SegNet: a network for detecting deepfake facial videos

Yu, Chia-Fu; Chen, Kangcheng; Chang, Ching-Tang; Ti, Yen‐Wu

doi:10.1007/s00530-021-00876-5

Cited by 11 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 3, we show a collection of articles (Reference) and their average scores according to the datasets. Faceforensics++ [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38] 94.2 [39], [40], [41], [42], [43] 93. 55 3 DeepFakeDetection [44] 90.80 --4 UADFV [45], [46], [47] 93.4 [48], [49] 98.7 5…”

Section: Performance Of the Datasetsmentioning

confidence: 99%

A survey on deepfake video detection datasets

Sohan,

Solaiman,

Hasan

2023

IJEECS

View full text Add to dashboard Cite

Deepfake video has usefulness in entertainment and multimedia technology, however, the danger of deepfake is significant to the social, economical, and political sectors so far. Specifically, to diverge any public opinion by generating fake news and spreading misleading information, national security may be under risk due to misrepresenting statements given by political leaders. The creation of such manipulated videos are getting easier day by day and at the same time it is necessary to detect and prevent them. In order to do that, researchers are creating challenging fake video databases for artificial intelligence (AI) based detection models to contribute to the research. This paper reviewed the existing deepfake video detection datasets available online and used in the previous research articles. We analyzed the literature from two different perspectives, datasets and detection models. The goal of this study is to introduce all publicly available datasets in this field including the discussion of techniques used to generate the data. In addition to our contribution, we showed a result comparison among different deepfake datasets and discussed the findings.

show abstract

Section: Performance Of the Datasetsmentioning

confidence: 99%

A survey on deepfake video detection datasets

Sohan,

Solaiman,

Hasan

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…With the development of deep learning techniques, image semantic segmentation [6] based methods have achieved great success in computer vision tasks. For pixel-level segmentation, there are models such as FCN [7] , SegNet [8] , U-Net, etc. Xue et al [9] used FCN to detect cracks in an underpass tunnel maintenance task which elevated the need for automated detection techniques.…”

Section: Introductionmentioning

confidence: 99%

High-speed railway concrete slab crack detection based on image semantic segmentation method

Man,

Mao,

Lai

et al. 2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

Rapid and accurate detection of surface cracks on high-speed railway concrete slabs is of great significance for maintaining the safety and reliability of railway structures. However, existing crack detection methods suffer from segmentation insufficiency and weak anti-interference capabilities. In this paper, a novel automated detection method based on image semantic segmentation is proposed to achieve segmentation detection and quantitative analysis of surface cracks on high-speed railway concrete track slabs. First, the crack images are preprocessed to enhance the crack edge features through white balance and filtering. Then, an image-driven semantic segmentation network CBAM-U-Net is utilized for pixel-level crack detection on the sampled crack images. The network reduces the computational effort and improves the accuracy mainly by improving the 'skip connection' information interaction mechanism of the U-Net network and introducing CBAM blocks. Finally, by counting the pixel number of the segmentation area, the crack can be quantitatively evaluated. The experimental result demonstrates the effectiveness of the proposed method, with an average Dice coefficient of 73.35%. This method provides a new strategy for automated crack detection on high-speed railway concrete track slabs.

show abstract