MTIDNet: A Multimodal Temporal Interest Detection Network for Video Summarization.

Xiaoyan Tian Ye Jin Zhao Zhang Peng Liu Xianglong Tang

Published in: ICASSP (2024)

Keyphrases

video summarization
temporal segmentation
audio visual
event detection
video browsing
video content
multi modal
detection algorithm
temporal information
video data
video retrieval
activity recognition