An Overview of Recent Work in Multimedia Forensics
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
In this paper, we review recent work in media forensics for digital images, video, audio, and documents.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2020) · arXiv · doi:10.48550/arxiv.2012.09841 · Cited by 2,514
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953 · cited 1×
“Likelihood-based diffusion models [12] and score-based generative models [13,14] can also create high-quality synthetic images with sharp edges and fine details.”
BackgroundStacked Cross Attention for Image-Text Matching
Lee, K.-H., Chen, X., Hua, G., Hu, H., & He, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_13 · Cited by 1,402
A Scale for the Measurement of the Psychological Magnitude Pitch
Stevens, S. S., Volkmann, J., & Newman, E. B. (1937) · The Journal of the Acoustical Society of America · doi:10.1121/1.1915893 · Cited by 1,107 · cited 1×
“A melspectrogram refers to a spectrogram with frequencies in the mel scale [56].”
Media Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979
Vaccari, C., & Chadwick, A. (2020) · Social Media + Society · doi:10.1177/2056305120903408 · Cited by 978
Noiseprint: A CNN-Based Camera Model Fingerprint
Cozzolino, D., & Verdoliva, L. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2916364 · Cited by 499 · cited 1×
“camera model fingerprint, was proposed in [32] for image”
MethodTowards Fast, Accurate and Stable 3D Dense Face Alignment
Guo, J., Zhu, X., Yang, Y., Yang, F., Lei, Z., & Li, S. Z. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58529-7_10 · Cited by 462
Recurrent convolutional structures for audio spoof and video deepfake detection
Chintha, A., Thai, B., Sohrawardi, S. J., Bhatt, K., Hickerson, A., Wright, M., & Ptucha, R. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2999185 · Cited by 226 · cited 1×
“In [55], the authors presented a convolutional RNN to detect synthetic speech.”
Background
Research works printed but not linked: 74
- kang, 2021, Edge and Feature Points Based Video Intra-frame Passive-blind Copypaste Forgery Detection, Intelligence in Networks, 6, 637
- güera, 2019, Media Forensics Using Machine Learning Approaches
- 10.1109/ICIP.2019.8804294 · DOI
- 10.1007/s11042-018-6775-x · doi:10.1007/s11042-018-6775-x
- 10.1109/AVSS.2018.8639163 · DOI · Paper page
- 10.1109/VCIP53242.2021.9675329 · DOI
- 10.1109/ICCV48922.2021.01383 · DOI
- 10.1109/WACV.2018.00111 · DOI
- 10.1109/ICIP42928.2021.9506600 · DOI
- bartusiak, 2019, An Adversarial Approach to Spliced Forgery Detection and Localization in Satellite Imagery
- 10.2352/ISSN.2470-1173.2018.07.MWSF-214 · DOI · Paper page
- 10.1109/ICASSP.2019.8683695 · DOI
- 10.1109/CVPRW50498.2020.00340 · DOI
- 10.1109/CVPRW53098.2021.00114 · DOI
- 10.1109/WIFS49906.2020.9360909 · DOI
- horváth, 2019, Anomaly-Based Manipulation Detection in Satellite Images, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 62
- kim, 0, Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech, Proceedings of the International Conference on Machine Learning, 139, 5530
- 10.1109/ICASSP39728.2021.9414427 · DOI
- 10.1109/IEEECONF53345.2021.9723142 · DOI
- 10.2352/ISSN.2470-1173.2021.4.MWSF-273 · DOI
- 10.1109/LSP.2021.3089437 · DOI · Paper page
- 10.1109/ICASSP39728.2021.9413391 · DOI · Paper page
- popov, 0, Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech, Proceedings of the International Conference on Machine Learning, 139, 8599
- 10.1007/s11042-021-11380-3 · DOI
- bestagini, 2012, An Overview on Video Forensics, Proceedings of the European Signal Processing Conference, 1229
- piva, 2013, An Overview on Image Forensics, International Scholarly Research Notices, 2013, 1
- 10.1007/978-3-030-87664-7_3 · DOI
- 10.1109/WIFS49906.2020.9360901 · DOI · Paper page
- bhagtani, 2022, An Overview of Recent Work in Media Forensics: Methods and Threats, ArXiv Preprint
- 10.1007/978-3-030-87664-7_13 · DOI
- 10.1007/978-3-030-87664-7_11 · DOI
- cozzolino, 2019, Extracting Camera-Based Fingerprints for Video Forensics, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop, 130
- 10.23919/EUSIPCO54536.2021.9616262 · DOI
- 10.1109/ICCV48922.2021.01483 · DOI · Paper page
- 10.1109/ICDAR.2017.202 · DOI
- 10.1371/journal.pcbi.1009650 · DOI
- 10.1007/s10032-011-0181-5 · DOI
- 10.1155/2020/8885861 · DOI · Paper page
- 10.1109/MSP.2008.931082 · DOI
- 10.1117/12.705837 · DOI
- 10.1109/TIFS.2017.2692722 · DOI
- 10.1109/SSIAI49293.2020.9094618 · DOI
- moreira, 0, SILA: A System for Scientific Image Analysis, under preparation
- 10.18653/v1/2020.emnlp-main.621 · DOI · Paper page
- 10.1109/ASYU52992.2021.9598977 · DOI
- 10.1109/TIFS.2019.2895965 · doi:10.1109/tifs.2019.2895965
- 10.1016/j.csl.2017.01.001 · DOI · Paper page
- 10.1109/ICAI52203.2021.9445238 · DOI
- 10.1109/ICFHR.2010.128 · doi:10.1109/icfhr.2010.128
- bik, 2016, The Prevalence of Inappropriate Image Duplication, Biomedical Research Publications, 7
- 10.1016/j.procs.2018.10.171 · DOI · Paper page
- 10.1109/TMM.2020.3021234 · DOI
- 10.1109/CISP-BMEI48845.2019.8966004 · doi:10.1109/cisp-bmei48845.2019.8966004
- 10.1016/j.image.2022.116638 · doi:10.1016/j.image.2022.116638
- 10.1109/ACCESS.2022.3140588 · doi:10.1109/access.2022.3140588
- 10.1109/TIFS.2019.2951313 · DOI · Paper page
- 10.1007/s11042-019-08306-5 · DOI
- 10.1007/978-3-030-00021-9_32 · doi:10.1007/978-3-030-00021-9_32
- 10.3390/info9070161 · doi:10.3390/info9070161
- 10.1109/TIFS.2019.2918085 · doi:10.1109/tifs.2019.2918085
- 10.1109/ICASSP43922.2022.9747639 · DOI
- 10.1109/CVPR.2019.00453 · DOI · Paper page
- karras, 2021, Alias-Free Generative Adversarial Networks, Advances in neural information processing systems
- 10.1109/CVPR46437.2021.01268 · DOI · Paper page
- 10.1109/CVPRW.2017.230 · DOI · Paper page
- 10.1109/TNNLS.2020.2967597 · DOI · Paper page
- 10.23919/EUSIPCO.2018.8553596 · DOI
- 10.1109/ICCV.2019.00475 · DOI · Paper page
- 10.1109/MIPR.2019.00024 · DOI
- 10.1007/978-3-030-01246-5_42 · DOI · Paper page
- 10.1109/CVPRW53098.2021.00115 · DOI
- li, 2020, Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks, Proceedings of the European Conference on Computer Vision, 121
- güera, 2019, We Need No Pixels: Video Manipulation Detection Using Stream Descriptors, Proceedings of the International Conference on Machine Learning Synthetic-Realities Deep Learning for Detecting AudioVisual Fakes Workshop
- 10.1109/JSTSP.2020.3008088 · DOI
Cited by
FairSSD: Understanding Bias in Synthetic Speech Detectors
Singh Yadav, A. K., Bhagtani, K., Salvi, D., Bestagini, P., & Delp, E. J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00445 · Cited by 12
“Speech signals can be bona fide ( i.e ., recorded from a human speaker) or synthetic ( i.e ., generated from a computer) [1, 2].”
Self-citationAre Recent Deepfake Speech Generators Detectable?
Bhagtani, K., Yadav, A. K. S., Bestagini, P., & Delp, E. J. (2024) · Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3658664.3659658 · Cited by 9
“D representation of speech obtained using Short Time Fourier Transform (STFT), with time on x-axis and frequency in mel scale on y-axis [6, 7, 35].”
BackgroundMethodSelf-citationAtamna, M., Tkachenko, I., & Miguet, S. (2023) · 2023 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip49359.2023.10222043 · Cited by 8
“In recent years, several methods have been proposed to effectively detect whether images or videos of people have been tampered with, and [1, 2] provide an overview of recent trends in the field of deepfake detection.”
Atamna, M., Tkachenko, I., & Miguet, S. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-88223-4_16 · Cited by 1
Metadata
- Authors
- Bhagtani, K., Yadav, A. K. S., Bartusiak, E. R., Xiang, Z., Shao, R., Baireddy, S., & Delp, E. J.
- Venue
- 2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR)
- Publisher
- IEEE
- Published
- 2022-08
- Pages
- 324-329
- OpenAlex
- W4294975742
- Cited by
- 25
- References
- 26
- FWCI
- 2.03
- Type
- conference paper
- Language
- en
- Open access
- closed
- Funders
- Defense Advanced Research Projects Agency (DARPA) (FA8750-20-2-1004,FA8750-16-2-0173)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: An Overview of Recent Work in Multimedia Forensics. https://app.cochat.ai/papers/10.1109/mipr54900.2022.00064
- The paper
- Bhagtani, K., Yadav, A. K. S., Bartusiak, E. R., Xiang, Z., Shao, R., Baireddy, S., & Delp, E. J. (2022). An Overview of Recent Work in Multimedia Forensics. 2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR). https://doi.org/10.1109/mipr54900.2022.00064
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.