The ACAV project aims at improving videos accessibility on the Web to people with sensory disabilities. For this purpose, additional descriptions of key visual/audio information of the video, that cannot be perceived, are presented using accessible output modalities. However, a personalization mechanism is necessary to adapt these descriptions and their presentations according to user interests, cognitive and physical capabilities. In this article, concepts needed for this kind of personalization are introduced and an adaptive personalization mechanism of descriptions and associated presentations is suggested and evaluated.