{"total":234,"rows":[{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229,"area":null},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186,"area":null},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153,"area":null},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138,"area":null},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109,"area":null},{"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,"area":"diffusion"},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100,"area":null},{"id":"2207.01567","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","created":"2022-07-04","cited_by_count":100,"area":null},{"id":"2303.10876","title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","created":"2023-03-20","cited_by_count":97,"area":null},{"id":"2112.10103","title":"SAGA: Stochastic Whole-Body Grasping with Contact","created":"2021-12-19","cited_by_count":91,"area":null},{"id":"2110.04573","title":"Space-Time-Separable Graph Convolutional Network for Pose Forecasting","created":"2021-10-09","cited_by_count":84,"area":null},{"id":"2211.14304","title":"BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction","created":"2022-11-25","cited_by_count":82,"area":"diffusion"},{"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,"area":null},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75,"area":null},{"id":"2108.08422","title":"Generating Smooth Pose Sequences for Diverse Human Motion Prediction","created":"2021-08-19","cited_by_count":66,"area":null},{"id":"2203.16051","title":"Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction","created":"2022-03-30","cited_by_count":66,"area":null},{"id":"2101.10025","title":"A Review of Graph Neural Networks and Their Applications in Power Systems","created":"2021-01-25","cited_by_count":63,"area":null},{"id":"2111.12073","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","created":"2021-11-23","cited_by_count":63,"area":null},{"id":"2111.12159","title":"Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure","created":"2021-11-23","cited_by_count":53,"area":null},{"id":"2203.01821","title":"Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph","created":"2022-03-03","cited_by_count":53,"area":null},{"id":"2104.04029","title":"TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild","created":"2021-04-08","cited_by_count":52,"area":null},{"id":"2203.05046","title":"Adaptive Trajectory Prediction via Transferable GNN","created":"2022-03-09","cited_by_count":51,"area":null},{"id":"2310.05921","title":"Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions","created":"2023-10-09","cited_by_count":50,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2203.01474","title":"Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction","created":"2022-03-03","cited_by_count":48,"area":null},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46,"area":null},{"id":"2110.07288","title":"View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums","created":"2021-10-14","cited_by_count":45,"area":null},{"id":"1909.03449","title":"Imitation Learning for Human Pose Prediction","created":"2019-09-08","cited_by_count":44,"area":"offlinerl"},{"id":"2310.02242","title":"Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models","created":"2023-10-03","cited_by_count":43,"area":"diffusion"},{"id":"2101.05390","title":"Universal Approximation Theorems for Differentiable Geometric Deep Learning","created":"2021-01-13","cited_by_count":41,"area":null},{"id":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"area":null},{"id":"2108.11244","title":"Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction","created":"2021-08-25","cited_by_count":37,"area":null},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37,"area":null},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36,"area":null},{"id":"2108.01316","title":"RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting","created":"2021-08-03","cited_by_count":36,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2102.09117","title":"Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking","created":"2021-02-18","cited_by_count":35,"area":null},{"id":"2106.09300","title":"Multi-level Motion Attention for Human Motion Prediction","created":"2021-06-17","cited_by_count":35,"area":null},{"id":"2302.04860","title":"Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors","created":"2023-02-09","cited_by_count":34,"area":null},{"id":"2310.13768","title":"PACE: Human and Camera Motion Estimation from in-the-wild Videos","created":"2023-10-20","cited_by_count":34,"area":null},{"id":"2210.05669","title":"A generic diffusion-based approach for 3D human pose prediction in the wild","created":"2022-10-11","cited_by_count":33,"area":"diffusion"},{"id":"2402.19348","title":"Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook","created":"2024-02-29","cited_by_count":33,"area":null},{"id":"2112.15012","title":"Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction","created":"2021-12-30","cited_by_count":31,"area":null},{"id":"2202.10688","title":"Graph Lifelong Learning: A Survey","created":"2022-02-22","cited_by_count":30,"area":null},{"id":"2203.01593","title":"3D Human Motion Prediction: A Survey","created":"2022-03-03","cited_by_count":30,"area":null},{"id":"2203.04132","title":"Motron: Multimodal Probabilistic Human Motion Forecasting","created":"2022-03-08","cited_by_count":30,"area":null},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2106.13432","title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2205.02540","title":"Real-time Controllable Motion Transition for Characters","created":"2022-05-05","cited_by_count":29,"area":null},{"id":"2208.00368","title":"Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction","created":"2022-07-31","cited_by_count":29,"area":null},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29,"area":null},{"id":"2106.11083","title":"Conditional Neural Relational Inference for Interacting Systems","created":"2021-06-21","cited_by_count":28,"area":null},{"id":"2205.15608","title":"Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction","created":"2022-05-31","cited_by_count":26,"area":null},{"id":"2303.05095","title":"Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting","created":"2023-03-09","cited_by_count":26,"area":null},{"id":"2312.14828","title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","created":"2023-12-22","cited_by_count":26,"area":null},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25,"area":null},{"id":"2202.04307","title":"Conditional Motion In-betweening","created":"2022-02-09","cited_by_count":25,"area":null},{"id":"2203.14250","title":"End-to-End Active Speaker Detection","created":"2022-03-27","cited_by_count":25,"area":null},{"id":"2208.07308","title":"Pose Forecasting in Industrial Human-Robot Collaboration","created":"2022-07-24","cited_by_count":25,"area":null},{"id":"2103.09755","title":"Aggregated Multi-GANs for Controlled 3D Human Motion Prediction","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23,"area":null},{"id":"2312.16737","title":"HMP: Hand Motion Priors for Pose and Shape Estimation from Video","created":"2023-12-27","cited_by_count":23,"area":null},{"id":"2106.02533","title":"Graph-based Deep Learning for Communication Networks: A Survey","created":"2021-06-04","cited_by_count":21,"area":null},{"id":"2305.12554","title":"CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion","created":"2023-05-21","cited_by_count":21,"area":null},{"id":"2105.11731","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","created":"2021-05-25","cited_by_count":20,"area":null},{"id":"2107.00894","title":"Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network","created":"2021-07-02","cited_by_count":20,"area":null},{"id":"2308.08942","title":"Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction","created":"2023-08-17","cited_by_count":20,"area":null},{"id":"2104.12446","title":"Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty","created":"2021-04-26","cited_by_count":19,"area":null},{"id":"2109.14128","title":"Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting","created":"2021-09-29","cited_by_count":19,"area":null},{"id":"2211.15501","title":"Proactive Robot Assistance via Spatio-Temporal Object Modeling","created":"2022-11-28","cited_by_count":18,"area":null},{"id":"2106.01981","title":"ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2207.09425","title":"Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos","created":"2022-07-19","cited_by_count":17,"area":null},{"id":"2307.16106","title":"TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction","created":"2023-07-30","cited_by_count":17,"area":"diffusion"},{"id":"2508.01126","title":"UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation","created":"2025-08-02","cited_by_count":17,"area":null},{"id":"2103.02758","title":"Learning Asynchronous and Sparse Human-Object Interaction in Videos","created":"2021-03-03","cited_by_count":16,"area":null},{"id":"2204.01565","title":"HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE","created":"2022-04-04","cited_by_count":16,"area":null},{"id":"2308.04808","title":"Joint-Relation Transformer for Multi-Person Motion Prediction","created":"2023-08-09","cited_by_count":16,"area":null},{"id":"2304.05729","title":"Dynamic Graph Representation Learning with Neural Networks: A Survey","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2408.16426","title":"COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation","created":"2024-08-29","cited_by_count":15,"area":"diffusion"},{"id":"2503.18589","title":"Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14,"area":null},{"id":"2111.06750","title":"STFL: A Temporal-Spatial Federated Learning Framework for Graph Neural Networks","created":"2021-11-12","cited_by_count":14,"area":null},{"id":"2302.14503","title":"Can We Use Diffusion Probabilistic Models for 3D Motion Prediction?","created":"2023-02-28","cited_by_count":14,"area":"diffusion"},{"id":"2407.11494","title":"Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction","created":"2024-07-16","cited_by_count":14,"area":"diffusion"},{"id":"2503.03262","title":"Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions","created":"2025-03-05","cited_by_count":14,"area":null},{"id":"2203.09116","title":"MotionAug: Augmentation with Physical Correction for Human Motion Prediction","created":"2022-03-17","cited_by_count":13,"area":null},{"id":"2306.03597","title":"Human-Object Interaction Prediction in Videos through Gaze Following","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2104.03020","title":"Graph-based Normalizing Flow for Human Motion Generation and Reconstruction","created":"2021-04-07","cited_by_count":12,"area":null},{"id":"2108.08633","title":"Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2209.12243","title":"Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting","created":"2022-09-25","cited_by_count":12,"area":null},{"id":"2501.06035","title":"Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction","created":"2025-01-10","cited_by_count":12,"area":null},{"id":"2107.00712","title":"Passing a Non-verbal Turing Test: Evaluating Gesture Animations Generated from Speech","created":"2021-07-01","cited_by_count":11,"area":null},{"id":"2208.03257","title":"3D Pose Based Feedback for Physical Exercises","created":"2022-08-05","cited_by_count":11,"area":null},{"id":"2304.06707","title":"Toward Reliable Human Pose Forecasting with Uncertainty","created":"2023-04-13","cited_by_count":11,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2410.17785","title":"TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports","created":"2024-10-23","cited_by_count":11,"area":null},{"id":"2412.02903","title":"EgoCast: Forecasting Egocentric Human Pose in the Wild","created":"2024-12-03","cited_by_count":11,"area":null}],"next_cursor":"100"}