An Empirical Study of CNN-LSTM on Class Imbalance Datasets for Violence Video Detection.
Moch Arief SoelemanCatur SupriyantoDwi Puji PrabowoPublished in: IC3INA (2021)
Keyphrases
- class imbalance
- imbalanced datasets
- sampling methods
- class distribution
- active learning
- cost sensitive learning
- cost sensitive
- class noise
- high dimensionality
- video sequences
- imbalanced data
- concept drift
- decision trees
- random sampling
- training dataset
- neural network
- change detection
- benchmark datasets
- class imbalanced
- high resolution