mlsanityData to 14 Oct 2026

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

arXiv 1905.04757 ↗First posted 12 May 2019cs.CVcited by 533

Not on the map. Why?

Abstract (arXiv)

Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of large-scale training samples, realistic number of distinct class categories, diversity in camera views, varied environmental conditions, and variety of human subjects. In this work, we introduce a large-scale dataset for RGB+D human action recognition, which is collected from 106 distinct subjects and contains more than 114 thousand video samples and 8 million frames. This dataset contains 120 different action classes including daily, mutual, and health-related activities. We evaluate the performance of a series of existing 3D activity analysis methods on this dataset, and show the advantage of applying deep learning methods for 3D-based human action recognition. Furthermore, we investigate a novel one-shot 3D activity recognition problem on our dataset, and a simple yet effective Action-Part Semantic Relevance-aware (APSR) framework is proposed for this task, which yields promising results for recognition of the novel action classes. We believe the introduction of this large-scale dataset will enable the community to apply, adapt, and develop various data-hungry learning techniques for depth-based and RGB+D-based human activity understanding. [The dataset is available at: http://rose1.ntu.edu.sg/Datasets/actionRecognition.asp]

Key facts. Cited by 533 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 53; 2022: 96; 2023: 114; 2024: 100; 2025: 96; 2026: 74.

533 papers.

Sort:

By area:

  1. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmarkcited by 1,109
  2. 2021Transformers in Vision: A Surveycited by 1,013
  3. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  4. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  5. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 408
  6. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  7. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 317
  8. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 287
  9. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 265
  10. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  11. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 249
  12. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 227
38 more
  1. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 206
  2. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  3. 2023DisCo: Disentangled Control for Realistic Human Dance Generationcited by 142
  4. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 117
  5. 2022Gait Recognition in the Wild with Dense 3D Representations and A Benchmarkcited by 114
  6. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 106
  7. 2023HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generationcited by 105
  8. 2023HumanTOMATO: Text-aligned Whole-body Motion Generationcited by 104
  9. 2023Inter-X: Towards Versatile Human-Human Interaction Analysiscited by 98
  10. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 96
  11. 2023Human Motion Generation: A Surveycited by 96
  12. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  13. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 90
  14. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  15. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  16. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  17. 2022ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generationcited by 77
  18. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  19. 2021Multi-Person Extreme Motion Predictioncited by 75
  20. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  21. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  22. 2022NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactionscited by 68
  23. 2024Large Motion Model for Unified Multi-Modal Motion Generationcited by 65
  24. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  25. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  26. 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
  27. 2023ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactionscited by 62
  28. 2022Implicit Neural Representations for Variable Length Human Motion Generationcited by 61
  29. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  30. 2023C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characterscited by 55
  31. 2022Towards Good Practices for Missing Modality Robust Action Recognitioncited by 54
  32. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  33. 2024ReGenNet: Towards Human Action-Reaction Synthesiscited by 53
  34. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 47
  35. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 44
  36. 2022Generative Action Description Prompts for Skeleton-based Action Recognitioncited by 43
  37. 2022STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognitioncited by 43
  38. 2022Interaction Transformer for Human Reaction Generationcited by 42

50 most cited of 533 All 533 (JSON)