Unsupervised Novelty Detection in Video with Adversarial Autoencoder Based on Non-Euclidean Space.
Jin-Young KimSung-Bae ChoPublished in: SITIS (2019)
Keyphrases
- novelty detection
- null space
- text filtering
- space time
- anomaly detection
- sentence level
- multimedia
- concept drift
- video frames
- video sequences
- video data
- low dimensional
- semi supervised
- data sets
- multi dimensional scaling
- minimum volume
- support vector data description
- vector space
- video content
- riemannian manifolds
- high dimensional