Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images.

Junhua Mao Jiajing Xu Yushi Jing Alan L. Yuille

Published in: CoRR (2016)

Keyphrases

annotated images
semantic web
multi modal
co occurrence
manually annotated
image annotation
ground truth
feature space
supervised learning
keywords
computer vision
dimensionality reduction
image classification
training set
training examples
high quality
web pages