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

Video Analysis and Summarization

Video Analysis and Summarization is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 30k research works in it since 1951. 9.8% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the automatic analysis and summarization of video content, covering topics such as shot boundary detection, user attention models, semantic analysis, key frame extraction, event detection, and the application of these techniques to soccer videos. It also explores the use of the MPEG-7 standard and content-based retrieval methods in video summarization.

  • Video Summarization
  • Content-Based Retrieval
  • Shot Boundary Detection
  • User Attention Model
  • MPEG-7 Standard
  • Semantic Analysis
  • Key Frame Extraction
  • Event Detection
  • Soccer Video
  • Multimodal Indexing
Research works
30k
fractional, since 1951
In the world top 10%
3k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+31%
the tick is no change
Largest producer
China
48% of the 10 largest, 2022-now
Video Analysis and Summarization

Which countries lead Video Analysis and Summarization research?

By volume, China and India publish the most (2.1k and 730 works in 2022-now).

By volume, 2022-now

  1. 1 China 2.1k works
  2. 2 India 730 works
  3. 3 United States 557 works
  4. 4 Japan 279 works
  5. 5 South Korea 177 works
  6. 6 United Kingdom 135 works
  7. 7 Türkiye 127 works
  8. 8 Germany 122 works
  9. 9 Canada 88 works
  10. 10 ?? 85 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: 48.0%India: 16.5%United States: 12.6%Japan: 6.3%6 others listed: 16.6%48%largest
China2,119 · 48.0%India730 · 16.5%United States557 · 12.6%Japan279 · 6.3%6 others listed734 · 16.6%

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

Which institutions lead Video Analysis and Summarization research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Video Analysis and Summarization research, followed by University of Science and Technology of China and Peking University.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 69 works
  2. 2 University of Science and Technology of ChinaChina 38 works
  3. 3 Peking UniversityChina 38 works
  4. 4 Tsinghua UniversityChina 37 works
  5. 5 Zhejiang UniversityChina 36 works
  6. 6 Beijing University of Posts and TelecommunicationsChina 32 works
  7. 7 Shanghai Jiao Tong UniversityChina 29 works
  8. 8 SRM Institute of Science and TechnologyIndia 28 works
  9. 9 University of Electronic Science and Technology of ChinaChina 28 works
  10. 10 Fudan UniversityChina 26 works

Who are the leading researchers in Video Analysis and Summarization?

The most-cited researchers publishing on Video Analysis and Summarization include Yoshua Bengio, Geoffrey E. Hinton and Xiangyu Zhang.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Geoffrey E. Hinton Canada 454k citations
  3. 3 Xiangyu Zhang 327k citations
  4. 4 Xiaogang Wang China 260k citations
  5. 5 Yann LeCun United States 256k citations
  6. 6 Andrew Zisserman United Kingdom 255k citations
  7. 7 Li Fei-Fei United States 225k citations
  8. 8 Rafael Lozano United States 224k citations
  9. 9 Kai You Wang China 224k citations
  10. 10 Trevor J. Darrell United States 206k 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 Video Analysis and Summarization?

The most cited paper in Video Analysis and Summarization is "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories" (Svetlana Lazebnik, C. Schmid, Jean Ponce, 2006), with 7,972 citations. Next come "Video Google: a text retrieval approach to object matching in videos" (6,474) and "Content-based image retrieval at the end of the early years" (6,087).

Most cited papers
#PaperReleasedCitations
1 Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories Svetlana Lazebnik, C. Schmid, Jean Ponce Conference paperOpen access 10 Jul 2006 7,972
2 Video Google: a text retrieval approach to object matching in videos Sivic, Zisserman Conference paper 2003 6,474
3 Content-based image retrieval at the end of the early years Arnold W. M. Smeulders, Marcel Worring, Simone Santini et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence 2000 6,087
4 The eyes have it: a task by data type taxonomy for information visualizations Ben Shneiderman Conference paper 23 Dec 2002 4,586
5 Simple online and realtime tracking Alex Bewley, Zongyuan Ge, Lionel Ott et al. Conference paperOpen access 17 Aug 2016 4,156
All 99 most cited papers, with filters and sorting

Where is Video Analysis and Summarization research done?

The largest centres of Video Analysis and Summarization research in 2022-now are Beijing (China), Shanghai (China), Tokyo (Japan) and Xi'an (China). Among places with at least 20 works in it, it is an unusually large share of all research in San Jose.

Largest cities, 2022-now

  1. 1 BeijingChina 429 works
  2. 2 ShanghaiChina 152 works
  3. 3 TokyoJapan 107 works
  4. 4 Xi'anChina 95 works
  5. 5 HangzhouChina 92 works
  6. 6 WuhanChina 91 works
  7. 7 GuangzhouChina 90 works
  8. 8 SeoulSouth Korea 85 works
  9. 9 ShenzhenChina 79 works
  10. 10 NanjingChina 77 works

Where it is the local speciality

  1. San JoseUS · 22.0 works12×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Video Analysis and Summarization than the world average.

See Video Analysis and Summarization on the map

Where is the best place to study Video Analysis and Summarization?

Among universities, judged by research, Hong Kong University of Science and Technology, Peking University 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%20%40%mean 23.52%fractional works in this field (log) →share of work in the world top 10% →Hong Kong University…National University …Peking 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.

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
1Hong Kong University of Science and TechnologyChina 77.534.6%6.8×14 +121.6%
2Peking UniversityChina 77.425.2%3.9×38 +69.5%
3National University of SingaporeSingapore 74.127.7%3.8×22 +84.7%
4University of Science and Technology of ChinaChina 72.216.4%6.7×38 +148.9%
5Tsinghua UniversityChina 70.222.7%3.3×37 +39.7%
6Zhejiang UniversityChina 69.521.4%2.7×36 +46.2%
7Nanyang Technological UniversitySingapore 64.621.0%4.9×19 +69.7%
8Harbin Institute of TechnologyChina 64.225.6%3.0×24 +119.6%
9University of Hong KongChina 62.623.8%3.0×14 +385.5%
10Fudan UniversityChina 62.416.8%3.5×26 +131.5%

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 Video Analysis and Summarization, country by country

Is Video Analysis and Summarization research growing?

Output in 2022-2025 was 31% higher than in 2018-2021, peaking in 2024. The fastest-growing topics are Video Analysis and Summarization.

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 Video Analysis and Summarization as a percentage of every work published that year, 0.029% in 2024.

still counting0.020%0.040%0.060%Video Analysis and Summarization0.026% in 202519801990200020102020

Fractional works of Video Analysis and Summarization 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%Video Analysis and Summarization9.6% 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 Video Analysis and Summarization. Posts are plain text and can be reported.