KIAM Main page Web Library  •  Publication Searh   

KIAM Preprint  80, Moscow, 2022
Authors: Meshchaninov V.P., Molodetskikh I.A., Vatolin D.S., Voloboy A.G.
Combining contrastive and supervised learning for video super-resolution detection
Upscaled video detection is a helpful tool in multimedia forensics, but its a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and deep-learning based super-resolution, and they leave unique traces. This paper proposes a new upscaled-resolution-detection method based on learning of visual representations using contrastive and cross-entropy losses. To explain how the method detects videos, the major components of our framework are systematically reviewed in particular, it is shown that most data-augmentation approaches hinder the learning of the method. Through extensive experiments on various datasets, our method has been shown to effectively detects upscaling even in compressed videos and outperforms the state-of-theart alternatives. The code and models are publicly available at
native resolution, upscaling detection, super-resolution, interpolation, video compression
Publication language: russian,  pages: 13
Research direction:
Programming, parallel computing, multimedia
Russian source text:
Export link to publication in format:   RIS    BibTeX
View statistics (updated once a day)
over the last 30 days 10 (-2), total hit from 06.12.2022 203
About authors:
  • Meshchaninov Viacheslav Pavlovich, Moscow State University
  • Molodetskikh Ivan Andreevich, Moscow State University
  • Vatolin Dmitriy Sergeevich, Moscow State University
  • Voloboy Alexey Gennadievich, RAS