Semantic-Driven Saliency-Context Separation for Video Captioning.

Heming Jing Yuejie Zhang Rui Feng Rui-Wei Zhao Tao Zhang Xuequan Lu Shang Gao

Published in: ICME (2022)

Keyphrases

video surveillance
video event
video annotation
semantic context
context dependent
object recognition
semantic web
data driven
semantic annotation
higher level
visual attention
video content
temporal information
video clips
semantic search
salient regions
multimedia