{"list":"other","total":61,"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"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":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"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":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"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":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"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":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"id":"1804.07739","title":"Synthesizing Images of Humans in Unseen Poses","created":"2018-04-20","cited_by_count":97},{"id":"2212.03741","title":"FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation","created":"2022-12-07","cited_by_count":88},{"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":"1909.00968","title":"Image Inpainting with Learnable Bidirectional Attention Maps","created":"2019-09-03","cited_by_count":64},{"id":"1911.09592","title":"mm-Pose: Real-Time Human Skeletal Posture Estimation using mmWave Radars and CNNs","created":"2019-11-21","cited_by_count":59},{"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":"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":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37},{"id":"2403.13304","title":"DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception","created":"2024-03-20","cited_by_count":32},{"id":"2308.12646","title":"The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings","created":"2023-08-24","cited_by_count":28},{"id":"2304.11603","title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","created":"2023-04-23","cited_by_count":22},{"id":"2207.11524","title":"Audio-driven Neural Gesture Reenactment with Video Motion Graphs","created":"2022-07-23","cited_by_count":18},{"id":"2107.04619","title":"Diverse Video Generation using a Gaussian Process Trigger","created":"2021-07-09","cited_by_count":17},{"id":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8},{"id":"2403.05834","title":"Enhancing Expressiveness in Dance Generation via Integrating Frequency and Music Style Information","created":"2024-03-09","cited_by_count":2}],"next_cursor":null}