Vigo: Audiovisual Fake Detection and Segment Localization

摘要

Recent years have seen a revolution in the creation of synthetic multimedia content. Algorithms with the ability to generate truly convincing images, videos, text and audio capable of fooling any human being. In addition to the possible beneficial uses that this type of technology may have, we must highlight the danger of its misuse for criminal or fraudulent activities. Deepfakes stand out as an example of a potentially dangerous use of these technologies, since they facilitate identity theft and the generation of misinformation. Current solutions are not capable of detecting this type of fake content with sufficient reliability. Therefore, it is crucial to develop new algorithms that solve this problem. This paper presents two methods focusing on the classification and localization of deepfake videos taking into account audio and visual information. These methods were submitted to the ACM 1M Deepfakes Detection Challenge, achieving the highest score in the temporal localization task and a top-five ranking in the classification task.