{"total":496,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501,"area":null},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408,"area":null},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265,"area":null},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257,"area":null},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249,"area":null},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"area":null},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193,"area":null},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142,"area":null},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117,"area":null},{"id":"2204.02569","title":"Gait Recognition in the Wild with Dense 3D Representations and A Benchmark","created":"2022-04-06","cited_by_count":114,"area":null},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106,"area":null},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104,"area":null},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96,"area":null},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96,"area":null},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95,"area":null},{"id":"2112.03590","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","created":"2021-12-07","cited_by_count":90,"area":null},{"id":"2106.15125","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","created":"2021-06-29","cited_by_count":87,"area":null},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85,"area":null},{"id":"2205.09443","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","created":"2022-05-19","cited_by_count":83,"area":null},{"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":"2108.03656","title":"Skeleton-Contrastive 3D Action Representation Learning","created":"2021-08-08","cited_by_count":76,"area":null},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75,"area":null},{"id":"2206.13028","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","created":"2022-06-27","cited_by_count":71,"area":null},{"id":"2205.13713","title":"PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences","created":"2022-05-27","cited_by_count":68,"area":null},{"id":"2212.07626","title":"NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions","created":"2022-12-15","cited_by_count":68,"area":null},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65,"area":null},{"id":"2112.13715","title":"SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos","created":"2021-12-27","cited_by_count":64,"area":null},{"id":"2108.07181","title":"Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation","created":"2021-08-16","cited_by_count":62,"area":null},{"id":"2303.03729","title":"Learning Discriminative Representations for Skeleton Based Action Recognition","created":"2023-03-07","cited_by_count":62,"area":null},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62,"area":null},{"id":"2203.13694","title":"Implicit Neural Representations for Variable Length Human Motion Generation","created":"2022-03-25","cited_by_count":61,"area":null},{"id":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58,"area":null},{"id":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55,"area":null},{"id":"2211.13916","title":"Towards Good Practices for Missing Modality Robust Action Recognition","created":"2022-11-25","cited_by_count":54,"area":null},{"id":"2312.02963","title":"MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures","created":"2023-12-05","cited_by_count":54,"area":null},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2403.09508","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","created":"2024-03-14","cited_by_count":47,"area":null},{"id":"2303.06242","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","created":"2023-03-10","cited_by_count":44,"area":null},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43,"area":null},{"id":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43,"area":null},{"id":"2207.01685","title":"Interaction Transformer for Human Reaction Generation","created":"2022-07-04","cited_by_count":42,"area":null},{"id":"2303.10904","title":"Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition","created":"2023-03-20","cited_by_count":42,"area":null},{"id":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42,"area":null},{"id":"2307.08476","title":"SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training","created":"2023-07-17","cited_by_count":41,"area":null},{"id":"2308.07092","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","created":"2023-08-14","cited_by_count":41,"area":null},{"id":"2303.14474","title":"3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition","created":"2023-03-25","cited_by_count":40,"area":null},{"id":"2208.12448","title":"CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation","created":"2022-08-26","cited_by_count":38,"area":null},{"id":"2210.08394","title":"mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors","created":"2022-10-15","cited_by_count":38,"area":null},{"id":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","cited_by_count":38,"area":null},{"id":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37,"area":null},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36,"area":null},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36,"area":null},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35,"area":null},{"id":"2208.03497","title":"Contrastive Positive Mining for Unsupervised 3D Action Representation Learning","created":"2022-08-06","cited_by_count":34,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2207.06101","title":"Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning","created":"2022-07-13","cited_by_count":33,"area":null},{"id":"2205.07417","title":"Transformers in 3D Point Clouds: A Survey","created":"2022-05-16","cited_by_count":31,"area":null},{"id":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","cited_by_count":31,"area":null},{"id":"2211.13466","title":"Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations","created":"2022-11-24","cited_by_count":31,"area":null},{"id":"2207.09644","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","created":"2022-07-20","cited_by_count":30,"area":null},{"id":"2212.02082","title":"Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning","created":"2022-12-05","cited_by_count":30,"area":null},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29,"area":null},{"id":"2209.02399","title":"SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition","created":"2022-09-01","cited_by_count":29,"area":null},{"id":"2405.18483","title":"Towards Open Domain Text-Driven Synthesis of Multi-Person Motions","created":"2024-05-28","cited_by_count":29,"area":null},{"id":"2411.18941","title":"Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2502.20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation","created":"2025-02-27","cited_by_count":28,"area":null},{"id":"2111.13089","title":"GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition","created":"2021-11-25","cited_by_count":27,"area":null},{"id":"2305.12398","title":"Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition","created":"2023-05-21","cited_by_count":27,"area":null},{"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,"area":null},{"id":"2203.13815","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","created":"2022-03-25","cited_by_count":26,"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":"2210.05895","title":"DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition","created":"2022-10-12","cited_by_count":26,"area":null},{"id":"2301.10931","title":"Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning","created":"2023-01-26","cited_by_count":26,"area":null},{"id":"2410.19818","title":"UniMTS: Unified Pre-training for Motion Time Series","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2108.04536","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","created":"2021-08-10","cited_by_count":25,"area":null},{"id":"2203.11113","title":"No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces","created":"2022-03-21","cited_by_count":25,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2302.09018","title":"Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences","created":"2023-02-17","cited_by_count":25,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2101.11530","title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition","created":"2021-01-27","cited_by_count":24,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2107.00606","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","created":"2021-07-01","cited_by_count":24,"area":null},{"id":"2308.03950","title":"Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization","created":"2023-08-07","cited_by_count":24,"area":null},{"id":"2110.11191","title":"Generative Adversarial Graph Convolutional Networks for Human Action Synthesis","created":"2021-10-21","cited_by_count":23,"area":null},{"id":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23,"area":null},{"id":"2307.07469","title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","created":"2023-07-14","cited_by_count":23,"area":null},{"id":"2406.13327","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","created":"2024-06-19","cited_by_count":23,"area":null},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2105.01563","title":"Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition","created":"2021-05-04","cited_by_count":22,"area":null},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22,"area":null},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null}],"next_cursor":"100"}