Perceptually Inspired & Semantically Aware Media Forensics

The social media-fuelled explosion of fake news and misinformation supported by tampered images has led to growth in the development of models and datasets for image manipulation detection. However, existing detection methods mostly treat media objects in isolation, without considering the impact of specific manipulations on viewer perception. Forensic datasets are usually analyzed based on the manipulation operations and corresponding pixel-based masks, but not on the semantics of the manipulation, i.e., type of scene, objects, and viewers' attention to scene content. The semantics of the manipulation play an important role in spreading misinformation through manipulated images. Not all images are equally misinforming! Depending on the type of fakes and who is viewing it, the takeaway could be very different. Our attempt is to develop semantic-aware forensic approaches to understand visual misinformation.