A recurrent memory module runs self-attention inside sliding temporal blocks and feeds the result back into an LSTM, improving accuracy on action recognition and sentiment analysis.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Non-local Recurrent Neural Memory for Supervised Sequence Modeling
A recurrent memory module runs self-attention inside sliding temporal blocks and feeds the result back into an LSTM, improving accuracy on action recognition and sentiment analysis.