{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2007.14808","title":"Face2Face: Real-time Face Capture and Reenactment of RGB Videos","created":"2020-07-29","cited_by_count":632},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"1803.09017","title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","created":"2018-03-23","cited_by_count":259},{"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":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184},{"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":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"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":"2101.11101","title":"Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents","created":"2021-01-26","cited_by_count":106},{"id":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98},{"id":"2001.09326","title":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","created":"2020-01-25","cited_by_count":84},{"id":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","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":"2108.00262","title":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","created":"2021-07-31","cited_by_count":58},{"id":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58},{"id":"2203.11389","title":"The VoiceMOS Challenge 2022","created":"2022-03-21","cited_by_count":57},{"id":"1903.03369","title":"Analyzing Input and Output Representations for Speech-Driven Gesture Generation","created":"2019-03-08","cited_by_count":52},{"id":"1906.04158","title":"Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction","created":"2019-06-10","cited_by_count":48},{"id":"1905.06598","title":"MoGlow: Probabilistic and controllable motion synthesis using normalising flows","created":"2019-05-16","cited_by_count":47},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44},{"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":"2102.11617","title":"A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020","created":"2021-02-23","cited_by_count":38},{"id":"2210.01448","title":"Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings","created":"2022-10-04","cited_by_count":38},{"id":"1908.09008","title":"Conditional Flow Variational Autoencoders for Structured Sequence Prediction","created":"2019-08-24","cited_by_count":37},{"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":"2007.12287","title":"Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics","created":"2020-07-23","cited_by_count":34},{"id":"1910.02181","title":"To React or not to React: End-to-End Visual Pose Forecasting for Personalized Avatar during Dyadic Conversations","created":"2019-10-05","cited_by_count":26},{"id":"2101.03769","title":"A Review of Evaluation Practices of Gesture Generation in Embodied Conversational Agents","created":"2021-01-11","cited_by_count":24},{"id":"2007.09170","title":"Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation","created":"2020-07-16","cited_by_count":20},{"id":"2207.11524","title":"Audio-driven Neural Gesture Reenactment with Video Motion Graphs","created":"2022-07-23","cited_by_count":18},{"id":"2108.11436","title":"Integrated Speech and Gesture Synthesis","created":"2021-08-25","cited_by_count":16},{"id":"2108.05762","title":"Multimodal analysis of the predictability of hand-gesture properties","created":"2021-08-12","cited_by_count":14},{"id":"2101.11898","title":"HEMVIP: Human Evaluation of Multiple Videos in Parallel","created":"2021-01-28","cited_by_count":13},{"id":"2209.01714","title":"On the Horizon: Interactive and Compositional Deepfakes","created":"2022-09-05","cited_by_count":13},{"id":"2101.05684","title":"Generating coherent spontaneous speech and gesture from text","created":"2021-01-14","cited_by_count":12},{"id":"2108.05709","title":"To Rate or Not To Rate: Investigating Evaluation Methods for Generated Co-Speech Gestures","created":"2021-08-12","cited_by_count":12},{"id":"1708.01640","title":"Speech-driven Animation with Meaningful Behaviors","created":"2017-08-04","cited_by_count":11},{"id":"2107.00712","title":"Passing a Non-verbal Turing Test: Evaluating Gesture Animations Generated from Speech","created":"2021-07-01","cited_by_count":11},{"id":"2108.04636","title":"SGToolkit: An Interactive Gesture Authoring Toolkit for Embodied Conversational Agents","created":"2021-08-10","cited_by_count":11},{"id":"2208.01917","title":"Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding","created":"2022-08-03","cited_by_count":7},{"id":"2102.12302","title":"A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents","created":"2021-02-24","cited_by_count":4},{"id":"2205.15573","title":"Text/Speech-Driven Full-Body Animation","created":"2022-05-31","cited_by_count":3},{"id":"2210.06974","title":"Evaluating Data-Driven Co-Speech Gestures of Embodied Conversational Agents through Real-Time Interaction","created":"2022-10-13","cited_by_count":3}],"next_cursor":null}