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

Digital Media Forensic Detection

Digital Media Forensic Detection is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 21k research works in it since 1954. 9.8% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the detection and identification of digital image forgeries, including techniques such as copy-move forgery detection, sensor pattern noise analysis, JPEG compression history estimation, camera model identification, splicing detection, and tampering localization. The papers also explore the application of deep learning methods for image forensics and the detection of inconsistencies in image manipulation.

  • Image Forgery Detection
  • Digital Forensics
  • Copy-Move Forgery
  • Sensor Pattern Noise
  • JPEG Compression
  • Camera Model Identification
  • Deep Learning
  • Splicing Detection
  • Tampering Localization
  • Resampling Detection
Research works
21k
fractional, since 1954
In the world top 10%
2.1k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+57%
the tick is no change
Largest producer
China
43% of the 10 largest, 2022-now
Digital Media Forensic Detection

Which countries lead Digital Media Forensic Detection research?

By volume, China and India publish the most (2.5k and 1.8k works in 2022-now).

By volume, 2022-now

  1. 1 China 2.5k works
  2. 2 India 1.8k works
  3. 3 United States 567 works
  4. 4 South Korea 185 works
  5. 5 United Kingdom 155 works
  6. 6 Italy 141 works
  7. 7 Indonesia 134 works
  8. 8 Iraq 130 works
  9. 9 Taiwan 127 works
  10. 10 Germany 116 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: 42.9%India: 30.5%United States: 9.7%South Korea: 3.2%6 others listed: 13.7%43%largest
China2,511 · 42.9%India1,786 · 30.5%United States567 · 9.7%South Korea185 · 3.2%6 others listed803 · 13.7%

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

Which institutions lead Digital Media Forensic Detection research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Digital Media Forensic Detection research, followed by SRM Institute of Science and Technology and Beijing University of Posts and Telecommunications.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 84 works
  2. 2 SRM Institute of Science and TechnologyIndia 54 works
  3. 3 Beijing University of Posts and TelecommunicationsChina 52 works
  4. 4 Vellore Institute of Technology UniversityIndia 43 works
  5. 5 Amrita Vishwa VidyapeethamIndia 40 works
  6. 6 Shanghai Jiao Tong UniversityChina 39 works
  7. 7 University of Science and Technology of ChinaChina 38 works
  8. 8 Fudan UniversityChina 33 works
  9. 9 Sun Yat-sen UniversityChina 32 works
  10. 10 Centre National de la Recherche ScientifiqueFrance 31 works

Who are the leading researchers in Digital Media Forensic Detection?

The most-cited researchers publishing on Digital Media Forensic Detection include M. Shoji, Yoshua Bengio and Geoffrey E. Hinton.

  1. 1 M. Shoji Japan 806k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Geoffrey E. Hinton Canada 454k citations
  4. 4 Xiangyu Zhang 327k citations
  5. 5 Xiaogang Wang China 260k citations
  6. 6 Yann LeCun United States 256k citations
  7. 7 Andrew Zisserman United Kingdom 255k citations
  8. 8 Li Fei-Fei United States 225k 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 Digital Media Forensic Detection?

The most cited paper in Digital Media Forensic Detection is "SSD: Single Shot MultiBox Detector" (Wei Liu, Dragomir Anguelov, Dumitru Erhan et al., 2016), with 21,849 citations. Next come "GAN（Generative Adversarial Nets）" (21,691) and "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks" (6,972).

Most cited papers
#PaperReleasedCitations
1 SSD: Single Shot MultiBox Detector Wei Liu, Dragomir Anguelov, Dumitru Erhan et al. · Lecture notes in computer science Conference paperOpen access 2016 21,849
2 GAN（Generative Adversarial Nets） 柴田 淳司 · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics Open access 15 Oct 2017 21,691
3 Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec Radford, Luke Metz, Soumith Chintala · arXiv (Cornell University) PreprintOpen access 19 Nov 2015 6,972
4 Least Squares Generative Adversarial Networks Xudong Mao, Qing Li, Haoran Xie et al. Conference paper Oct 2017 5,285
5 High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu et al. Conference paper Jun 2018 4,526
All 99 most cited papers, with filters and sorting

Where is Digital Media Forensic Detection research done?

The largest centres of Digital Media Forensic Detection research in 2022-now are Beijing (China), Shanghai (China), Chennai (India) and Nanjing (China).

Largest cities, 2022-now

  1. 1 BeijingChina 438 works
  2. 2 ShanghaiChina 185 works
  3. 3 ChennaiIndia 154 works
  4. 4 NanjingChina 138 works
  5. 5 Xi'anChina 135 works
  6. 6 GuangzhouChina 135 works
  7. 7 SeoulSouth Korea 103 works
  8. 8 ChengduChina 94 works
  9. 9 BengaluruIndia 89 works
  10. 10 New DelhiIndia 89 works
See Digital Media Forensic Detection on the map

Where is the best place to study Digital Media Forensic Detection?

Among universities, judged by research, University of Science and Technology of China, National Institute of Technology Patna and Nanyang Technological 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 18.81%fractional works in this field (log) →share of work in the world top 10% →National Institute o…Nanyang Technologica…University of Scienc…SRM Institute of Sci…
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
1University of Science and Technology of ChinaChina 66.021.1%4.8×38 +16.5%
2National Institute of Technology PatnaIndia 65.936.4%12.0×11 +128.1%
3Nanyang Technological UniversitySingapore 62.121.2%4.3×23 +115.1%
4SRM Institute of Science and TechnologyIndia 60.09.1%8.0×54 +257.2%
5Shenzhen UniversityChina 60.013.6%6.0×29 +28.1%
6Beijing University of Posts and TelecommunicationsChina 59.39.3%12.2×52 +50.0%
7Shanghai Jiao Tong UniversityChina 58.719.4%2.0×39 +57.2%
8Nanjing University of Information Science and TechnologyChina 58.511.6%10.3×28 +30.9%
9Fudan UniversityChina 57.816.3%3.1×33 +124.9%
10Beijing Jiaotong UniversityChina 56.030.1%5.3×22 +1.0%

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 Digital Media Forensic Detection, country by country

Is Digital Media Forensic Detection research growing?

Output in 2022-2025 was 57% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Digital Media Forensic 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 Digital Media Forensic Detection as a percentage of every work published that year, 0.034% in 2024.

still counting0.020%0.040%Digital Media Forensic Detection0.034% in 202519801990200020102020

Fractional works of Digital Media Forensic 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%Digital Media Forensic Detection9.8% 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 Digital Media Forensic Detection. Posts are plain text and can be reported.