Conference proceeding
MVFNet: Multipurpose Video Forensics Network using Multiple Forms of Forensic Evidence
Proceedings / IEEE Workshop on Applications of Computer Vision, pp 2207-2217
26 Feb 2025
Abstract
While videos can be falsified in many different ways, most existing forensic networks are specialized to detect only a single manipulation type (e.g. deepfake, inpainting). This poses a significant issue as the manipulation used to falsify a video is not known a priori. To address this problem, we propose MVFNet - a multipurpose video forensics network capable of detecting multiple types of manipulations including inpainting, deepfakes, splicing, and editing. Our network does this by extracting and jointly analyzing a broad set of forensic feature modalities that capture both spatial and temporal anomalies in falsified videos. To re-liably detect and localize fake content of all shapes and sizes, our network employs a novel Multi-Scale Hierarchi-cal Transformer module to identify forensic inconsistencies across multiple spatial scales. Experimental results show that our network obtains state-of-the-art performance in general scenarios where multiple different manipulations are possible, and rivals specialized detectors in targeted scenarios.
Metrics
3 Record Views
Details
- Title
- MVFNet: Multipurpose Video Forensics Network using Multiple Forms of Forensic Evidence
- Creators
- Tai D. Nguyen - Drexel UniversityMatthew C. Stamm - Drexel University
- Publication Details
- Proceedings / IEEE Workshop on Applications of Computer Vision, pp 2207-2217
- Series
- IEEE Winter Conference on Applications of Computer Vision
- Publisher
- IEEE; LOS ALAMITOS
- Number of pages
- 11
- Grant note
- 2320600 / National Science Foundation (10.13039/100000001)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:001481328900211
- Scopus ID
- 2-s2.0-105003634895
- Other Identifier
- 991022048282704721