What the Appearance Channel from Two-Stream Architectures for Activity Recognition Is Learning?
Sign Up to like & getrecommendations! Published in 2020 at "Pattern Recognition"
DOI: 10.1007/978-3-030-49076-8_24
Abstract: The automatic recognition of human activities from video data is being led by spatio-temporal Convolutional Neural Networks (3D CNNs), in particular two-stream architectures such as I3D that reports the best accuracy so far. Despite the… read more here.
Keywords: activity recognition; two stream; recognition; activity ... See more keywords