{"total":686,"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":"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":"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":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","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":"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":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168,"area":"diffusion"},{"id":"2201.00766","title":"Class-Incremental Continual Learning into the eXtended DER-verse","created":"2022-01-03","cited_by_count":124,"area":"distill"},{"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":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","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":"2307.10173","title":"DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering","created":"2023-07-19","cited_by_count":103,"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":"2409.07825","title":"Deep Multimodal Learning with Missing Modality: A Survey","created":"2024-09-12","cited_by_count":92,"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":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90,"area":null},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88,"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":"2207.13807","title":"Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields","created":"2022-07-27","cited_by_count":85,"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":"2410.08202","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","created":"2024-10-10","cited_by_count":82,"area":"mllm"},{"id":"2305.10345","title":"MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing","created":"2023-05-12","cited_by_count":79,"area":null},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","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":"2203.06714","title":"A Survey on Deep Graph Generation: Methods and Applications","created":"2022-03-13","cited_by_count":69,"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":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67,"area":"mllm"},{"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":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64,"area":null},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63,"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":"2108.01959","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","created":"2021-08-04","cited_by_count":58,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"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":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53,"area":null},{"id":"2503.11187","title":"FastVID: Dynamic Density Pruning for Fast Video Large Language Models","created":"2025-03-14","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"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":"2109.07531","title":"Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers","created":"2021-09-15","cited_by_count":46,"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":"2303.10904","title":"Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition","created":"2023-03-20","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":"2601.14724","title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","created":"2026-01-21","cited_by_count":41,"area":"mllm"},{"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":"2309.01372","title":"DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion","created":"2023-09-04","cited_by_count":37,"area":"diffusion"},{"id":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37,"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":"2206.14674","title":"Signature Methods in Machine Learning","created":"2022-06-29","cited_by_count":34,"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":"2207.06101","title":"Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning","created":"2022-07-13","cited_by_count":33,"area":null},{"id":"2108.03619","title":"Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection","created":"2021-08-08","cited_by_count":32,"area":"distill"},{"id":"2104.02710","title":"The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions","created":"2021-04-06","cited_by_count":31,"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":"2203.01593","title":"3D Human Motion Prediction: A Survey","created":"2022-03-03","cited_by_count":30,"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":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","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":"2112.04178","title":"Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition","created":"2021-12-08","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":"2310.03986","title":"Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation","created":"2023-10-06","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":"2203.15935","title":"Graph Neural Networks in IoT: A Survey","created":"2022-03-29","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":"2305.08953","title":"Motion Question Answering via Modular Motion Programs","created":"2023-05-15","cited_by_count":27,"area":"lr"},{"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":"2309.14331","title":"LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference","created":"2023-09-25","cited_by_count":27,"area":null},{"id":"2103.05266","title":"BASAR:Black-box Attack on Skeletal Action Recognition","created":"2021-03-09","cited_by_count":26,"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":"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":"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":"2407.08428","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2412.09613","title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models","created":"2024-12-12","cited_by_count":25,"area":"mllm"},{"id":"2101.11530","title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition","created":"2021-01-27","cited_by_count":24,"area":null}],"next_cursor":"100"}