A naive mid-level concept-based fusion approach to violence detection in Hollywood movies.
Bogdan IonescuJan SchlüterIonut MironicaMarkus SchedlPublished in: ICMR (2013)
Keyphrases
- mid level
- action recognition
- low level
- event detection
- low level features
- high level
- levels of abstraction
- superpixels
- visual information
- text categorization
- bag of words
- visual concepts
- visual cues
- computer vision
- video data
- activity recognition
- information retrieval
- semantic information
- feature space
- video sequences