We present the alpha version of COM-PRESS - An Image Manipulation Analysis Dashboard for Fact-checkers. This was also accepted as extended paper at MISDOOM 2023.
Picture by Kevin Faingnaert
Dr. Hannes Mareen
Hannes is a Postdoctoral Researcher at IDLab-MEDIA. From 2017 until 2021, he pursued a PhD degree with the financial support of the Research Foundation - Flanders (FWO).
His research interests cover multimedia compression, security, and forensics. More specifically, his PhD research focused on video watermarking to trace digital pirates. He also researched image & video forgery detection, fingerprinting, perceptual hashing, optical character recognition, dense captioning, low-delay live streaming, medical image analysis and other applications.
Moreover, Hannes is enthusiastic about science communication targeted to non-experts. He won several awards, incl. the Agoriaprijs, two best poster awards (1, 2), the #ThesisThread competition, and the bronze trophy in the Vlaamse PhD Cup.
Our paper titled "Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations" was accepted at the IEEE International Conference on Consumer Electronics (ICCE) 2024.
Our paper titled Training Data Improvement for Image Forgery Detection using Comprint accepted at the IEEE International Conference on Consumer Electronics (ICCE) 2023.
Congratulations to Hannes Mareen, Postdoc Researcher at IDLab-MEDIA, who won the bronze trophy at the Vlaamse PhD Cup 2022
Our paper titled "Fast and Blind Detection of Rate-Distortion-Preserving Video Watermarks" was accepted for presentation at the Int. Workshop on Digital Forensics (WSDF) 2022, held in conjunction with the Int. Conference on Availability, Reliability and Security (ARES) 2022.
Our paper titled "Watermarking for Large-Scale Video Distribution through Out-of-the-Loop Frame Replacement" was accepted at the European Workshop on Visual Information Processing (EUVIP) 2022.
Our paper titled Comprint - Image Forgery Detection and Localization using Compression Fingerprints was accepted at the Workshop on MultiMedia Forensics in the WILD (MMForWILD) 2022, held in conjunction with the Int. Conference on Pattern Recognition (ICPR) 2022.
Our paper "Keyframe Insertion for Random Access and Packet-Loss Repair in H.264/AVC, H.265/HEVC, and H.266/VVC" was accepted at the Data Compression Conference (DCC) 2022, and our paper "A study on keyframe injection in three generations of video coding standards for fast channel switching and packet-loss repair" was accepted at Multimedia Tools and Applications.
Our paper titled "Fast Fallback Watermark Detection using Perceptual Hashes" was accepted for publication to the special issue "Recent Developments and Applications of Image Watermarking" of MDPI Electronics
Paper presented at ICICT 2021 - Implementation-Free Forensic Watermarking
Paper accepted in MDPI Electronics - Keyframe Insertion - Enabling Low-Latency Random Access and Packet Loss Repair
Paper accepted in IEEE TCSVT - Forensic Watermarking Fallback System
Paper accepted in IEEE Access - Rate-Distortion-Preserving Forensic Video Watermarking
Telenet's .comdom app - safe sexting in a world of AI?
The RHETORiC project will therefore design interface elements and machine learning approaches to create semi-automated tools for news editors and media audiences to identify and counter polarization and contribute constuctively to online debates.
Paper accepted at IWDW 2018 - Traitor Tracing After Visible Watermark Removal
Best Poster Award at IEEE-EURASIP Summer School on Signal Processing (S3P) 2018