Multi-Modal Scene Duplicate Detection from News Videos Focusing on Human Faces.
Haruka KumagaiIchiro IdeHiroshi MuraseKeisuke DomanDaisuke DeguchiPublished in: Int. J. Semantic Comput. (2015)
Keyphrases
- multi modal
- duplicate detection
- human faces
- news video
- facial expressions
- face detection
- face recognition
- video sequences
- face images
- video database
- high dimensional
- video shots
- news stories
- semantic concepts
- video content
- feature points
- image sequences
- three dimensional
- video frames
- video search
- machine learning
- image regions
- moving objects
- key frames
- image annotation
- video data
- visual features
- information extraction
- feature extraction
- database