181 citations · 206 across the 17 of their papers we have counts for
19 papers
Energy-Latency Attacks: A New Adversarial Threat to Deep Learning
Hanene F. Z. Brachemi Meftah, Wassim Hamidouche, Sid Ahmed Fezza +1
The growing computational demand for deep neural networks ( DNNs) has raised concerns about their energy consumption and carbon footprint, particularly as the size and complexity o…
Improved Encoding for Overfitted Video Codecs
Thomas Leguay, Théo Ladune, Pierrick Philippe +1
Overfitted neural video codecs offer a decoding complexity orders of magnitude smaller than their autoencoder counterparts. Yet, this low complexity comes at the cost of limited co…
Low-complexity Overfitted Neural Image Codec
Thomas Leguay, Théo Ladune, Pierrick Philippe +2
We propose a neural image codec at reduced complexity which overfits the decoder parameters to each input image. While autoencoders perform up to a million multiplications per deco…
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-…
Perceptual Quality Assessment of HEVC and VVC Standards for 8K Video
Charles Bonnineau, Wassim Hamidouche, Jerome Fournier +3
With the growing data consumption of emerging video applications and users requirement for higher resolutions, up to 8K, a huge effort has been made in video compression technologi…
Reveal of Vision Transformers Robustness against Adversarial Attacks
Ahmed Aldahdooh, Wassim Hamidouche, Olivier Deforges
The major part of the vanilla vision transformer (ViT) is the attention block that brings the power of mimicking the global context of the input image. For better performance, ViT…