Science Explorer Back to mapMap
Discussion
Topic · Computer Vision and Pattern Recognition

Multimodal Machine Learning Applications

Multimodal Machine Learning Applications is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 22k research works in it since 1975. 9.6% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the development and improvement of visual question answering systems, image captioning techniques, and neural networks for understanding and generating descriptions of images and videos. The research involves semantic reasoning, multimodal fusion, scene graph generation, attention mechanisms, and deep learning approaches to bridge the gap between vision and language.

  • Visual Question Answering
  • Image Captioning
  • Neural Networks
  • Semantic Reasoning
  • Multimodal Fusion
  • Scene Graph Generation
  • Video Description
  • Attention Mechanism
  • Language Understanding
  • Deep Learning
Research works
22k
fractional, since 1975
In the world top 10%
2.1k
per year above
Top-10% rate
9.6%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+106%
the tick is no change
Largest producer
China
56% of the 10 largest, 2022-now
Multimodal Machine Learning Applications

Which countries lead Multimodal Machine Learning Applications research?

By volume, China and the United States publish the most (6.5k and 1.9k works in 2022-now).

By volume, 2022-now

  1. 1 China 6.5k works
  2. 2 United States 1.9k works
  3. 3 India 914 works
  4. 4 South Korea 428 works
  5. 5 United Kingdom 417 works
  6. 6 Japan 376 works
  7. 7 Germany 344 works
  8. 8 Australia 269 works
  9. 9 Singapore 238 works
  10. 10 Italy 230 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: 55.8%United States: 16.4%India: 7.9%South Korea: 3.7%6 others listed: 16.2%56%largest
China6,451 · 55.8%United States1,890 · 16.4%India914 · 7.9%South Korea428 · 3.7%6 others listed1,873 · 16.2%

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

Which institutions lead Multimodal Machine Learning Applications research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Multimodal Machine Learning Applications research, followed by Tsinghua University and University of Science and Technology of China.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 297 works
  2. 2 Tsinghua UniversityChina 167 works
  3. 3 University of Science and Technology of ChinaChina 132 works
  4. 4 Peking UniversityChina 131 works
  5. 5 University of Electronic Science and Technology of ChinaChina 120 works
  6. 6 Zhejiang UniversityChina 120 works
  7. 7 Beijing University of Posts and TelecommunicationsChina 117 works
  8. 8 Shanghai Jiao Tong UniversityChina 117 works
  9. 9 Harbin Institute of TechnologyChina 110 works
  10. 10 University of Chinese Academy of SciencesChina 103 works

Who are the leading researchers in Multimodal Machine Learning Applications?

The most-cited researchers publishing on Multimodal Machine Learning Applications include Kaiming He, Yoshua Bengio and Geoffrey E. Hinton.

  1. 1 Kaiming He Israel 562k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Geoffrey E. Hinton Canada 454k citations
  4. 4 Ross Girshick Israel 356k citations
  5. 5 Xiangyu Zhang 327k citations
  6. 6 Jian Sun 281k citations
  7. 7 Xiaogang Wang China 260k citations
  8. 8 Yann LeCun United States 256k citations
  9. 9 Andrew Zisserman United Kingdom 255k citations
  10. 10 Li Fei-Fei United States 225k citations

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

What are the most cited papers in Multimodal Machine Learning Applications?

The most cited paper in Multimodal Machine Learning Applications is "Exploiting Generative AI to Scale up Intelligent Tutoring Systems" (Jakubův, Jan, Chvalovský, Karel, Goertzel, Zarathustra et al., 2023), with 79,061 citations. Next come "ImageNet: A large-scale hierarchical image database" (63,518) and "Microsoft COCO: Common Objects in Context" (43,802).

Most cited papers
#PaperReleasedCitations
1 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
2 ImageNet: A large-scale hierarchical image database Jia Hao Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition Conference paper Jun 2009 63,518
3 Microsoft COCO: Common Objects in Context Tsung-Yi Lin, Michael Maire, Serge Belongie et al. · Lecture notes in computer science Conference paperOpen access 2014 43,802
4 Fully convolutional networks for semantic segmentation Jonathan Long, Evan Shelhamer, Trevor J. Darrell Conference paper Jun 2015 37,703
5 Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Kumar Das et al. Conference paper Oct 2017 23,064
All 97 most cited papers, with filters and sorting

Where is Multimodal Machine Learning Applications research done?

The largest centres of Multimodal Machine Learning Applications research in 2022-now are Beijing (China), Shanghai (China), Xi'an (China) and Shenzhen (China). Among places with at least 20 works in it, it is an unusually large share of all research in San Mateo, Shanghai and Redmond.

Largest cities, 2022-now

  1. 1 BeijingChina 1.5k works
  2. 2 ShanghaiChina 513 works
  3. 3 Xi'anChina 298 works
  4. 4 ShenzhenChina 289 works
  5. 5 HangzhouChina 287 works
  6. 6 NanjingChina 281 works
  7. 7 GuangzhouChina 277 works
  8. 8 WuhanChina 244 works
  9. 9 SingaporeSingapore 238 works
  10. 10 SeoulSouth Korea 232 works

Where it is the local speciality

  1. San MateoUS · 22.2 works30×
  2. Shanghai30.3 works17×
  3. RedmondUS · 20.1 works16×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Multimodal Machine Learning Applications than the world average.

See Multimodal Machine Learning Applications on the map

Where is the best place to study Multimodal Machine Learning Applications?

Among universities, judged by research, Nanyang Technological University, Mohamed bin Zayed University of Artificial Intelligence and National University of Singapore 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%10%20%mean 17.03%fractional works in this field (log) →share of work in the world top 10% →Mohamed bin Zayed Un…Nanyang Technologica…University of Hong K…National University …
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.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Nanyang Technological UniversitySingapore 82.020.5%9.0×83 +83.6%
2Mohamed bin Zayed University of Artificial IntelligenceUnited Arab Emirates 78.523.1%49.0×23 +1262.5%
3National University of SingaporeSingapore 76.216.8%5.9×82 +146.4%
4University of Hong KongChina 75.518.0%5.0×54 +257.3%
5Tsinghua UniversityChina 73.314.0%6.2×167 +72.3%
6Chinese University of Hong KongChina 72.017.0%4.9×41 +49.4%
7Hong Kong University of Science and TechnologyChina 71.914.7%11.2×54 +161.0%
8Xidian UniversityChina 71.617.1%10.0×85 +179.9%
9University of Science and Technology of ChinaChina 69.411.6%9.6×132 +122.0%
10Northwestern Polytechnical UniversityChina 68.217.5%4.9×65 +146.2%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Multimodal Machine Learning Applications, country by country

Is Multimodal Machine Learning Applications research growing?

Output in 2022-2025 was 106% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Multimodal Machine Learning Applications.

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 Multimodal Machine Learning Applications as a percentage of every work published that year, 0.038% in 2024.

still counting0.025%0.050%0.075%Multimodal Machine Learning Applications0.060% in 202519801990200020102020

Fractional works of Multimodal Machine Learning Applications 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%Multimodal Machine Learning Applications9.5% in 202520102020

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.

Discussion

Ask a question or share a note about Multimodal Machine Learning Applications. Posts are plain text and can be reported.