Deep Matching and Validation Network: An End-to-End Solution to Constrained Image Splicing Localization and Detection
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Image splicing is a very common image manipulation technique that is sometimes used for malicious purposes. A splicing detection and localization algorithm usually takes an input image and produces a binary decision indicating whether the input image has been manipulated, and also a segmentation mask that corresponds to the spliced region. Most existing splicing detection and localization pipelines suffer from two main shortcomings: 1) they use handcrafted features that are not robust against subsequent processing (e.g., compression), and 2) each stage of the pipeline is usually optimized independently. In this paper we extend the formulation of the underlying splicing problem to consider two input images, a query image and a potential donor image. Here the task is to estimate the probability that the donor image has been used to splice the query image, and obtain the splicing masks for both the query and donor images. We introduce a novel deep convolutional neural network architecture, called Deep Matching and Validation Network (DMVN), which simultaneously localizes and detects image splicing. The proposed approach does not depend on handcrafted features and uses raw input images to create deep learned representations. Furthermore, the DMVN is end-to-end optimized to produce the probability estimates and the segmentation masks. Our extensive experiments demonstrate that this approach outperforms state-of-the-art splicing detection methods by a large margin in terms of both AUC score and speed.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
An Evaluation of Popular Copy-Move Forgery Detection Approaches
Christlein, V., Riess, C., Jordan, J., Riess, C., & Angelopoulou, E. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2218597 · Cited by 802 · cited 4×
“es more than one region); and 2) reduce false alarms on those visually similar but non-spliced regions. Table 1: CISD performance comparison on CASIA Method Precision Recall F-score Time (sec/sample) [10] 51.64% 82.92% 63.64% 1.85 [27] 99.69% 53.53% 69.66% 6.2710+2 [33] 96.14% 58.95% 73.09% 8.61 [11] 98.97% 63.34% 77.…”
BackgroundMethodInfluentialCozzolino, D., Poggi, G., & Verdoliva, L. (2017) · Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3082031.3083247 · Cited by 349
Research works printed but not linked: 23
- 10.1109/TIFS.2011.2129512 · DOI · Paper page
- Amerini Irene, 2014, 2014 IEEE International Workshop on. IEEE, 143--148
- 10.1109/TIFS.2015.2445742 · DOI · Paper page
- Asghar Khurshid, 2016, Copy-move and splicing image forgery detection and localization techniques: a review. Australian Journal of Forensic Sciences
- 10.1145/2361407.2361424 · DOI
- 10.1109/TIFS.2012.2187516 · DOI · Paper page
- 10.1016/j.diin.2013.04.007 · DOI · Paper page
- 10.1109/TIFS.2007.916285 · DOI · Paper page
- 10.1109/TIFS.2011.2106121 · DOI · Paper page
- 10.1109/TIFS.2015.2455334 · DOI · Paper page
- 10.1109/WIFS.2015.7368565 · DOI · Paper page
- Cozzolino Davide, 2016, 2016 IEEE International Workshop on. IEEE, 1--6.
- 10.1109/TIFS.2015.2493989 · DOI
- 10.1109/MMUL.2013.17 · DOI · Paper page
- 10.1109/TIFS.2011.2169959 · DOI · Paper page
- 10.1109/MINES.2010.196 · DOI
- 10.1109/MSP.2008.931079 · DOI · Paper page
- Hsu Yu-Feng, Detecting image splicing using geometry invariants and camera characteristics consistency
- 10.1016/j.neucom.2016.04.068 · DOI
- 10.1109/TIFS.2017.2656823 · DOI · Paper page
- 10.1109/TIFS.2014.2381872 · DOI · Paper page
- 10.1007/978-3-319-10602-1_48 · DOI · Paper page
- 10.1145/2560365 · DOI
Cited by
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
Wu, Y., AbdAlmageed, W., & Natarajan, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00977 · Cited by 647
Self-citationRecurrent convolutional strategies for face manipulation detection in videos
Sabir, E., Cheng, J., Jaiswal, A., AbdAlmageed, W., Masi, I., & Natarajan, P. (2019) · arXiv · doi:10.48550/arxiv.1905.00582 · Cited by 443
“Digital image manipulation such as copy-move and splicing [44, 43] are examples of deliberate manipulation, while image repurposing [17, 35, 18] is an example of misleading context.”
BackgroundSelf-citationLiu, X., Liu, Y., Chen, J., & Liu, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3189545 · Cited by 417
BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization
Wu, Y., Abd-Almageed, W., & Natarajan, P. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_11 · Cited by 334
Self-citation
Metadata
- Authors
- Wu, Y., Abd-Almageed, W., & Natarajan, P.
- Venue
- Proceedings of the 25th ACM international conference on Multimedia
- Publisher
- ACM
- Published
- 2017-10-19
- Pages
- 1480-1502
- OpenAlex
- W2963447079
- Cited by
- 114
- References
- 3
- FWCI
- 2.43
- Type
- conference paper
- Language
- en
- Open access
- closed
- Funders
- the Defense Advanced Research Projects Agency (FA8750-16-2-0204)
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: Deep Matching and Validation Network: An End-to-End Solution to Constrained Image Splicing Localization and Detection. https://app.cochat.ai/papers/10.1145/3123266.3123411
- The paper
- Wu, Y., Abd-Almageed, W., & Natarajan, P. (2017). Deep Matching and Validation Network: An End-to-End Solution to Constrained Image Splicing Localization and Detection. Proceedings of the 25th ACM international conference on Multimedia. https://doi.org/10.1145/3123266.3123411
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.