Science Explorer Back to mapMap
Discussion
Subfield · Computer Science

Computer Vision and Pattern Recognition research

Computer Vision and Pattern Recognition is a subfield of Computer Science. Science Explorer counts 1.1M research works in it since 1950. 9.8% of them reached the world's top 10% most cited for their field and year.

In short: computerized information extraction from images.

Research works
1.1M
fractional, since 1950
In the world top 10%
109k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Topics
35
Growth, 2018-21 → 2022-25
+39%
the tick is no change
Largest producer
China
53% of the 10 largest, 2022-now

What is Computer Vision and Pattern Recognition research about, and what is growing?

By the world's output in 2021-25, its most used keywords are Deep Learning, Convolutional Neural Networks, Neural Networks, Convolutional Networks, Computer Vision, Image Recognition. Gaining share since 2011-15: Image Recognition, Object Detection, Image Captioning, Visual Question Answering, Computer Vision. Losing share: Local Binary Patterns, Depth Estimation, Stereo Vision, Hyperspectral Imaging.

▲ gaining share of this field◆ holding its share▼ losing share

Size is the world's fractional works in 2021-25 in the topics tagged with each word; colour compares the word's share of this field with 2011-15. Each links to the topic it comes from most.

All 40 words, with their numbers
  1. Deep Learning201k▲ 1.25×18 topics
  2. Convolutional Neural Networks88k▲ 1.75×6 topics
  3. Neural Networks46k▲ 2.0×5 topics
  4. Convolutional Networks38k◆ 0.95×3 topics
  5. Computer Vision37k▲ 3.6×2 topics
  6. Image Recognition33k▲ 11×1 topic
  7. Object Detection33k▲ 11×1 topic
  8. Unsupervised Learning24k◆ 0.96×2 topics
  9. Pose Estimation24k▲ 1.70×2 topics
  10. Image Processing22k▲ 1.88×3 topics
  11. Machine Learning21k▼ 0.69×3 topics
  12. Generative Adversarial Networks21k▲ 2.1×2 topics
  13. Face Recognition21k◆ 0.94×2 topics
  14. Sparse Representation21k◆ 0.87×2 topics
  15. Optimal Motion Planning20k▲ 1.19×1 topic
  16. Sampling-Based Algorithms20k▲ 1.19×1 topic
  17. Object Tracking19k▲ 1.26×1 topic
  18. Visual Tracking19k▲ 1.26×1 topic
  19. Local Binary Patterns18k▼ 0.51×2 topics
  20. Feature Matching17k▼ 0.66×1 topic
  21. Local Descriptors17k▼ 0.66×1 topic
  22. Medical Image Analysis16k◆ 0.98×2 topics
  23. Hyperspectral Imaging16k▼ 0.60×2 topics
  24. Image Segmentation15k▼ 0.75×2 topics
  25. Depth Estimation14k▼ 0.58×1 topic
  26. Stereo Vision14k▼ 0.58×1 topic
  27. Action Recognition13k▲ 1.82×1 topic
  28. Spatiotemporal Features13k▲ 1.82×1 topic
  29. Image Captioning13k▲ 6.5×1 topic
  30. Visual Question Answering13k▲ 6.5×1 topic
  31. Education13k▲ 1.46×1 topic
  32. Technology13k▲ 1.46×1 topic
  33. Image Denoising12k▼ 0.68×1 topic
  34. Sparse Representations12k▼ 0.68×1 topic
  35. Feature Extraction11k▲ 2.9×2 topics
  36. Age Estimation11k▲ 1.57×1 topic
  37. Facial Landmark Detection11k▲ 1.57×1 topic
  38. Image11k▲ 1.25×1 topic
  39. Super-Resolution11k▲ 1.25×1 topic
  40. Chaos11k▼ 0.83×1 topic

Which countries lead Computer Vision and Pattern Recognition research?

On research quality in 2022-now, China, the United States and the United Kingdom rank highest in Computer Vision and Pattern Recognition. By volume, China and India publish the most (125k and 37k works in 2022-now).

By research quality, 2022-now

  1. 1 China #2 all time 1.10× citation excellence · 0.84× journals · 100% breadth 11.5% top 10% · 110k works
  2. 2 United States #1 all time 1.12× citation excellence · 1.76× journals · 100% breadth 11.6% top 10% · 24k works
  3. 3 United Kingdom #4 all time 1.32× citation excellence · 1.46× journals · 100% breadth 13.2% top 10% · 6.5k works
  4. 4 Germany #3 all time 1.05× citation excellence · 1.51× journals · 100% breadth 9.4% top 10% · 6.9k works
  5. 5 Singapore #5 all time 1.83× citation excellence · 1.67× journals · 100% breadth 20.2% top 10% · 2k works
  6. 6 Australia #8 all time 1.60× citation excellence · 1.21× journals · 100% breadth 16.3% top 10% · 3.2k works
  7. 7 Switzerland #6 all time 1.39× citation excellence · 1.89× journals · 100% breadth 14.7% top 10% · 1.3k works
  8. 8 South Korea #10 all time 0.97× citation excellence · 0.94× journals · 100% breadth 10.2% top 10% · 7.3k works
  9. 9 Canada #9 all time 1.11× citation excellence · 1.19× journals · 100% breadth 11.2% top 10% · 3.9k works
  10. 10 France #7 all time 0.75× citation excellence · 1.27× journals · 100% breadth 6.4% top 10% · 4.5k works

The track on each row is that row's top-10% rate. The ranking itself is the quality score, which compares the rate with what each place's own topics predict, adds its share of papers in the Nature Index journals, and counts output and breadth too.

Of 66 countries ranked in Computer Vision and Pattern Recognition. Ranked on the quality score for 2022-now; the bracket is the all-time rank.

All countries ranked in Computer Vision and Pattern Recognition

By volume, 2022-now

  1. 1 China 125k works
  2. 2 India 37k works
  3. 3 United States 28k works
  4. 4 Japan 8.2k works
  5. 5 South Korea 8.2k works
  6. 6 Germany 7.7k works
  7. 7 United Kingdom 7.4k works
  8. 8 France 5k works
  9. 9 Italy 4.9k works
  10. 10 Indonesia 4.7k 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: 53.1%India: 15.5%United States: 11.8%Japan: 3.5%6 others listed: 16.1%53%largest
China125k · 53.1%India37k · 15.5%United States28k · 11.8%Japan8,235 · 3.5%6 others listed38k · 16.1%

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

Which institutions lead Computer Vision and Pattern Recognition research?

Chinese Academy of Sciences (China) ranks first in Computer Vision and Pattern Recognition on research quality in 2022-now, followed by Tsinghua University and Nanyang Technological University.

By research quality, 2022-now

  1. 1 Chinese Academy of Sciences China · Beijing · #1 all time 12.4% top 10% · 3.9k works
  2. 2 Tsinghua University China · Beijing · #5 all time 18.1% top 10% · 1.7k works
  3. 3 Nanyang Technological University Singapore · Singapore · #6 all time 23.7% top 10% · 799 works
  4. 4 Alphabet (United States) United States · Mountain View · #17 all time 29.7% top 10% · 439 works
  5. 5 University of Science and Technology of China China · Hefei · #10 all time 16.4% top 10% · 1.4k works
  6. 6 ETH Zurich Switzerland · Zurich · #3 all time 24.3% top 10% · 324 works
  7. 7 Peking University China · Beijing · #12 all time 17.5% top 10% · 1.1k works
  8. 8 Shanghai Jiao Tong University China · Shanghai · #15 all time 14.6% top 10% · 1.8k works
  9. 9 Zhejiang University China · Hangzhou · #24 all time 16.5% top 10% · 1.5k works
  10. 10 Hong Kong University of Science and Technology China · Hong Kong · #14 all time 23.4% top 10% · 462 works

The track on each row is that row's top-10% rate. The ranking itself is the quality score, which compares the rate with what each place's own topics predict, adds its share of papers in the Nature Index journals, and counts output and breadth too.

Of 963 institutions above the floor of 40 fractional works in Computer Vision and Pattern Recognition.

Top 100 Computer Vision and Pattern Recognition institutions

Who are the leading researchers in Computer Vision and Pattern Recognition?

Counting only their work in Computer Vision and Pattern Recognition, Luc Van Gool, Dacheng Tao and Shuicheng Yan have the most papers in the world top 10% for their subfield and year beyond the 10% expected.

  1. 1 Luc Van Gool Switzerland · #11,566 worldwide overall 245.1 of 684 papers here in the top 10%
  2. 2 Dacheng Tao Australia · #9,106 worldwide overall 252.7 of 550 papers here in the top 10%
  3. 3 Shuicheng Yan Singapore · #2,993 worldwide overall 198.8 of 442 papers here in the top 10%
  4. 4 Ming–Hsuan Yang United States · #5,070 worldwide overall 199.6 of 381 papers here in the top 10%
  5. 5 Yi Ping Yang Australia · #5,101 worldwide overall 184.1 of 372 papers here in the top 10%
  6. 6 Xuelong Li China · #5,338 worldwide overall 164.5 of 384 papers here in the top 10%
  7. 7 Andrew Zisserman United Kingdom · #2,710 worldwide overall 157.7 of 334 papers here in the top 10%
  8. 8 Xiaogang Wang China · #14,719 worldwide overall 135.0 of 197 papers here in the top 10%
  9. 9 Anil Kumar Jain United States · #5,446 worldwide overall 152.8 of 313 papers here in the top 10%
  10. 10 Huchuan Lu China · #6,031 worldwide overall 142.9 of 305 papers here in the top 10%

Ranked on their work in Computer Vision and Pattern Recognition alone: how many more of their papers here reached the world top 10% for their subfield and year than the 10% expected, among 1,219,546 ranked researchers with a paper here. Each paper counts once, so many strong papers outrank one famous one, and a long record of ordinary papers does not climb. Identities come from OpenAlex author disambiguation, which occasionally merges or splits people.

Top 100 Computer Vision and Pattern Recognition researchers

What are the most cited papers in Computer Vision and Pattern Recognition?

The most cited paper in Computer Vision and Pattern Recognition is "Deep Residual Learning for Image Recognition" (Kaiming He, Xiangyu Zhang, Shaoqing Ren et al., 2016), with 229,585 citations. Next come "Random Forests" (132,956) and "U-Net: Convolutional Networks for Biomedical Image Segmentation" (92,751).

Most cited papers
#PaperReleasedCitations
1 Deep Residual Learning for Image Recognition Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. Conference paperOpen access Jun 2016 229,585
2 Random Forests Leo Breiman · Machine Learning Open access Oct 2001 132,956
3 U-Net: Convolutional Networks for Biomedical Image Segmentation Olaf Ronneberger, Philipp F. Fischer, Thomas Brox · Lecture notes in computer science Conference paperOpen access 2015 92,751
4 Deep learning Yann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature Open access 26 May 2015 84,939
5 Exploiting Generative AI to Scale up Intelligent Tutoring Systems Jakubův, Jan, Chvalovský, Karel, Goertzel, Zarathustra et al. · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) Open access 2023 79,061
All 97 most cited papers, with filters and sorting

Where is Computer Vision and Pattern Recognition research done?

The largest centres of Computer Vision and Pattern Recognition research in 2022-now 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 Chertsey, Cerdanyola del Vallès and Marina del Rey.

Largest cities, 2022-now

  1. 1 BeijingChina 22k works
  2. 2 ShanghaiChina 8.8k works
  3. 3 Xi'anChina 7.1k works
  4. 4 NanjingChina 6.4k works
  5. 5 WuhanChina 5.7k works
  6. 6 GuangzhouChina 4.9k works
  7. 7 HangzhouChina 4.5k works
  8. 8 ChengduChina 4.1k works
  9. 9 ChennaiIndia 4k works
  10. 10 SeoulSouth Korea 3.9k works

Where it is the local speciality

  1. ChertseyGB · 25.6 works19×
  2. Cerdanyola del Vallès37.4 works18×
  3. Marina del ReyUS · 98.1 works16×
  4. Martigny-CombeCH · 52.3 works14×
  5. George TownKY · 40.1 works13×
  6. Ridgefield ParkUS · 55.3 works11×
  7. Bingen am RheinDE · 36.8 works9.9×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Computer Vision and Pattern Recognition than the world average.

See Computer Vision and Pattern Recognition on the map

Computer Vision and Pattern Recognition research by country

The best places for Computer Vision and Pattern Recognition research inside each country, with that country's researchers and world standing.

Where is the best place to study Computer Vision and Pattern Recognition?

Among universities, judged by research, Nanyang Technological University, Tsinghua University and ETH Zurich score highest, combining standing in the field's ranking, citation excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%10%20%mean 18.08%fractional works in this field (log) →share of work in the world top 10% →ETH ZurichNanyang Technologica…Tsinghua UniversityUniversity of Scienc…
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Standingthis field's institution ranking, three quarters all time and a quarter 2022-now
50%
Citation excellenceshare of its work in the world top 10%, 2022-now and all time averaged
20%
Specialisationhow much of its work is in this field, counted up to 10× the world share
5%
Sizeits output in this field, on a log scale
15%
Growthoutput growth, counted from -20% to +20%
5%
Internationalshare of its work with a co-author abroad
5%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreRank in field (all time)Top 10%SpecialisationWorksGrowth
1Nanyang Technological UniversitySingapore 86.7#3 (#6)22.7%4.3×900 +43.0%
2Tsinghua UniversityChina 85.3#2 (#5)17.1%3.1×1,898 +31.5%
3ETH ZurichSwitzerland 83.9#6 (#3)23.0%1.9×353 -4.7%
4University of Science and Technology of ChinaChina 78.8#5 (#10)15.7%5.1×1,568 +58.3%
5Hong Kong University of Science and TechnologyChina 77.4#10 (#14)21.8%5.0×535 +85.0%
6Stanford UniversityUnited States 76.9#13 (#4)19.0%1.0×371 -4.0%
7Peking UniversityChina 75.5#7 (#12)16.6%2.4×1,257 +20.8%
8National University of SingaporeSingapore 73.7#18 (#13)18.1%2.1×650 +45.3%
9University of Chinese Academy of SciencesChina 73.1#15 (#7)12.6%2.8×1,177 +11.7%
10Shanghai Jiao Tong UniversityChina 73.0#8 (#15)14.2%2.7×2,002 +36.2%

Universities only. The score blends standing (50%), citation excellence (20%), size (15%), specialisation (5%), growth (5%), international reach (5%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise. Standing is the score in this field's institution ranking, three quarters over all time and a quarter 2022-now; excellence averages the two windows too. Four years alone undercount fields such as AI, where many conference and arXiv papers from 2022 on carry no affiliation in the data.

Every institution in Computer Vision and Pattern Recognition, country by country

Is Computer Vision and Pattern Recognition research growing?

Output in 2022-2025 was 39% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Advanced Neural Network Applications, Face recognition and analysis and Robotic Path Planning Algorithms.

still counting19801990200020102020
grewheldshrank

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

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Computer Vision and Pattern Recognition as a percentage of every work published that year, 1.3% in 2024.

still counting1.0%2.0%Computer Vision and Pattern Recognition1.3% in 202519801990200020102020

Fractional works of Computer Vision and Pattern Recognition over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Computer Vision and Pattern Recognition9.7% in 2025200020102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

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.

  1. Advanced Neural Network Applications+120%
  2. Face recognition and analysis+59%
  3. Robotic Path Planning Algorithms+55%
  4. Human Pose and Action Recognition+53%
  5. Image Enhancement Techniques+51%
  6. Image Processing and 3D Reconstruction+50%
← shrinkingno changegrowing →

Growth in output from 2018-21 to 2022-25. Every topic is a page of its own.

What does Computer Vision and Pattern Recognition include?

Advanced Vision and Imag…67kAdvanced Vision and Imaging: 67k fractional worksAdvanced Image and Video…65kAdvanced Image and Video Retrieval Techniques: 65k fractional worksRobotic Path Planning Algorithms: 60k fractional worksImage and Signal Denoising Methods: 59k fractional worksAdvanced Neural Network Applications: 52k fractional worksImage Retrieval and Classification Techniques: 49k fractional worksVideo Surveillance and Tracking Methods: 47k fractional worksOptical measurement and interference techniques: 44k fractional worksMedical Image Segmentation Techniques: 43k fractional worksFace and Expression Recognition: 42k fractional worksChaos-based Image/Signal Encryption: 37k fractional worksContext-Aware Activity Recognition Systems: 36k fractional works

Area is fractional works in that topic. Every name below is a page of its own.

Share who leads Computer Vision and Pattern Recognition

Who leads Computer Vision and Pattern Recognition, on Science Explorer

A card with the countries and institutions that lead Computer Vision and Pattern Recognition, for a post or a slide.

Download the card

1200 × 630 PNG, sized for social posts, drawn from the latest snapshot.

The leading institutions' badges6Each links to that institution's page and updates with every snapshot

Questions people ask

Who leads computer vision research?

Chinese Academy of Sciences (China) ranks first in Computer Vision and Pattern Recognition on research quality in 2022-now, followed by Tsinghua University and Nanyang Technological University. On research quality in 2022-now, China, the United States and the United Kingdom rank highest in Computer Vision and Pattern Recognition. By volume, China and India publish the most (125k and 37k works in 2022-now).

All 1,273 questions in the Question Catalogue

Discussion

Ask a question or share a note about Computer Vision and Pattern Recognition. Keep it to the research: no personal attacks, advertising or links. Any reader can report a post, which collapses it for everyone until it is opened.