Improving Audio-Visual Segmentation with Bidirectional Generation.

Dawei Hao Yuxin Mao Bowen He Xiaodong Han Yuchao Dai Yiran Zhong

Published in: CoRR (2023)

Keyphrases

audio visual
multi modal
temporal segmentation
visual information
multi stream
image segmentation
multimedia
video summarization
multiscale
visual data
emotion recognition
temporal context
person authentication
audio visual speech recognition
image database
multimodal fusion