{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"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":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"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":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"1805.11714","title":"Deep Video Portraits","created":"2018-05-29","cited_by_count":267},{"id":"2112.05329","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","created":"2021-12-10","cited_by_count":209},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"id":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"1711.09561","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","created":"2017-11-27","cited_by_count":176},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126},{"id":"1805.06485","title":"QuaterNet: A Quaternion-based Recurrent Model for Human Motion","created":"2018-05-16","cited_by_count":109},{"id":"1906.01524","title":"Text-based Editing of Talking-head Video","created":"2019-06-04","cited_by_count":103},{"id":"2203.14057","title":"FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset","created":"2022-03-26","cited_by_count":98},{"id":"1910.09070","title":"Structured Prediction Helps 3D Human Motion Modelling","created":"2019-10-20","cited_by_count":96},{"id":"1705.00053","title":"The Pose Knows: Video Forecasting by Generating Pose Futures","created":"2017-04-28","cited_by_count":88},{"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":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67},{"id":"2108.00262","title":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","created":"2021-07-31","cited_by_count":58},{"id":"2111.12159","title":"Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure","created":"2021-11-23","cited_by_count":53},{"id":"1804.10652","title":"Human Motion Modeling using DVGANs","created":"2018-04-27","cited_by_count":45},{"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":"2007.13886","title":"Perpetual Motion: Generating Unbounded Human Motion","created":"2020-07-27","cited_by_count":36},{"id":"2012.14259","title":"Context-Aware Personality Inference in Dyadic Scenarios: Introducing the UDIVA Dataset","created":"2020-12-28","cited_by_count":31},{"id":"1401.4994","title":"A Review of Verbal and Non-Verbal Human-Robot Interactive Communication","created":"2014-01-20","cited_by_count":16},{"id":"2302.06514","title":"Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?","created":"2023-02-13","cited_by_count":16},{"id":"1801.09092","title":"Interactive Generative Adversarial Networks for Facial Expression Generation in Dyadic Interactions","created":"2018-01-27","cited_by_count":15},{"id":"2208.07862","title":"StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3","created":"2022-08-16","cited_by_count":11},{"id":"2305.15270","title":"Reversible Graph Neural Network-based Reaction Distribution Learning for Multiple Appropriate Facial Reactions Generation","created":"2023-05-24","cited_by_count":11}],"next_cursor":null}