DeepSafety: Multi-level Audio-Text Feature Extraction and Fusion Approach for Violence Detection in Conversations.
Amna AnwarEiman KanjoDario Ortega AnderezPublished in: CoRR (2022)
Keyphrases
- feature extraction
- text graphics
- detection algorithm
- preprocessing
- information retrieval
- frequency domain
- soccer video
- object detection
- text mining
- event detection
- feature extraction and classification
- false positives
- feature fusion
- multimedia
- video recordings
- frequency analysis
- text to speech
- information fusion
- conversational speech
- spoken documents
- multi modal fusion
- data fusion
- signal processing
- feature set
- feature vectors
- face recognition
- speaker identification
- iris recognition
- extracted features
- cepstral features
- cross media retrieval
- feature selection