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

Visual Attention and Saliency Detection

Visual Attention and Saliency Detection is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 17k research works in it since 1953. 9.8% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on computational modeling and detection of visual saliency, including topics such as saliency detection, visual attention, deep learning for salient object detection, analysis of eye movements, image and video segmentation, and the interplay between bottom-up and top-down attention mechanisms.

  • Saliency Detection
  • Visual Attention
  • Salient Object Detection
  • Deep Learning
  • Eye Movements
  • Image Segmentation
  • Video Object Segmentation
  • Neural Networks
  • Bottom-Up Attention
  • Top-Down Attention
Research works
17k
fractional, since 1953
In the world top 10%
1.6k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+29%
the tick is no change
Largest producer
China
61% of the 10 largest, 2022-now
Visual Attention and Saliency Detection

Which countries lead Visual Attention and Saliency Detection research?

By volume, China and the United States publish the most (2.8k and 588 works in 2022-now).

By volume, 2022-now

  1. 1 China 2.8k works
  2. 2 United States 588 works
  3. 3 India 248 works
  4. 4 Germany 177 works
  5. 5 United Kingdom 175 works
  6. 6 Japan 169 works
  7. 7 South Korea 149 works
  8. 8 Canada 99 works
  9. 9 France 84 works
  10. 10 Italy 78 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: 61.1%United States: 12.9%India: 5.5%Germany: 3.9%6 others listed: 16.6%61%largest
China2,776 · 61.1%United States588 · 12.9%India248 · 5.5%Germany177 · 3.9%6 others listed755 · 16.6%

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

Which institutions lead Visual Attention and Saliency Detection research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Visual Attention and Saliency Detection research, followed by Shanghai Jiao Tong University and Xidian University.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 79 works
  2. 2 Shanghai Jiao Tong UniversityChina 50 works
  3. 3 Xidian UniversityChina 41 works
  4. 4 Tsinghua UniversityChina 39 works
  5. 5 Tianjin UniversityChina 36 works
  6. 6 Beihang UniversityChina 34 works
  7. 7 Zhejiang UniversityChina 34 works
  8. 8 Dalian University of TechnologyChina 33 works
  9. 9 Centre National de la Recherche ScientifiqueFrance 31 works
  10. 10 Harbin Institute of TechnologyChina 30 works

Who are the leading researchers in Visual Attention and Saliency Detection?

The most-cited researchers publishing on Visual Attention and Saliency Detection include Kaiming He, Yoshua Bengio and Ross Girshick.

  1. 1 Kaiming He Israel 562k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Ross Girshick Israel 356k citations
  4. 4 Karl John Friston United Kingdom 310k citations
  5. 5 Jian Sun 281k citations
  6. 6 Xiaogang Wang China 260k citations
  7. 7 Yann LeCun United States 256k citations
  8. 8 Andrew Zisserman United Kingdom 255k citations
  9. 9 Li Fei-Fei United States 225k citations
  10. 10 Kai You Wang China 224k 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 Visual Attention and Saliency Detection?

The most cited paper in Visual Attention and Saliency Detection is "Image quality assessment: from error visibility to structural similarity" (Zhou Wang, Alan Conrad Bovik, Hamid R. Sheikh et al., 2004), with 58,409 citations. Next come "Rapid object detection using a boosted cascade of simple features" (18,370) and "A feature-integration theory of attention" (12,545).

Most cited papers
#PaperReleasedCitations
1 Image quality assessment: from error visibility to structural similarity Zhou Wang, Alan Conrad Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing Apr 2004 58,409
2 Rapid object detection using a boosted cascade of simple features Paul A. Viola, Michael Jones Conference paper 24 Aug 2005 18,370
3 A feature-integration theory of attention Anne Treisman, Garry A. Gelade · Cognitive Psychology 1980 12,545
4 A model of saliency-based visual attention for rapid scene analysis Laurent Itti, Christof Koch, Ernst Niebur · IEEE Transactions on Pattern Analysis and Machine Intelligence 1998 11,422
5 A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics David Martín, Charless C. Fowlkes, Doron Tal et al. Conference paper 13 Nov 2002 8,139
All 99 most cited papers, with filters and sorting

Where is Visual Attention and Saliency Detection research done?

The largest centres of Visual Attention and Saliency Detection 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 Guilin and Dalian.

Largest cities, 2022-now

  1. 1 BeijingChina 436 works
  2. 2 ShanghaiChina 220 works
  3. 3 Xi'anChina 167 works
  4. 4 NanjingChina 144 works
  5. 5 HangzhouChina 128 works
  6. 6 WuhanChina 113 works
  7. 7 TianjinChina 103 works
  8. 8 ChengduChina 83 works
  9. 9 SeoulSouth Korea 81 works
  10. 10 GuangzhouChina 80 works

Where it is the local speciality

  1. GuilinCN · 21.1 works4.9×
  2. DalianCN · 62.3 works4.6×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Visual Attention and Saliency Detection than the world average.

See Visual Attention and Saliency Detection on the map

Where is the best place to study Visual Attention and Saliency Detection?

Among universities, judged by research, Nanyang Technological University, Dalian University of Technology and Nankai University 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 24.14%fractional works in this field (log) →share of work in the world top 10% →City University of H…Nanyang Technologica…Dalian University of…Nankai 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 78.028.7%7.0×26 +59.2%
2Dalian University of TechnologyChina 75.723.4%7.6×33 +13.7%
3Nankai UniversityChina 74.723.1%7.7×24 +76.2%
4City University of Hong KongChina 74.431.3%6.4×17 +7.2%
5Anhui UniversityChina 69.721.8%12.7×26 +31.3%
6Xidian UniversityChina 67.619.1%12.4×41 +8.5%
7Dalian Minzu UniversityChina 66.031.7%52.1×11 +437.9%
8Shanghai Jiao Tong UniversityChina 65.615.0%3.8×50 +25.0%
9Hong Kong Polytechnic UniversityChina 63.821.9%4.1×16 +159.8%
10Hong Kong University of Science and TechnologyChina 63.625.4%6.2×12 +42.7%

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 Visual Attention and Saliency Detection, country by country

Is Visual Attention and Saliency Detection research growing?

Output in 2022-2025 was 29% higher than in 2018-2021, peaking in 2023. The fastest-growing topics are Visual Attention and Saliency Detection.

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 Visual Attention and Saliency Detection as a percentage of every work published that year, 0.019% in 2024.

still counting0.010%0.020%0.030%Visual Attention and Saliency Detection0.020% in 202519801990200020102020

Fractional works of Visual Attention and Saliency Detection 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%Visual Attention and Saliency Detection9.9% 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.

Discussion

Ask a question or share a note about Visual Attention and Saliency Detection. Posts are plain text and can be reported.