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

Junhua Mao Jiajing Xu Yushi Jing Alan L. Yuille

Published in: NIPS (2016)

Keyphrases

annotated images
manually annotated
semantic web
ground truth
web pages
training set
image annotation
feature extraction
multi modal
multimedia
machine learning
supervised learning
co occurrence
domain specific
face recognition
semi supervised learning
web images