M3sum: A Novel Unsupervised Language-Guided Video Summarization.

Hongru Wang Baohang Zhou Zhengkun Zhang Yiming Du David Ho Kam-Fai Wong

Published in: ICASSP (2024)

Keyphrases

video summarization
audio visual
event detection
video content
video browsing
video sequences
video summaries
key frames
video data
natural language
video retrieval
surveillance videos
semi supervised
video frames
real time
image data