2 papers
cs.CV2025
Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples
Konstantinos Tsigos, Evlampios Apostolidis, Vasileios Mezaris
In this paper, we introduce the idea of using adversarially-generated samples of the input images that were classified as deepfakes by a detector, to form perturbation masks for in…
cs.CV2021
Video Summarization Using Deep Neural Networks: A Survey
Evlampios Apostolidis, Eleni Adamantidou, Alexandros I. Metsai +2
Video summarization technologies aim to create a concise and complete synopsis by selecting the most informative parts of the video content. Several approaches have been developed…