MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding.

Quan Kong Ziming Wu Ziwei Deng Martin Klinkigt Bin Tong Tomokazu Murakami

Published in: ICCV (2019)

Keyphrases

human actions
cross modal
action recognition
visual data
multi modal
spatio temporal
space time
human activities
human motion
visual features
video sequences
activity recognition
image retrieval
bag of words
multimedia retrieval
visual similarity
object detection
data sets
information retrieval