CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition.

Lantian Li Xiaolou Li Haoyu Jiang Chen Chen Ruihai Hou Dong Wang

Published in: CoRR (2023)

Keyphrases

feature extraction
audio visual
multi modal
visual information
feature set
video summarization
image classification
multimedia
visual data
pattern recognition
multi stream
person authentication
audio visual speech recognition
computer vision
audio features
object recognition
low level
data analysis