Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning.

Zhihao Fan Zhongyu Wei Siyuan Wang Xuanjing Huang

Published in: ACL (1) (2019)

Keyphrases

visual vocabulary
visual information
visual categorization
visual features
visual appearance
data sets
low level
construction process
visual tasks
e learning
case study
information technology
hidden markov models
visual words
visual representation
concept detectors