Do Textual Descriptions Help Action Recognition?

Matteo Bruni Tiberio Uricchio Lorenzo Seidenari Alberto Del Bimbo

Published in: ACM Multimedia (2016)

Keyphrases

action recognition
textual descriptions
bag of words
semantic representation
web images
human actions
action classification
computer vision
activity recognition
metadata
recognizing human actions
semantic information
semantic concepts
keywords
multi modal
keyword queries
graph cuts
relevance feedback