---
title: "Skeleton and pose (NTU RGB+D, Human3.6M): tasks and access"
description: "Skeleton and pose (NTU RGB+D, Human3.6M): compare tasks, official access, usage conditions and evaluation. Includes research-paper mention counts and trends."
url: https://scholar4ai.com/datasets/skeleton-and-pose-ntu-rgb-d-human3-6m
markdown_url: https://scholar4ai.com/datasets/skeleton-and-pose-ntu-rgb-d-human3-6m.md
license: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
share_text: "Skeleton and pose (NTU RGB+D, Human3.6M): compare tasks, official access, usage conditions and evaluation. Includes research-paper mention counts and trends. (as of 2026-11-05)"
data_url: https://scholar4ai.com/data/rankings.json
updated: 2026-11-05T06:02:37+09:00
window: 2026-10-07 to 2026-11-05
source: OpenAlex (CC0)
---

# Skeleton and pose (NTU RGB+D, Human3.6M)

[Browse dataset profiles](https://scholar4ai.com/datasets/directory/page/6.md)

Faces, people, poses, facial expressions and human actions in images and video.

- data category: Face, person and video benchmarks
- 0 papers in the last 7 days
- Names searched for: NTU RGB+D, NTU-RGB+D, NTU RGB-D, NTU60, NTU120, Human3.6M

Most-used data: https://scholar4ai.com/rankings/datasets.md · All Face, person and video benchmarks datasets: https://scholar4ai.com/datasets/face-person-and-video-benchmarks.md

## Tasks, access and usage conditions

Mention counts below measure name matches in tracked papers, not benchmark quality or downloads. A family count can cover multiple datasets; it is not a separate count for each comparison row. Choose a task and version first, preserve evaluation splits, and follow the linked release terms. The site's content license does not replace the datasets' own terms.

*Dataset comparison: tasks, access and usage conditions*

| Dataset / version | Task and evaluation | Access and preparation | Usage conditions |
|---|---|---|---|
| NTU RGB+D 60 / 120 | Action recognition with RGB, depth, infrared and 3D skeleton sequences; 60 or 120 classes. Evaluation: Use the version-specific cross-subject and cross-view/setup protocols; report missing skeletons and modality exclusions. | [Official source / documentation](https://rose1.ntu.edu.sg/dataset/actionRecognition/) Select the 56,880-sample original release or 114,480-sample extension and the required modalities; follow the lab’s application instructions. | Follow the lab’s release/application conditions and citation requirements; access is not an unrestricted right to redistribute recordings. |
| Human3.6M | 3D human-pose estimation from controlled motion-capture recordings. Evaluation: State MPJPE or aligned P-MPJPE, units, subject split and alignment; these metrics are not interchangeable. | [Official source / documentation](https://doi.org/10.1109/TPAMI.2013.248) Use the creator’s registered release referenced by the paper; preserve subject IDs and camera calibration. | Requires the applicable dataset agreement; no blanket commercial or redistribution permission is asserted. |

Guide updated 2026-11-05.

## Key findings

- From Nov 2023 to Oct 2026, 105 archived papers mentioned Skeleton and pose (NTU RGB+D, Human3.6M) in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Dec 2025 (8).
- Skeleton and pose (NTU RGB+D, Human3.6M) was mentioned in 1 paper in the last 30 days (2026-10-07 to 2026-11-05), ranking #165 of the 246 datasets mentioned.
- By journal category: AI (1).
- Most of them appeared in Pattern Recognition (1).
- From 2017 to 2026 (so far), Skeleton and pose (NTU RGB+D, Human3.6M) was mentioned in 160 papers in the tracked journals, most of them in AI (158), operations research (1) and information systems (1).
- 33 of them were published in 2025, against 0 in 2017.
- Since 2023, the institutions with the most of these papers were Chinese Academy of Sciences (6), Peking University (6) and Beihang University (5).
- The journals publishing most of them were Pattern Recognition (23), IEEE Transactions on Pattern Analysis and Machine Intelligence (21) and IEEE Transactions on Neural Networks and Learning Systems (11).
- The most-cited of them is “NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding” (IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019), with 1,833 citations.
- Papers use Skeleton and pose (NTU RGB+D, Human3.6M) most often with Action recognition (Kinetics, UCF101, HMDB51) (17), ImageNet (17) and MS COCO (15); it has 12 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.

## Mentions over 36 months

*Papers mentioning it by publication month, Nov 2023 to Oct 2026 (titles, abstracts and keywords; the full texts of earlier months are still being searched)*

| Trend | Nov 23–Oct 24 | Nov 24–Oct 25 | Nov 25–Oct 26 | 36 months |
|---|---:|---:|---:|---:|
|  | 37 | 27 | 41 | 105 |

## Papers per year

*Papers per publication year and category*

| Category | 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 | 2025 | 2026 (so far) |
|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
| [AI](https://scholar4ai.com/categories/ai.md) | 0 | 4 | 8 | 7 | 7 | 13 | 20 | 36 | 32 | 31 |
| [Operations Research](https://scholar4ai.com/categories/operations-research.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
| [Information Systems](https://scholar4ai.com/categories/information-systems.md) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
| All categories | 0 | 4 | 8 | 7 | 7 | 13 | 20 | 36 | 33 | 32 |

## Where the papers come from

*Journals with the most papers, since 2023*

| # | Journal | Papers |
|---:|---|---:|
| 1 | [Pattern Recognition](https://scholar4ai.com/journals/pattern-recognition.md) | 23 |
| 2 | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 21 |
| 3 | [IEEE Transactions on Neural Networks and Learning Systems](https://scholar4ai.com/journals/ieee-transactions-on-neural-networks-and-learning-systems.md) | 11 |
| 4 | [Artificial Intelligence Review](https://scholar4ai.com/journals/artificial-intelligence-review.md) | 10 |
| 5 | [International Journal of Computer Vision](https://scholar4ai.com/journals/international-journal-of-computer-vision.md) | 10 |
| 6 | [Applied Intelligence](https://scholar4ai.com/journals/applied-intelligence.md) | 7 |
| 7 | [Expert Systems with Applications](https://scholar4ai.com/journals/expert-systems-with-applications.md) | 5 |
| 8 | [Pattern Recognition Letters](https://scholar4ai.com/journals/pattern-recognition-letters.md) | 4 |
| 9 | [Neural Computing and Applications](https://scholar4ai.com/journals/neural-computing-and-applications.md) | 4 |
| 10 | [Information Fusion](https://scholar4ai.com/journals/information-fusion.md) | 4 |

*Institutions with the most papers, since 2023*

| # | Institution | Papers |
|---:|---|---:|
| 1 | [Chinese Academy of Sciences](https://scholar4ai.com/institutions/chinese-academy-of-sciences.md) | 6 |
| 2 | [Peking University](https://scholar4ai.com/institutions/peking-university.md) | 6 |
| 3 | [Beihang University](https://scholar4ai.com/institutions/beihang-university.md) | 5 |
| 4 | [Tsinghua University](https://scholar4ai.com/institutions/tsinghua-university.md) | 5 |
| 5 | [Dalian University of Technology](https://scholar4ai.com/institutions/dalian-university-of-technology.md) | 4 |
| 6 | [Shenzhen University](https://scholar4ai.com/institutions/shenzhen-university.md) | 4 |
| 7 | [University of Chinese Academy of Sciences](https://scholar4ai.com/institutions/university-of-chinese-academy-of-sciences.md) | 4 |
| 8 | [Beijing University of Posts and Telecommunications](https://scholar4ai.com/institutions/beijing-university-of-posts-and-telecommunications.md) | 3 |
| 9 | [Institute of Automation](https://scholar4ai.com/institutions/institute-of-automation.md) | 3 |
| 10 | [Nanyang Technological University](https://scholar4ai.com/institutions/nanyang-technological-university.md) | 3 |

*Countries with the most papers, since 2023*

| # | Country | Papers |
|---:|---|---:|
| 1 | China | 70 |
| 2 | Australia | 15 |
| 3 | United Kingdom | 15 |
| 4 | United States | 12 |
| 5 | India | 6 |
| 6 | Spain | 5 |
| 7 | Japan | 5 |
| 8 | Singapore | 5 |
| 9 | Germany | 4 |
| 10 | Hong Kong | 4 |

*Keywords with the most papers, since 2023*

| # | Keyword | Papers |
|---:|---|---:|
| 1 | skeleton-based action recognition | 27 |
| 2 | Human3.6M | 25 |
| 3 | [graph convolutional networks](https://scholar4ai.com/keywords/graph-convolutional-networks.md) | 23 |
| 4 | 3D human pose estimation | 17 |
| 5 | human action recognition | 15 |
| 6 | MPI-INF-3DHP | 10 |
| 7 | NTU RGB+D | 10 |
| 8 | human motion prediction | 10 |
| 9 | CMU MoCap | 8 |
| 10 | [contrastive learning](https://scholar4ai.com/keywords/contrastive-learning.md) | 7 |

## Most-cited papers

*Most-cited papers since 2017*

| # | Citations | Per month | Title | Journal | Published | Authors |
|---:|---:|---:|---|---|---|---|
| 1 | 1,833 | 20.4 | [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://doi.org/10.1109/tpami.2019.2916873) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2019-05-14 | Jun Liu, Amir Shahroudy, Mauricio Pérez et al. |
| 2 | 537 | 9.6 | [Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition](https://doi.org/10.1109/tpami.2022.3157033) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2022-03-07 | Yifan Song, Zhang Zhang, Caifeng Shan et al. |
| 3 | 437 | 13.2 | [MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model](https://doi.org/10.1109/tpami.2024.3355414) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2024-01-29 | Mingyuan Zhang, Zhongang Cai, Liang Pan et al. |
| 4 | 272 | 2.9 | [LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images](https://doi.org/10.1109/tpami.2019.2892985) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2019-01-01 | Grégory Rogez, Philippe Weinzaepfel, Cordelia Schmid |
| 5 | 243 | 3.5 | [Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction](https://doi.org/10.1109/tpami.2021.3053765) | [IEEE Transactions on Pattern Analysis and Machine Intelligence](https://scholar4ai.com/journals/ieee-transactions-on-pattern-analysis-and-machine-intelligence.md) | 2021-01-22 | Maosen Li, Siheng Chen, Xu Chen et al. |

## Used together with

Papers use Skeleton and pose (NTU RGB+D, Human3.6M) most often with Action recognition (Kinetics, UCF101, HMDB51) (17), ImageNet (17) and MS COCO (15); it has 12 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.

*What papers use Skeleton and pose (NTU RGB+D, Human3.6M) together with (at least 3 papers; lift 1 = chance)*

| Used with | Type | Papers using both | Lift |
|---|---|---:|---:|
| [Action recognition (Kinetics, UCF101, HMDB51)](https://scholar4ai.com/datasets/action-recognition-kinetics-ucf101-hmdb51.md) | Dataset | 17 | 17.5 |
| [ImageNet](https://scholar4ai.com/datasets/imagenet.md) | Dataset | 17 | 2.2 |
| [MS COCO](https://scholar4ai.com/datasets/ms-coco.md) | Dataset | 15 | 4.8 |
| [YouTube / TikTok](https://scholar4ai.com/datasets/youtube-tiktok.md) | Dataset | 9 | 1.5 |
| [CIFAR-10 / CIFAR-100](https://scholar4ai.com/datasets/cifar-10-cifar-100.md) | Dataset | 7 | 1.5 |
| [MNIST / Fashion-MNIST](https://scholar4ai.com/datasets/mnist-fashion-mnist.md) | Dataset | 7 | 1.9 |
| [BraTS](https://scholar4ai.com/datasets/brats.md) | Dataset | 3 | 3.3 |
| [Cityscapes](https://scholar4ai.com/datasets/cityscapes.md) | Dataset | 3 | 3.0 |
| [DOTA / xView](https://scholar4ai.com/datasets/dota-xview.md) | Dataset | 3 | 14.7 |
| [IMDb](https://scholar4ai.com/datasets/imdb.md) | Dataset | 3 | 3.8 |
| [nuScenes / Waymo Open / Argoverse](https://scholar4ai.com/datasets/nuscenes-waymo-open-argoverse.md) | Dataset | 3 | 3.0 |
| [PASCAL VOC](https://scholar4ai.com/datasets/pascal-voc.md) | Dataset | 3 | 2.7 |

The whole network: https://scholar4ai.com/code/network.md

## Papers

*Papers mentioning Skeleton and pose (NTU RGB+D, Human3.6M) in the last 30 days, newest first.*

| Date | Title | Journal | Authors | Affiliations |
|---|---|---|---|---|
| 2026-10-10 | [LDOFormer: Low-rank and Decorrelation-regularized Transformer for 3D human pose estimation](https://doi.org/10.1016/j.patcog.2026.115065) | [Pattern Recognition](https://scholar4ai.com/journals/pattern-recognition.md) | Yu Zou, Zhigeng Pan, Xianxuan Lin et al. | Nanjing University of Information Science and Technology; Jiangsu Open University |

## Cite this page

Scholar4AI. (2026). Skeleton and pose (NTU RGB+D, Human3.6M). Journal and Conference Research Rankings. Retrieved November 5, 2026, from https://scholar4ai.com/datasets/skeleton-and-pose-ntu-rgb-d-human3-6m

```bibtex
@misc{scholar4ai-datasets-skeleton-and-pose-ntu-rgb-d-human3-6m,
  author = {{Scholar4AI}},
  title = {Skeleton and pose (NTU RGB+D, Human3.6M)},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/datasets/skeleton-and-pose-ntu-rgb-d-human3-6m}},
  urldate = {2026-11-05},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}
```

License: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/).