{"id":"2503.20308","title":"Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics","created":"2025-03-26","cited_by_count":10},{"id":"2105.09652","title":"Speaker disentanglement in video-to-speech conversion","created":"2021-05-20","cited_by_count":6},{"id":"2407.01034","title":"Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert","created":"2024-07-01","cited_by_count":6},{"id":"1710.00920","title":"End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech","created":"2017-10-02","cited_by_count":4},{"id":"2107.12003","title":"Facetron: A Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations","created":"2021-07-26","cited_by_count":4}],"next_cursor":null}