181 citations · 286 across the 67 of their papers we have counts for
8 papers · 1 filter
Evaluation of Pre-Trained CNN Models for Geographic Fake Image Detection
Sid Ahmed Fezza, Mohammed Yasser Ouis, Bachir Kaddar +2
Thanks to the remarkable advances in generative adversarial networks (GANs), it is becoming increasingly easy to generate/manipulate images. The existing works have mainly focused…
2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos
Ahmed Telili, Sid Ahmed Fezza, Wassim Hamidouche +1
Recently, with the growing popularity of mobile devices as well as video sharing platforms (e.g., YouTube, Facebook, TikTok, and Twitch), User-Generated Content (UGC) videos have b…
Ensemble Learning for Efficient VVC Bitrate Ladder Prediction
Fatemeh Nasiri, Wassim Hamidouche, Luce Morin +2
Changing the encoding parameters, in particular the video resolution, is a common practice before transcoding. To this end, streaming and broadcast platforms benefit from so-called…
Performance Analysis of Optimized Versatile Video Coding Software Decoders on Embedded Platforms
Anup Saha, Wassim Hamidouche, Miguel Chavarrías +3
In recent years, the global demand for high-resolution videos and the emergence of new multimedia applications have created the need for a new video coding standard. Hence, in July…
Deep-based Film Grain Removal and Synthesis
Zoubida Ameur, Wassim Hamidouche, Edouard François +3
In this paper, deep learning-based techniques for film grain removal and synthesis that can be applied in video coding are proposed. Film grain is inherent in analog film content b…
Federated Adversarial Training with Transformers
Ahmed Aldahdooh, Wassim Hamidouche, Olivier Déforges
Federated learning (FL) has emerged to enable global model training over distributed clients' data while preserving its privacy. However, the global trained model is vulnerable to…
OpenVVC: a Lightweight Software Decoder for the Versatile Video Coding Standard
Thomas Amestoy, Pierre-loup Cabarat, Guillaume Gautier +2
In the recent years, users requirements for higher resolution, coupled with the apparition of new multimedia applications, have created the need for a new video coding standard. Th…
CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability
Charles Bonnineau, Wassim Hamidouche, Jean-François Travers +3
In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-…