Multimodal active speaker detection using cross-attention and contextual information.

Bogdan Mocanu Ruxandra Tapu

Published in: ICCE (2024)

Keyphrases

contextual information
context aware
audio visual
spatial context
high level
multi modal
visual data
social context
semantic information
object detection
computer vision
contextual knowledge
context aware recommendation
context awareness
contextual features
higher order
user context