Top-down attention recurrent VLAD encoding for action recognition in videos.

Swathikiran Sudhakaran Oswald Lanz

Published in: Intelligenza Artificiale (2019)

Keyphrases

action recognition in videos
action recognition
image search
feed forward
human actions
recurrent neural networks
multi unit combinatorial auctions
spatio temporal
variable length
data sets
search engine
artificial neural networks
image coding
encoding scheme
fractal image compression
encoding schemes