{"list":"other","total":73,"rows":[{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"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":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"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":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"2009.02119","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","created":"2020-09-04","cited_by_count":202},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198},{"id":"2403.17694","title":"AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation","created":"2024-03-26","cited_by_count":194},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","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":"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":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"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":"2305.18295","title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","created":"2023-05-29","cited_by_count":142},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137},{"id":"2301.03786","title":"DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation","created":"2023-01-10","cited_by_count":136},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"1811.09245","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","created":"2018-11-22","cited_by_count":120},{"id":"1910.09139","title":"DwNet: Dense warp-based network for pose-guided human video generation","created":"2019-10-21","cited_by_count":115},{"id":"1810.12541","title":"Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots","created":"2018-10-30","cited_by_count":110},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109},{"id":"2002.09219","title":"Stochastic Latent Residual Video Prediction","created":"2020-02-21","cited_by_count":108},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"id":"2211.14758","title":"VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild","created":"2022-11-27","cited_by_count":106},{"id":"1904.12165","title":"Improved Conditional VRNNs for Video Prediction","created":"2019-04-27","cited_by_count":104},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98},{"id":"2305.04919","title":"DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models","created":"2023-05-08","cited_by_count":85},{"id":"2001.09326","title":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","created":"2020-01-25","cited_by_count":84},{"id":"2007.12553","title":"Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach","created":"2020-07-24","cited_by_count":65},{"id":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55},{"id":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55},{"id":"2312.02963","title":"MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures","created":"2023-12-05","cited_by_count":54},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49},{"id":"2307.10797","title":"HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces","created":"2023-07-20","cited_by_count":48},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42},{"id":"2208.10441","title":"The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation","created":"2022-08-22","cited_by_count":40},{"id":"2305.11094","title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","created":"2023-05-18","cited_by_count":40},{"id":"2405.09814","title":"Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis","created":"2024-05-16","cited_by_count":40},{"id":"2404.01862","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","created":"2024-04-02","cited_by_count":35},{"id":"2212.04970","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers","created":"2022-12-09","cited_by_count":33},{"id":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","cited_by_count":29},{"id":"2310.06851","title":"BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer","created":"2023-09-07","cited_by_count":21},{"id":"2205.06421","title":"Talking Face Generation with Multilingual TTS","created":"2022-05-13","cited_by_count":18},{"id":"2311.17532","title":"Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation","created":"2023-11-29","cited_by_count":17},{"id":"2203.12780","title":"Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera","created":"2022-03-24","cited_by_count":12},{"id":"2409.16404","title":"FastTalker: Jointly Generating Speech and Conversational Gestures from Text","created":"2024-09-24","cited_by_count":4}],"next_cursor":null}