Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description.

Xishan Zhang Ke Gao Yongdong Zhang Dongming Zhang Jintao Li Qi Tian

Published in: CVPR (2017)

Keyphrases

high level
video sequences
video content
real time
dynamic environments
video streams
data fusion
multimedia
video frames
multi modal fusion
digital video
multimedia data
video data
data driven
low level
video surveillance
video database
computer vision
online video
multimodal fusion
neural network