SNIS: A Signal Noise Separation-Based Network for Post-Processed Image Forgery Detection
The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
Image forgery detection has aroused widespread research interest in both academia and industry because of its potential security threats. Existing forgery detection methods achieve excellent tampered regions localization performance when forged images have not undergone post-processing, which can be detected by observing changes in the statistical features of images. However, forged images may be carefully post-processed to conceal forgery boundaries in a particular scenario. It becomes tough challenging to these methods. In this paper, we perform an analogous analysis between image forgery detection and blind signal separation, and formulate the post-processed image forgery detection problem into a signal noise separation problem. We also propose a signal noise separation-based (SNIS) network to solve the problem of detecting post-processed image forgery. Specifically, we first adopt the signal noise separation module to separate tampered region from the complex background region with post-processing noise, which weakens or even eliminates the negative impact of post-processing on forgery detection. Then, the multi-scale feature learning module uses a parallel atrous convolution architecture to learn high-level global features from multiple perspectives. Besides, a feature fusion module is utilized to enhance the discriminability of tampered regions and real regions by strengthening the boundary information. Finally, the prediction module is designed to predict the tampered region and classify the type of tampering operation. Extensive experiments show that the proposed SNIS is not only effective for forgery detection on forged images without post-processing, but also promising in robustness against multiple post-processing attacks. Furthermore, SNIS is robust in detecting forged images from unknown sources.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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 · cited 1×
“The backbone consists of ResNet 101 network [50] and convolutional block attention module (CBAM) [51].”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“The prediction module utilizes the region proposal network (RPN) [52] and CBAM attention module to propose the regions of interest (RoI) for bounding box regression, which is defined as F roi .”
MethodMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
CBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
CASIA Image Tampering Detection Evaluation Database
Dong, J., Wang, W., & Tan, T. (2013) · 2013 IEEE China Summit and International Conference on Signal and Information Processing · doi:10.1109/chinasip.2013.6625374 · Cited by 813 · cited 1×
“2) Datasets: We compare SNIS with some state-of-the-art methods on NIST Nimble 2016 (NIST16) [54], Columbia [55] and CASIA [56] dataset.”
MethodSelf-citationSegmentation-Based Image Copy-Move Forgery Detection Scheme
Li, J., Li, X., Yang, B., & Sun, X. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2381872 · Cited by 810
Exposing digital forgeries by detecting traces of resampling
Popescu, A. C., & Farid, H. (2005) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2004.839932 · Cited by 795
Learning Rich Features for Image Manipulation Detection
Zhou, P., Han, X., Morariu, V. I., & Davis, L. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00116 · Cited by 778
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 · cited 6×
“…is 0.460 better than RGB-N [16], 0.109 better than Cons-N [13], 0.486 better than DFCN [17], 0.594 better than Noiseprint [43], 0.563 better than ManTra-Net [44], and 0.459 better than OSN [46] in forged region localization when tampered images have undergone different post-processing operations.”
BackgroundMethodInfluentialBayar, B., & Stamm, M. C. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2825953 · Cited by 599 · cited 1×
“Bayar and Stamm [28] developed a constrained convolutional layer to suppress the content of an image and adaptively learn operation detection features.”
BackgroundNoiseprint: 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 5×
“Cozzolino and Verdoliva [43] designed a Siamese network to extract a camera model fingerprint, so that model-related artifacts are enhanced, and then forgery localization can be achieved.”
BackgroundMethodInfluentialImage Forgery Localization via Fine-Grained Analysis of CFA Artifacts
Ferrara, P., Bianchi, T., De Rosa, A., & Piva, A. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2202227 · Cited by 492 · cited 5×
“We can clearly see that SNIS outperforms ELA , NOI1 , and CFA1 on NIST16, Columbia, and CASIA datasets.”
BackgroundMethodInfluentialHybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries
Bappy, J. H., Simons, C., Nataraj, L., Manjunath, B. S., & Roy-Chowdhury, A. K. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2895466 · Cited by 477 · cited 2×
“In [14], a manipulation localization architecture enabled tampered regions to be segmented out from non-tampered ones by utilizing resampling features, long short-term memory cells, and an encoder-decoder network.”
BackgroundMethodUsing noise inconsistencies for blind image forensics
Mahdian, B., & Saic, S. (2009) · Image and Vision Computing · doi:10.1016/j.imavis.2009.02.001 · Cited by 415 · cited 3×
“For forged images without post-processing, we verify the tampered region localization performance of SNIS and compare it with methods ELA [5], NOI1 [6], CFA1 [8], RGB-N [16], Cons-N [13] and DFCN [17].”
BackgroundMethodExposing Digital Image Forgeries by Illumination Color Classification
de Carvalho, T. J., Riess, C., Angelopoulou, E., Pedrini, H., & de Rezende Rocha, A. (2013) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2013.2265677 · Cited by 406 · cited 1×
“These methods mainly realize image forgery localization by exposing some observable artifacts, such as color inconsistency [3], [4], compression error difference [5], noise inconsistency [6], [7], camera filter array patterns [8], semantic patches [9], [10], [11], and edge feature [12].”
MethodSpace or time adaptive signal processing by neural network models
Herault, J., & Jutten, C. (1986) · AIP Conference Proceedings · doi:10.1063/1.36258 · Cited by 403 · cited 1×
“The goal of blind signal separation is to restore the source signals from the observed mixed signals [47], [48].”
BackgroundImage Splicing Localization using a Multi-task Fully Convolutional Network (MFCN)
Salloum, R., Ren, Y., & Jay Kuo, C.-C. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.01.010 · Cited by 395 · cited 2×
“In [12], a multi-task fully convolutional network that can learn both surface label and the edge of the spliced region was designed to localize image splicing attacks.”
BackgroundMethodIdentification of bitmap compression history: jpeg detection and quantizer estimation
Fan, Z., & de Queiroz, R. L. (2003) · IEEE Transactions on Image Processing · doi:10.1109/tip.2002.807361 · Cited by 364 · cited 1×
“pression [23], [24], and semantic focused operation [25], [26].”
BackgroundRobust Median Filtering Forensics Using an Autoregressive Model
Kang, X., Stamm, M. C., Peng, A., & Liu, K. J. R. (2013) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2013.2273394 · Cited by 229 · cited 2×
“In [18], the statistical properties of the median filter residual were fitted to an autoregressive (AR) model and the AR coefficients were defined as the features for median filtering detection.”
MethodCAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing
Kwon, M.-J., Yu, I.-J., Nam, S.-H., & Lee, H.-K. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00042 · Cited by 226
Fast and Effective Image Copy-Move Forgery Detection via Hierarchical Feature Point Matching
Li, Y., & Zhou, J. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2876837 · Cited by 225 · cited 1×
“Many image forensics techniques have been designed to detect a specific tampering operation, such as median filter-ing [18], [19], blurring [20], [21], resampling [22], JPEG compression [23], [24], and semantic focused operation [25], [26].”
BackgroundIndependent component analysis: An introduction
Tharwat, A. (2021) · Applied Computing and Informatics · doi:10.1016/j.aci.2018.08.006 · Cited by 211
A family of fixed-point algorithms for independent component analysis
Hyvarinen, A. (2002) · 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1997.604766 · Cited by 199 · cited 2×
“signals from the observed mixed signals [47], [48].”
BackgroundImage Tampering Localization Using a Dense Fully Convolutional Network
Zhuang, P., Li, H., Tan, S., Li, B., & Huang, J. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3070444 · Cited by 185 · cited 9×
“From this Table, it is evident that the SNIS performance is 0.460 better than RGB-N [16], 0.109 better than Cons-N [13], 0.486 better than DFCN [17], 0.594 better than Noiseprint [43], 0.563 better than ManTra-Net [44], and 0.459 better than OSN [46] in forged region localization when tampered…”
BackgroundMethodInfluentialRobust Detection of Image Operator Chain With Two-Stream Convolutional Neural Network
Liao, X., Li, K., Zhu, X., & Liu, K. J. R. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002391 · Cited by 175 · cited 2×
“The reason is that image forgery usually involves multiple complex tampering manipulations [15].”
BackgroundMethodSelf-citationIdentification of Various Image Operations Using Residual-Based Features
Li, H., Luo, W., Qiu, X., & Huang, J. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2599849 · Cited by 165
Effective image splicing detection based on image chroma
Wang, W., Dong, J., & Tan, T. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5413549 · Cited by 163 · cited 1×
“These methods mainly realize image forgery localization by exposing some observable artifacts, such as color inconsistency [3], [4], compression error difference [5], noise inconsistency [6], [7], camera filter array patterns [8], semantic patches [9], [10], [11], and edge feature [12].”
MethodSelf-citationBlind Detection of Median Filtering in Digital Images: A Difference Domain Based Approach
Chen, C., Ni, J., & Huang, J. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2277814 · Cited by 146 · cited 1×
“Many image forensics techniques have been designed to detect a specific tampering operation, such as median filtering [18], [19], blurring [20], [21], resampling [22], JPEG com-”
MethodColor-Decoupled Photo Response Non-Uniformity for Digital Image Forensics
Li, C., & Li, Y. (2011) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2011.2160750 · Cited by 138
Constrained R-Cnn: A General Image Manipulation Detection Model
Yang, C., Li, H., Lin, F., Jiang, B., & Zhao, H. (2020) · 2020 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102825 · Cited by 138
Exposing image splicing with inconsistent local noise variances
Pan, X., Zhang, X., & Lyu, S. (2012) · 2012 IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2012.6215223 · Cited by 120 · cited 1×
“These methods mainly realize image forgery localization by exposing some observable artifacts, such as color inconsistency [3], [4], compression error difference [5], noise inconsistency [6], [7], camera filter array patterns [8], semantic patches [9], [10], [11], and edge feature [12].”
MethodImage Forgery Localization via Integrating Tampering Possibility Maps
Li, H., Luo, W., Qiu, X., & Huang, J. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2656823 · Cited by 114 · cited 1×
“These methods mainly realize image forgery localization by exposing some observable artifacts, such as color inconsistency [3], [4], compression error difference [5], noise inconsistency [6], [7], camera filter array patterns [8], semantic patches [9], [10], [11], and edge feature [12].”
MethodRobust Image Forgery Detection over Online Social Network Shared Images
Wu, H., Zhou, J., Tian, J., & Liu, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01308 · Cited by 86 · cited 6×
“…is 0.460 better than RGB-N [16], 0.109 better than Cons-N [13], 0.486 better than DFCN [17], 0.594 better than Noiseprint [43], 0.563 better than ManTra-Net [44], and 0.459 better than OSN [46] in forged region localization when tampered images have undergone different post-processing operations.”
BackgroundMethodInfluentialQin, C., Liu, E., Feng, G., & Zhang, X. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3047142 · Cited by 78 · cited 1×
“Image forgery has recently become a potential threat, which has a negative impact on many aspects of our life, such as fake news, false propaganda, bogus certificate, and even blackmail [1], [2].”
BackgroundWang, J., Wang, H., Li, J., Luo, X., Shi, Y.-Q., & Jha, S. K. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2922309 · Cited by 67 · cited 2×
“Wang et al. [34] utilized the conversion error, rounding error, and truncation error on the pixel in the spherical coordinate system to detect the recompression in the color images.”
BackgroundDownscaling Factor Estimation on Pre-JPEG Compressed Images
Liu, X., Lu, W., Zhang, Q., Huang, J., & Shi, Y.-Q. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2893353 · Cited by 60 · cited 2×
“Liu et al. [33] proposed to use the histogram of the difference image extremum interval to estimate the downscaling factor of the pre-JPEG compressed images.”
BackgroundMethodBR$^2$Net: Defocus Blur Detection Via a Bidirectional Channel Attention Residual Refining Network
Tang, C., Liu, X., An, S., & Wang, P. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2985541 · Cited by 50 · cited 1×
“Many image forensics techniques have been designed to detect a specific tampering operation, such as median filtering [18], [19], blurring [20], [21], resampling [22], JPEG com-”
MethodSelf-supervised Domain Adaptation for Forgery Localization of JPEG Compressed Images
Rao, Y., & Ni, J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01476 · Cited by 50 · cited 1×
“Rao and Ni [45] proposed a self-supervised domain adaptation network consists of a Siamese architecture and a compression approximation network for JPEG-resistant image forgery localization.”
BackgroundImage Forensics Based on Transfer Learning and Convolutional Neural Network
Zhan, Y., Chen, Y., Zhang, Q., & Kang, X. (2017) · ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec) · doi:10.1145/3082031.3083250 · Cited by 43 · cited 1×
“Zhan et al. [31] trained a forensic model utilizing prior knowledge transferred from the steganalysis model and presented a parameter transfer strategy for general-purpose operation detection on different databases.”
MethodYi-fang, C., Wang, Z., Wang, Z. J., & Kang, X. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2998401 · Cited by 28 · cited 1×
“Chen et al. [29] automated the neural network architecture design for multi-purpose image forensics, which generated high-performing CNNs for specific forensic tasks through reinforcement learning.”
BackgroundLocating splicing forgery by adaptive-SVD noise estimation and vicinity noise descriptor
Liu, B., & Pun, C. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.12.105 · Cited by 25 · cited 2×
“In [26], noise discrepancy was analyzed to expose splicing forgery artifacts.”
BackgroundMethodWang, H., Wang, J., Luo, X., Zheng, Y., Ma, B., Sun, J., & Jha, S. K. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3111195 · Cited by 25 · cited 2×
“Wang et al. [35] detected double JPEG compressed images by using quaternion mapping to retrain the relationship between continuously compressed JPEG images.”
BackgroundMethodDetectability of the Order of Operations: An Information Theoretic Approach
Chu, X., Chen, Y., & Liu, K. J. R. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2510958 · Cited by 24 · cited 2×
“Considering that the order of operations affects the generated fake image, Chu et al. [37] formulated the order of operations detection problem as a multiple hypotheses testing problem.”
BackgroundIdentifying tampering operations in image operator chains based on decision fusion
Chen, J., Liao, X., & Qin, Z. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116287 · Cited by 20 · cited 2×
“In [39], different forensic knowledge integrated by a decision fusion method has been used to identify multiple tampering operations in image operation chains.”
BackgroundMethodSelf-citationQuantization Step Estimation for JPEG Image Forensics
Li, W., Li, X., Ni, R., & Zhao, Y. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3123477 · Cited by 18 · cited 2×
“A function of the candidate step taking a similar shape to the DCT coefficients distribution of compressed images was introduced in [24] to achieve quantization step estimation for JPEG images.”
BackgroundMethodReal-time detecting one specific tampering operation in multiple operator chains
Gao, S., Liao, X., & Liu, X. (2019) · Journal of Real-Time Image Processing · doi:10.1007/s11554-019-00860-3 · Cited by 17 · cited 1×
“Recently, there have been a lot of efforts to detect multiple operations in digital images [32], [33], [34], [35], [36], [37], [38], [39], [40], [41].”
BackgroundSelf-citationA Transformer based Approach for Image Manipulation Chain Detection
You, J., Li, Y., Zhou, J., Hua, Z., Sun, W., & Li, X. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475513 · Cited by 15 · cited 1×
“Recently, there have been a lot of efforts to detect multiple operations in digital images [32], [33], [34], [35], [36], [37], [38], [39], [40], [41].”
BackgroundDetecting and classifying blurred image regions
Xu, W., Mulligan, J., Xu, D., & Chen, X. (2013) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2013.6607422 · Cited by 11 · cited 2×
“In [20], an approach was presented to construct an optimal blurring detection classifier based on support vector machines, which used different types of image information, including image color, gradient, and spectral information.”
BackgroundMethodFirst step towards parameters estimation of image operator chain
Liao, X., Huang, Z., Peng, L., & Qiao, T. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.045 · Cited by 11 · cited 1×
“Recently, there have been a lot of efforts to detect multiple operations in digital images [32], [33], [34], [35], [36], [37], [38], [39], [40], [41].”
BackgroundSelf-citationForensic Analysis of JPEG-Domain Enhanced Images via Coefficient Likelihood Modeling
Yang, J., Zhu, G., Luo, Y., Kwong, S., Zhang, X., & Zhou, Y. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3071218 · Cited by 10 · cited 2×
“[32] designed a statistical likelihood function to characterize the mixed compression and enhancement artifacts, and to further estimate parameters of JPEG-domain enhanced images.”
BackgroundSingh, G., & Goyal, P. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533733 · Cited by 7 · cited 1×
“Singh and Goyal [30] exploited local dense connections and global residual learning for better general-purpose forensics performance by using robust residual dense blocks.”
BackgroundA Features Decoupling Method for Multiple Manipulations Identification in Image Operation Chains
Chen, J., Liao, X., Wang, W., & Qin, Z. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414628 · Cited by 4 · cited 2×
“Our recent work [40] proposed a features decoupling method based on blind signal separation”
BackgroundMethodSelf-citationImage Forgery Detection Based on Semantic Image Understanding
Ye, K., Dong, J., Wang, W., Xu, J., & Tan, T. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7299-4_39 · Cited by 3 · cited 1×
“These methods mainly realize image forgery localization by exposing some observable artifacts, such as color inconsistency [3], [4], compression error difference [5], noise inconsistency [6], [7], camera filter array patterns [8], semantic patches [9], [10], [11], and edge feature [12].”
MethodSelf-citation
Research works printed but not linked: 3
- Krawetz, 2007, A picture’s worth: Digital image analysis and forensics, Hacker Factor Solutions, 1
- 2016, NIST Manipulation Evaluation Dataset
- 2004, Columbia Image Splicing Detection Evaluation Dataset
Cited by
Deepfake Detection: A Comprehensive Survey from the Reliability Perspective
Wang, T., Liao, X., Chow, K. P., Lin, X., & Wang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3699710 · Cited by 107
Self-citationToward Effective Image Manipulation Detection With Proposal Contrastive Learning
Zeng, Y., Zhao, B., Qiu, S., Dai, T., & Xia, S. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3247607 · Cited by 68
“SNIS [17] propose a signal noise separation module to separate tampered region for post-processing forgery detection.”
BackgroundExploring autonomous methods for deepfake detection: A detailed survey on techniques and evaluation
Sunil, R., Mer, P., Diwan, A., Mahadeva, R., & Sharma, A. (2025) · Heliyon · doi:10.1016/j.heliyon.2025.e42273 · Cited by 54
Robust data hiding method based on frequency coefficient variance in repetitive compression
Solak, S. B., Abdirashid, A. M., ADJEVI, A., & Sahu, A. K. (2024) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2024.101756 · Cited by 38
Review of Image Forensic Techniques Based on Deep Learning
Shi, C., Chen, L., Wang, C., Zhou, X., & Qin, Z. (2023) · Mathematics · doi:10.3390/math11143134 · Cited by 47
Self-citation
Metadata
- Authors
- Chen, J., Liao, X., Wang, W., Qian, Z., Qin, Z., & Wang, Y.
- Affiliations
- Hunan University (CN)
- Chinese Academy of Sciences (CN)
- Fudan University (CN)
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2023-02
- Volume
- 33
- Issue
- 2
- Pages
- 935-951
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W4294811474
- Cited by
- 129
- References
- 53
- Citations by year
- 2026: 39 · 2025: 54 · 2024: 23 · 2023: 12
- FWCI
- 7.36
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Circuits and Systems for Video Technology (publishedVersion)
- Funders
- National Natural Science Foundation of China (61972142, 61972395, U20A20174, U20B2051, 62002112)
- Natural Science Foundation of Hunan Province (2020JJ4212, 2021JJ40117)
- Science and Technology Projects of Hunan Province (2015TP1004)
- Science and Technology Key Projects of Changsha City (kh2103003)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Keywords
- image forgery detection, post-processing attacks, blind source separation, signal-to-noise separation, tampered region localization, dilated convolution, multi-scale feature learning, feature fusion
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
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.