Science Explorer Interactive view Map

Human Pose and Action Recognition

Human Pose and Action Recognition is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 29k research works in it since 1969. 22.7% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the development and application of deep learning techniques for human action recognition and pose estimation. It covers topics such as spatiotemporal feature learning, convolutional networks, 3D human pose estimation, skeleton-based recognition, and video classification. The research aims to advance the understanding and accurate detection of human actions in various environments.

  • Action Recognition
  • Pose Estimation
  • Spatiotemporal Features
  • Convolutional Networks
  • 3D Human Pose
  • Skeleton-Based Recognition
  • Video Classification
  • Deep Learning
  • Human Activity Analysis
  • Temporal Convolutional Networks
Research works
29k
fractional, since 1969
In the world top 10%
6.6k
per year above
Top-10% rate
22.7%
share of its works in the world top 10%
Growth, 2013–17 → 2018–22
+97%
the tick is no change

Which countries lead Human Pose and Action Recognition research?

By volume, China and India publish the most (4.6k and 1.1k works in 2022–2025).

By volume, 2022–2025

  1. 1 China 4.6k works
  2. 2 India 1.1k works
  3. 3 United States 903 works
  4. 4 Japan 402 works
  5. 5 South Korea 377 works
  6. 6 United Kingdom 275 works
  7. 7 Germany 272 works
  8. 8 Italy 162 works
  9. 9 Canada 158 works
  10. 10 France 153 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 55.0%India: 13.0%United States: 10.7%Japan: 4.8%6 others listed: 16.5%55%largest
China4,640 · 55.0%India1,102 · 13.0%United States903 · 10.7%Japan402 · 4.8%6 others listed1,396 · 16.5%

Shares of the rows listed above, not of the whole node.

Which institutions lead Human Pose and Action Recognition research?

By volume in 2022–2025, Tsinghua University publishes the most Human Pose and Action Recognition research, followed by Beijing University of Posts and Telecommunications and Shanghai Jiao Tong University.

By volume, 2022–2025

  1. 1 Tsinghua University China 95 works
  2. 2 Beijing University of Posts and Telecommunications China 83 works
  3. 3 Shanghai Jiao Tong University China 82 works
  4. 4 Zhejiang University China 76 works
  5. 5 University of Science and Technology of China China 75 works
  6. 6 Chinese Academy of Sciences China 70 works
  7. 7 Peking University China 70 works
  8. 8 Beijing Institute of Technology China 64 works
  9. 9 Sun Yat-sen University China 62 works
  10. 10 University of Electronic Science and Technology of China China 60 works

Who are the leading researchers in Human Pose and Action Recognition?

The most-cited researchers publishing on Human Pose and Action Recognition include Andrew Zisserman, Karen Simonyan and Piotr Dollár.

  1. 1 Andrew Zisserman 25k citations
  2. 2 Karen Simonyan 23k citations
  3. 3 Piotr Dollár 20k citations
  4. 4 Dragomir Anguelov 18k citations
  5. 5 Kaiming He 17k citations
  6. 6 Li Fei-Fei 17k citations
  7. 7 Serge Belongie 14k citations
  8. 8 Xiaogang Wang 13k citations
  9. 9 Jitendra Malik 12k citations
  10. 10 Tsung-Yi Lin 11k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

Where is Human Pose and Action Recognition research done?

The largest centres of Human Pose and Action Recognition research in 2022–2025 are Beijing (China), Shanghai (China), Xi'an (China) and Nanjing (China). Among places with at least 20 works in it, it is an unusually large share of all research in Shenzhen.

Largest cities, 2022–2025

  1. 1 Beijing China 1k works
  2. 2 Shanghai China 345 works
  3. 3 Xi'an China 256 works
  4. 4 Nanjing China 253 works
  5. 5 Hangzhou China 202 works
  6. 6 Wuhan China 202 works
  7. 7 Guangzhou China 201 works
  8. 8 Seoul South Korea 178 works
  9. 9 Shenzhen China 177 works
  10. 10 Tokyo Japan 158 works

Where it is the local speciality

  1. ShenzhenCN · 177.0 works5.1×
← less than its size predictsmore →

Location quotient: how much more of its research is in Human Pose and Action Recognition than the world average.

See Human Pose and Action Recognition on the map

Where is the best place to study Human Pose and Action Recognition?

Among universities, judged by research, Beijing University of Posts and Telecommunications, Air University and University of Science and Technology of China score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%20%40%mean 30.35%fractional works in this node (log) →share in the world top 10% →Beijing University of Posts and Telecommunications: 83, 14.6%Air University: 17, 42.9%University of Science and Technology of China: 75, 23.7%University of Aizu: 9, 39.2%Tsinghua University: 95, 29.7%Peking University: 70, 33.4%Carnegie Mellon University: 32, 37.6%University of Electronic Science and Technology of China: 60, 20.3%Nanyang Technological University: 46, 38.5%Xidian University: 54, 23.6%Air UniversityUniversity of AizuUniversity of Scienc…Beijing University o…
above the meannear itbelow it

One dot per university in the table below. The upper left is the interesting corner: small places doing unusually strong work.

#UniversityScoreTop 10%SpecialisationWorksGrowth
1Beijing University of Posts and Telecommunications China 65.714.6%13.2×83 +200.7%
2Air University Pakistan 59.842.9%28.1×17
3University of Science and Technology of China China 59.223.7%6.2×75 +308.6%
4University of Aizu Japan 56.639.2%20.0×9 +136.0%
5Tsinghua University China 55.729.7%4.8×95 +128.4%
6Peking University China 54.233.4%4.4×70 +125.8%
7Carnegie Mellon University United States 53.737.6%7.8×32 +41.3%
8University of Electronic Science and Technology of China China 53.320.3%5.2×60 +334.7%
9Nanyang Technological University Singapore 53.338.5%5.6×46 -6.9%
10Xidian University China 53.223.6%7.3×54 +100.7%

Universities only. Score blends excellence (30%), specialisation (25%), size (20%), growth (15%) and international reach (10%), 2015–2022; growth compares 2010–14 with 2015–19.

Is Human Pose and Action Recognition research growing?

Output in 2018–2022 was 97% higher than in 2013–2017, peaking in 2025. The fastest-growing topics are Human Pose and Action Recognition.

19801990200020102020
grewheldshrank

The same series as a ribbon — one cell per year, darker for more. The line above answers how much; this answers when.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.