{"list":"other","total":65,"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"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":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"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":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"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":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"1912.05566","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","created":"2019-12-11","cited_by_count":250},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"1803.10404","title":"Lip Movements Generation at a Glance","created":"2018-03-28","cited_by_count":155},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151},{"id":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149},{"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":"2301.13430","title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis","created":"2023-01-31","cited_by_count":131},{"id":"2201.07786","title":"Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation","created":"2022-01-19","cited_by_count":119},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"1906.01524","title":"Text-based Editing of Talking-head Video","created":"2019-06-04","cited_by_count":103},{"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":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93},{"id":"2002.10137","title":"Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose","created":"2020-02-24","cited_by_count":92},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92},{"id":"2312.09109","title":"VideoLCM: Video Latent Consistency Model","created":"2023-12-14","cited_by_count":92},{"id":"2108.07938","title":"FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning","created":"2021-08-18","cited_by_count":90},{"id":"2305.05445","title":"StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator","created":"2023-05-09","cited_by_count":89},{"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":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86},{"id":"1804.04786","title":"Talking Face Generation by Conditional Recurrent Adversarial Network","created":"2018-04-13","cited_by_count":84},{"id":"2001.05201","title":"Everybody's Talkin': Let Me Talk as You Want","created":"2020-01-15","cited_by_count":83},{"id":"2211.12368","title":"Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition","created":"2022-11-22","cited_by_count":81},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81},{"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":"2106.04185","title":"LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization","created":"2021-06-08","cited_by_count":67},{"id":"2312.04483","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","created":"2023-12-07","cited_by_count":50},{"id":"2211.09809","title":"SPACE: Speech-driven Portrait Animation with Controllable Expression","created":"2022-11-17","cited_by_count":49},{"id":"2104.07995","title":"Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation","created":"2021-04-16","cited_by_count":47},{"id":"2205.01155","title":"Emotion-Controllable Generalized Talking Face Generation","created":"2022-05-02","cited_by_count":43},{"id":"2311.15230","title":"GAIA: Zero-shot Talking Avatar Generation","created":"2023-11-26","cited_by_count":43},{"id":"2305.02572","title":"High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning","created":"2023-05-04","cited_by_count":37},{"id":"2008.01077","title":"Self-attention encoding and pooling for speaker recognition","created":"2020-08-03","cited_by_count":33},{"id":"2212.04970","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers","created":"2022-12-09","cited_by_count":33},{"id":"2304.00334","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","created":"2023-04-01","cited_by_count":32},{"id":"2212.05005","title":"Memories are One-to-Many Mapping Alleviators in Talking Face Generation","created":"2022-12-09","cited_by_count":22},{"id":"1806.00154","title":"Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks","created":"2018-06-01","cited_by_count":21},{"id":"2211.06757","title":"DriftRec: Adapting diffusion models to blind JPEG restoration","created":"2022-11-12","cited_by_count":15},{"id":"2108.05650","title":"UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing","created":"2021-08-12","cited_by_count":11}],"next_cursor":null}