An LSTM autoencoder reconstruction error, combined across X, Y, Z axes with inverse-training-error weights, distinguishes normal from abnormal gait with per-sequence AUC 0.969.
Assessment of gait normal- ity using a depth camera and mirrors
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
-
Skeleton-based Gait Index Estimation with LSTMs
An LSTM autoencoder reconstruction error, combined across X, Y, Z axes with inverse-training-error weights, distinguishes normal from abnormal gait with per-sequence AUC 0.969.