Aim and Topics
The rapid growth of multimedia collections world-wide opens new challenges to multimedia technology with respect to crime prevention and investigation. The protection of images, video, and audio data from illegal use, as well as its exploitation in forensics and intelligence, have become serious challenges as the sheer data volume renders a full manual inspection by an expert impossible. Tools are needed to support the protection, management, processing, interpretation, and visualization of multimedia data in the different steps of the investigation process. Many exciting solutions for related problems have been developed in the multimedia research community (including knowledge extraction, categorization, indexing, browsing and visualization), forming an excellent basis for forensics and intelligence. The problem with many solutions developed so far is that they work well in controlled settings like those typical of laboratory experiments, but often fail to provide reliable answers in real-life conditions such as those encountered by forensic analysts and investigators in their daily activities.
MMForWILD offers a forum for proposing multimedia forensic solutions meeting the operational needs of forensics and intelligence operators. The workshop is targeted both at researchers working on innovative multimedia technology and experts developing tools in the field. The goal of the workshop is to attract and invite papers investigating the use of multimedia forensics outside the controlled environment of research laboratories (LEA, Practitioners, etc.). It intends to offer a venue for theory- and data-driven techniques addressing the trustworthiness of media data and the ability of verifying their integrity to prevent harmful misuses, seeking for solutions at the edge of signal processing, deep learning, multimedia analysis. Topics like database mismatch, lack of training data, supervised and unsupervised methodologies, vulnerability assessment against attacks, tampering detection in the presence of unknown post-processing, deep-fakes detection and so on, would all be themes of interest for the workshop. The relevance of these topics is also demonstrated by other similar activities in top international conferences (e.g., workshop on Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes" @ICML2019, workshop on Media Forensics @CVPR2019).
- Submission deadline: October 10th 2020
- Author notification: November 10th 2020
- Camera-ready submission: November 15th 2020
Papers will be selected by a single blind (reviewers are anonymous) review process based on their originality, relevance, and clarity of presentation. All submitted papers will be reviewed by at least 2 PC members, according to their expertise. Workshop Chairs will be responsible for the final decision about each work, especially for borderline situation.