Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization

Due to its high societal impact, deepfake detection is getting active attention in the computer vision community. Most deepfake detection methods rely on identity, facial attribute and adversarial perturbation based spatio-temporal modifications at the whole video or random locations, while keeping the meaning of the content intact. However, a sophisticated deepfake may contain only a small segment of video/audio manipulation, through which the meaning of the content can be, for example, completely inverted from sentiment perspective. To address this gap, we introduce a content driven audio-visual deepfake dataset, termed as Localized Audio Visual DeepFake (LAV-DF), explicitly designed for the task of learning temporal forgery localization. Specifically, the content driven audio-visual manipulations are performed at strategic locations in order to change the sentiment polarity of the whole video. Our baseline method for benchmarking the proposed dataset is a 3DCNN model, termed as Boundary Aware Temporal Forgery Detection (BA-TFD), which is guided via contrastive, boundary matching and frame classification loss functions. Our extensive quantitative analysis demonstrates the strong performance of the proposed method for both task of temporal forgery localization and deepfake detection.