{"list":"other","total":74,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"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":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2210.03142","title":"On Distillation of Guided Diffusion Models","created":"2022-10-06","cited_by_count":725},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2009.00713","title":"WaveGrad: Estimating Gradients for Waveform Generation","created":"2020-09-02","cited_by_count":622},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"1511.01844","title":"A note on the evaluation of generative models","created":"2015-11-05","cited_by_count":292},{"id":"1705.07120","title":"VAE with a VampPrior","created":"2017-05-19","cited_by_count":248},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"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":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"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":"2207.06635","title":"EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations","created":"2022-07-14","cited_by_count":172},{"id":"1601.06733","title":"Long Short-Term Memory-Networks for Machine Reading","created":"2016-01-25","cited_by_count":161},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98},{"id":"2008.08171","title":"Learning to Generate Diverse Dance Motions with Transformer","created":"2020-08-18","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":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84},{"id":"2201.04439","title":"Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases","created":"2022-01-12","cited_by_count":72},{"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":"2111.12159","title":"Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure","created":"2021-11-23","cited_by_count":53},{"id":"1903.03369","title":"Analyzing Input and Output Representations for Speech-Driven Gesture Generation","created":"2019-03-08","cited_by_count":52},{"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":"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":"2009.07637","title":"ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit","created":"2020-09-16","cited_by_count":31},{"id":"2106.01950","title":"The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models","created":"2021-06-03","cited_by_count":23},{"id":"2106.13871","title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","created":"2021-06-25","cited_by_count":22},{"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":"2208.09406","title":"Dance Style Transfer with Cross-modal Transformer","created":"2022-08-19","cited_by_count":20},{"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":"1605.06921","title":"Generative Choreography using Deep Learning","created":"2016-05-23","cited_by_count":12},{"id":"2101.05684","title":"Generating coherent spontaneous speech and gesture from text","created":"2021-01-14","cited_by_count":12},{"id":"1708.01640","title":"Speech-driven Animation with Meaningful Behaviors","created":"2017-08-04","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":"2209.14828","title":"Denoising Diffusion Probabilistic Models for Styled Walking Synthesis","created":"2022-09-29","cited_by_count":6},{"id":"2102.07284","title":"Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows","created":"2021-02-15","cited_by_count":4},{"id":"2107.00730","title":"Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability","created":"2021-07-01","cited_by_count":4},{"id":"1802.08370","title":"Do WaveNets Dream of Acoustic Waves?","created":"2018-02-23","cited_by_count":1},{"id":"2207.12126","title":"PirouNet: Creating Dance through Artist-Centric Deep Learning","created":"2022-07-21","cited_by_count":1}],"next_cursor":null}