{"list":"other","total":79,"rows":[{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"1904.03278","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":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"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":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"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":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"2304.08577","title":"Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model","created":"2023-04-17","cited_by_count":107},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85},{"id":"1904.09882","title":"You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions","created":"2019-04-22","cited_by_count":82},{"id":"2203.07706","title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","created":"2022-03-15","cited_by_count":77},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75},{"id":"1705.06400","title":"Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks","created":"2017-05-18","cited_by_count":61},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53},{"id":"2410.10010","title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling","created":"2024-10-13","cited_by_count":47},{"id":"2501.05098","title":"Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset","created":"2025-01-09","cited_by_count":33},{"id":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","cited_by_count":31},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2504.02478","title":"MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities","created":"2025-04-03","cited_by_count":30},{"id":"2404.09988","title":"in2IN: Leveraging individual Information to Generate Human INteractions","created":"2024-04-15","cited_by_count":29},{"id":"2502.20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation","created":"2025-02-27","cited_by_count":28},{"id":"2312.08983","title":"Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting","created":"2023-12-14","cited_by_count":27},{"id":"2408.17135","title":"TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation","created":"2024-08-30","cited_by_count":27},{"id":"2412.16982","title":"InterDance:Reactive 3D Dance Generation with Realistic Duet Interactions","created":"2024-12-22","cited_by_count":22},{"id":"2508.02106","title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis","created":"2025-08-04","cited_by_count":20},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19},{"id":"2404.01081","title":"PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation","created":"2024-04-01","cited_by_count":18},{"id":"2404.11987","title":"MultiPhys: Multi-Person Physics-aware 3D Motion Estimation","created":"2024-04-18","cited_by_count":18},{"id":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14},{"id":"2110.14994","title":"Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition","created":"2021-10-28","cited_by_count":13},{"id":"2401.16173","title":"Reconstructing Close Human Interactions from Multiple Views","created":"2024-01-29","cited_by_count":7},{"id":"2408.02110","title":"AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos","created":"2024-08-04","cited_by_count":7},{"id":"2503.16973","title":"ARFlow: Human Action-Reaction Flow Matching with Physical Guidance","created":"2025-03-21","cited_by_count":7},{"id":"2510.14976","title":"Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation","created":"2025-10-16","cited_by_count":7},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7},{"id":"2512.19692","title":"Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models","created":"2025-12-22","cited_by_count":6},{"id":"2601.09518","title":"Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations","created":"2026-01-14","cited_by_count":6},{"id":"2510.10206","title":"It Takes Two: Learning Interactive Whole-Body Control Between Humanoid Robots","created":"2025-10-11","cited_by_count":5},{"id":"2502.13134","title":"RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations","created":"2025-02-18","cited_by_count":4},{"id":"2507.02565","title":"Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning","created":"2025-07-03","cited_by_count":4},{"id":"2307.00464","title":"Human-to-Human Interaction Detection","created":"2023-07-02","cited_by_count":3},{"id":"2603.00144","title":"Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation","created":"2026-02-24","cited_by_count":3},{"id":"2506.03084","title":"InterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mamba","created":"2025-06-03","cited_by_count":2},{"id":"2603.15083","title":"ReactMotion: Generating Reactive Listener Motions from Speaker Utterance","created":"2026-03-16","cited_by_count":1},{"id":"2604.01082","title":"ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data","created":"2026-04-01","cited_by_count":1}],"next_cursor":null}