Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos.

De-An Huang Joseph J. Lim Li Fei-Fei Juan Carlos Niebles

Published in: CVPR (2017)

Keyphrases

reference resolution
instructional videos
referring expressions
natural language processing
relation extraction

visual information
semi supervised
visual features
visual content
natural language text

named entity recognition
coreference resolution
unsupervised learning
automatic extraction

artificial intelligence
content analysis
information extraction
low level