National Repository of Grey Literature 1 records found  Search took 0.01 seconds. 
Audiovisual person recognition
Bahounek, Ondřej ; Mošner, Ladislav (referee) ; Plchot, Oldřich (advisor)
This work focuses on audiovisual verification of a person in a video or from a facial image and a voice recording. The models use a fusion of voice and face embeddings. The models assign weights to both modalities, allowing them to give more attention to one or the other. The results from these models demonstrate good resistance to the degradation of one of the modalities.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.