Djilali, Y.A.D.[Yasser Abdelaziz Dahou]
Co Author Listing * Do Vision and Language Encoders Represent the World Similarly?
* Do VSR Models Generalize Beyond LRS3?
* Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment
* Learning Saliency From Fixations
* Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
* Rethinking 360° Image Visual Attention Modelling with Unsupervised Learning
* Simple baselines can fool 360° saliency metrics
7 for Djilali, Y.A.D.