mlsanityData to 7 Oct 2026

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

arXiv 1604.02808 ↗First posted 11 Apr 2016cs.CVcited by 683

Not on the map. Why?

Abstract (arXiv)

Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of training samples, distinct class labels, camera views and variety of subjects. In this paper we introduce a large-scale dataset for RGB+D human action recognition with more than 56 thousand video samples and 4 million frames, collected from 40 distinct subjects. Our dataset contains 60 different action classes including daily, mutual, and health-related actions. In addition, we propose a new recurrent neural network structure to model the long-term temporal correlation of the features for each body part, and utilize them for better action classification. Experimental results show the advantages of applying deep learning methods over state-of-the-art hand-crafted features on the suggested cross-subject and cross-view evaluation criteria for our dataset. The introduction of this large scale dataset will enable the community to apply, develop and adapt various data-hungry learning techniques for the task of depth-based and RGB+D-based human activity analysis.

Key facts. Cited by 683 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 92; 2022: 121; 2023: 130; 2024: 140; 2025: 109; 2026: 91.

683 papers.

Sort:

By area:

  1. 2021Transformers in Vision: A Surveycited by 1,009
  2. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  3. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  4. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
  5. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  6. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  7. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  8. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  9. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  10. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  11. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  12. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
38 more
  1. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 109
  2. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 105
  3. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
  4. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 95
  5. 2023Human Motion Generation: A Surveycited by 95
  6. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 89
  7. 2024MotionLLM: Understanding Human Behaviors from Human Motions and Videoscited by 89
  8. 2024Deep Multimodal Learning with Missing Modality: A Surveycited by 89
  9. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  10. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
  11. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  12. 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understandingcited by 85
  13. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  14. 2024Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-trainingcited by 82
  15. 2023MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensingcited by 77
  16. 2024OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generationcited by 77
  17. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  18. 2021Multi-Person Extreme Motion Predictioncited by 74
  19. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  20. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  21. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  22. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  23. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  24. 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimationcited by 64
  25. 2021iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysiscited by 63
  26. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  27. 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
  28. 2024MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Modelscited by 61
  29. 2021Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learningcited by 58
  30. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  31. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  32. 2022Towards Good Practices for Missing Modality Robust Action Recognitioncited by 53
  33. 2021Home Action Genome: Cooperative Compositional Action Understandingcited by 52
  34. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  35. 2025FastVID: Dynamic Density Pruning for Fast Video Large Language Modelscited by 47
  36. 2021Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformerscited by 46
  37. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 46
  38. 2022Generative Action Description Prompts for Skeleton-based Action Recognitioncited by 43

50 most cited of 683 All 683 (JSON)