{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"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":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"1705.02445","title":"On human motion prediction using recurrent neural networks","created":"2017-05-06","cited_by_count":338},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229},{"id":"2212.04495","title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","created":"2022-12-08","cited_by_count":218},{"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":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"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":"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":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"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":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"1904.03419","title":"Context-aware Human Motion Prediction","created":"2019-04-06","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":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66},{"id":"2304.10417","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","created":"2023-04-20","cited_by_count":64},{"id":"2108.00262","title":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","created":"2021-07-31","cited_by_count":58},{"id":"2007.11154","title":"Rethinking CNN Models for Audio Classification","created":"2020-07-22","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":"2111.14820","title":"Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective","created":"2021-11-29","cited_by_count":40},{"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":"2305.18891","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","created":"2023-05-30","cited_by_count":40},{"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":"2004.07301","title":"ESResNet: Environmental Sound Classification Based on Visual Domain Models","created":"2020-04-15","cited_by_count":31},{"id":"2203.04132","title":"Motron: Multimodal Probabilistic Human Motion Forecasting","created":"2022-03-08","cited_by_count":30},{"id":"2311.00994","title":"LaughTalk: Expressive 3D Talking Head Generation with Laughter","created":"2023-11-02","cited_by_count":27},{"id":"2202.04307","title":"Conditional Motion In-betweening","created":"2022-02-09","cited_by_count":25},{"id":"2005.08891","title":"Generative Tweening: Long-term Inbetweening of 3D Human Motions","created":"2020-05-18","cited_by_count":23},{"id":"2205.02625","title":"GANimator: Neural Motion Synthesis from a Single Sequence","created":"2022-05-05","cited_by_count":23},{"id":"2310.06851","title":"BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer","created":"2023-09-07","cited_by_count":21},{"id":"2303.01765","title":"Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement","created":"2023-03-03","cited_by_count":18},{"id":"2306.09417","title":"Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis","created":"2023-06-15","cited_by_count":13},{"id":"2308.14448","title":"ExpCLIP: Bridging Text and Facial Expressions via Semantic Alignment","created":"2023-08-28","cited_by_count":13},{"id":"2303.12822","title":"Co-Speech Gesture Synthesis using Discrete Gesture Token Learning","created":"2023-03-04","cited_by_count":9},{"id":"2207.10120","title":"BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis","created":"2022-07-20","cited_by_count":5},{"id":"2308.10680","title":"Co-Speech Gesture Detection through Multi-Phase Sequence Labeling","created":"2023-08-21","cited_by_count":5},{"id":"2305.15740","title":"MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generation","created":"2023-05-25","cited_by_count":3}],"next_cursor":null}