Active Speakers in Context
CVPR, pp. 12462-12471, 2020.
We have shown that our method outperforms the state-of-the-art in active speaker detection, and works remarkably well in challenging scenarios when many candidate speakers or only small faces are on-screen
Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. Although this strategy can be enough for addressing single-speaker scenarios, it prevents accurate detection when the task is to identify who of many candidate speakers are talking. This paper introduces the Active S...More
PPT (Upload PPT)