Djilali, Y.A.D.[Yasser Abdelaziz Dahou]
* 2021: Rethinking 360° Image Visual Attention Modelling with Unsupervised Learning
* 2021: Simple baselines can fool 360° saliency metrics
* 2023: Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
* 2024: Do VSR Models Generalize Beyond LRS3?
* 2024: Learning Saliency From Fixations