Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 1,818

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

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

Open access
Liu, Jun, Shahroudy, Amir, Perez, Mauricio, Wang, Gang, Duan, Ling-Yu, Kot, Alex C.·2020·IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI 10.1109/tpami.2019.2916873
Open this paper in CoChat — free account

Abstract

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2019.2916873

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 9 references

Research works printed but not linked: 103

  1. 10.1109/CVPR.2018.00300 · DOI
  2. 10.1109/TPAMI.2015.2505295 · DOI
  3. 10.1016/j.patcog.2015.11.019 · DOI · Paper page
  4. 10.1016/j.cviu.2018.04.007 · DOI · Paper page
  5. 10.1016/j.patcog.2016.05.019 · DOI · Paper page
  6. 10.1109/CVPR.2017.391 · DOI · Paper page
  7. 10.1109/MMUL.2012.24 · DOI · Paper page
  8. 10.1142/S0218001415550083 · DOI · Paper page
  9. han, 2017, Space-time representation of people based on 3D skeletal data: A review, Comput Vis Image Understanding, 158, 85, 10.1016/j.cviu.2017.01.011 · DOI · Paper page
  10. 10.1016/j.patrec.2013.02.006 · DOI · Paper page
  11. 10.1145/3077136.3080831 · DOI
  12. ye, 2013, A survey on human motion analysis from depth data, Time-of-Flight and Depth Imaging Sensors Algorithms and Applications, 149
  13. 10.1109/CVPR.2014.339 · DOI · Paper page
  14. 10.1145/2647868.2654912 · DOI
  15. rahmani, 2014, HOPC: Histogram of oriented principal components of 3D pointclouds for action recognition, Proc Eur Conf Comput Vis, 742
  16. 10.1109/TPAMI.2016.2533389 · DOI · Paper page
  17. 10.1109/ICIP.2015.7350781 · DOI · Paper page
  18. 10.1109/CVPR.2017.713 · DOI · Paper page
  19. 10.1109/TPAMI.2016.2640292 · DOI · Paper page
  20. 10.1145/2733373.2806315 · DOI
  21. 10.1109/CVPR.2014.108 · DOI · Paper page
  22. 10.1109/CVPR.2011.5995316 · DOI · Paper page
  23. 10.1109/ICCV.2015.460 · DOI · Paper page
  24. 10.1109/WACV.2014.6836044 · DOI
  25. 10.1109/ISCCSP.2014.6877819 · DOI
  26. 10.1109/TPAMI.2013.198 · DOI · Paper page
  27. ohn-bar, 2013, Joint angles similarities and HOG$^2$2 for action recognition, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit Workshops, 465
  28. 10.1109/CVPR.2014.82 · DOI · Paper page
  29. 10.1109/ICPR.2014.772 · DOI · Paper page
  30. 10.1109/TPAMI.2019.2894422 · DOI
  31. 10.1109/CVPR.2014.104 · DOI
  32. 10.1016/j.patrec.2014.04.011 · DOI · Paper page
  33. 10.1007/s11263-014-0777-6 · DOI · Paper page
  34. soomro, 2012, UCF101: A dataset of 101 human actions classes from videos in the wild, arXiv preprint arXiv 1212 0402
  35. kay, 0, The kinetics human action video dataset, arXiv preprint arXiv 1705 06950
  36. du, 2015, Hierarchical recurrent neural network for skeleton based action recognition, Proc IEEE Conf Comput Vis Pattern Recognit, 1110
  37. liu, 2017, PKU-MMD: A large scale benchmark for continuous multi-modal human action understanding, arXiv preprint arXiv 1703 08337
  38. 10.1109/CVPRW.2012.6239175 · DOI · Paper page
  39. liu, 2016, Spatio-temporal LSTM with trust gates for 3D human action recognition, Proc Eur Conf Comput Vis, 816
  40. 10.1109/CVPR.2016.115 · DOI · Paper page
  41. 10.1109/ICCV.2013.227 · DOI · Paper page
  42. 10.1109/CVPR.2015.7299172 · DOI · Paper page
  43. 10.1109/CVPR.2015.7298708 · DOI
  44. 10.1109/TPAMI.2017.2691321 · DOI · Paper page
  45. 10.1109/TMM.2018.2802648 · DOI · Paper page
  46. 10.1007/978-3-030-01234-2_21 · DOI
  47. 10.1109/CVPR.2018.00126 · DOI
  48. 10.1109/CVPR.2018.00056 · DOI · Paper page
  49. 10.1109/ICME.2017.8019438 · DOI
  50. 10.1109/CVPR.2018.00558 · DOI · Paper page
  51. 10.1109/TCSII.2019.2899829 · DOI
  52. 10.1016/B978-0-12-813445-0.00005-8 · DOI
  53. 10.1109/CVPR.2017.387 · DOI · Paper page
  54. 10.1109/CVPR.2017.498 · DOI
  55. zhu, 2016, Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks, Proc 30th AAAI Conf Artif Intell, 3697
  56. 10.1109/CVPR.2017.137 · DOI · Paper page
  57. 10.1109/CVPR.2017.751 · DOI · Paper page
  58. 10.1109/ICCV.2017.316 · DOI · Paper page
  59. ke, 2018, Global regularizer and temporal-aware cross-entropy for skeleton-based early action recognition, Proc 14th Asian Conf Comput Vis, 1
  60. 10.1109/CVPRW.2017.207 · DOI · Paper page
  61. 10.1109/ICCV.2017.621 · DOI
  62. 10.1109/CVPR.2018.00539 · DOI · Paper page
  63. 10.1109/CVPRW.2017.165 · doi:10.1109/cvprw.2017.165
  64. 10.1109/TPAMI.2014.2316828 · DOI · Paper page
  65. baradel, 2017, Pose-conditioned spatio-temporal attention for human action recognition, arXiv preprint arXiv 1703 10593
  66. han, 2013, Enhanced computer vision with microsoft kinect sensor: A review, IEEE Trans Cybern, 43, 1318, 10.1109/TCYB.2013.2265378 · DOI · Paper page
  67. howard, 2017, MobileNets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv 1704 04861
  68. 10.1109/ASRU.2013.6707742 · DOI · Paper page
  69. 10.1109/CVPR.2018.00871 · DOI
  70. 10.1109/TPAMI.2017.2771306 · DOI · Paper page
  71. 10.1109/CVPR.2018.00127 · DOI · Paper page
  72. 10.1016/j.patcog.2016.01.020 · DOI
  73. 10.1109/TIP.2018.2812099 · DOI · Paper page
  74. kone?n?, 2014, One-shot-learning gesture recognition using HOG-HOF features, J Mach Learn Res, 15, 2513
  75. 10.1109/TIP.2017.2785279 · DOI · Paper page
  76. 10.1109/TPAMI.2015.2513479 · DOI
  77. 10.1016/j.patcog.2017.02.030 · DOI · Paper page
  78. fanello, 2013, One-shot learning for real-time action recognition, Proc Iberian Conf Pattern Recognit Image Anal, 31, 10.1007/978-3-642-38628-2_4 · DOI
  79. 10.1109/TPAMI.2019.2898954 · DOI · Paper page
  80. 10.1109/TPAMI.2018.2863279 · DOI
  81. simonyan, 0, Two-stream convolutional networks for action recognition in videos, Proc 27th Int Conf Neural Inf Process Syst, 568
  82. simonyan, 2015, Very deep convolutional networks for large-scale image recognition, Proc Int Conf Learn Representations, 1
  83. 10.1109/ICCV.2017.394 · DOI
  84. 10.18653/v1/N16-1174 · DOI · Paper page
  85. 10.3115/v1/D14-1162 · DOI · Paper page
  86. 10.1016/j.patrec.2016.06.012 · DOI · Paper page
  87. 10.1109/THMS.2015.2504550 · DOI · Paper page
  88. 10.1109/CVPRW.2010.5543273 · DOI · Paper page
  89. sung, 2011, Human activity detection from RGBD images, Proc AAAI Conf Plan Activity Intent Recognit, 47
  90. 10.1109/CVPR.2012.6247813 · DOI · Paper page
  91. 10.1109/CVPRW.2012.6239233 · DOI · Paper page
  92. cheng, 2012, Human daily action analysis with multi-view and color-depth data, Proc Eur Conf Comput Vis Workshops, 52
  93. 10.1109/LSP.2017.2690339 · DOI · Paper page
  94. 10.1177/0278364913478446 · DOI · Paper page
  95. 10.1109/CVPR.2017.52 · DOI
  96. 10.1109/CVPR.2013.98 · DOI · Paper page
  97. koch, 2015, Siamese neural networks for one-shot image recognition, Proc 32nd Int Conf Mach Learn, 1
  98. 10.1109/ICCV.2013.406 · DOI
  99. 10.1109/CVPR.2015.7298860 · DOI
  100. vinyals, 0, Matching networks for one shot learning, Proc 30th Int Conf Neural Inf Process Syst, 3637
  101. ravi, 2017, Optimization as a model for few-shot learning, Proc Int Conf Learn Representations, 1
  102. 10.1109/CVPR.2018.00157 · DOI
  103. 10.1109/TPAMI.2006.79 · DOI · Paper page

Cited by

See all 1,818

Metadata

Authors
Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.-Y., & Kot, A. C.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2020-10-01
Volume
42
Issue
10
Pages
2684-2701
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
DOI
10.1109/tpami.2019.2916873
OpenAlex
W2944006115
Cited by
1,818
References
9
FWCI
57.76
Type
journal article
Language
en
Open access
green
Licence
Funders
  • National Research Foundation (NRF2016NRF-NSFC001-098)
  • National Natural Science Foundation of China (61661146005, U1611461)
  • National Basic Research Program of China (2015CB351806)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding. https://app.cochat.ai/papers/10.1109/tpami.2019.2916873
The paper
Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.-Y., & Kot, A. C. (2020). NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2019.2916873

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.