MSRC: multimodal spatial regression with semantic context for phrase grounding.

Kan Chen Rama Kovvuri Jiyang Gao Ram Nevatia

Published in: Int. J. Multim. Inf. Retr. (2018)

Keyphrases

semantic context
video annotation
visual information
multi modal
discriminative power
visual words
high level semantics
spatial information
co occurrence
visual features
video search
keywords
low level
low level features