MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction.

Wang Jing Aixin Sun Hao Zhang Xiaoli Li

Published in: ACL (1) (2023)

Keyphrases

natural language
activity detection
neural network
user interaction
zernike moments
multimedia
real time
public space
video streams
video sequences
space time
monte carlo
video data
video images
video database
super resolution
multi view
higher order
knowledge representation
active learning
image sequences