Audio-Visual Event Localization based on Cross-Modal Interacting Guidance.

Qiurui Yue Xiaoyu Wu Jiayi Gao

Published in: AIKE (2021)

Keyphrases

audio visual
cross modal
multi modal
visual data
event detection
visual information
high dimensional
image annotation
data sets
multimedia retrieval
contextual information
image retrieval
visual similarity
visual features
data management
multimedia databases
metadata