Two-layers re-ranking approach based on contextual information for visual concepts detection in videos.
Abdelkader HamadiGeorges QuénotPhilippe MulhemPublished in: CBMI (2012)
Keyphrases
- contextual information
- visual concepts
- visual data
- video content
- video annotation
- concept detectors
- context aware
- semantic concepts
- visual content
- video sequences
- video frames
- object categories
- high level
- video search
- object detection
- visual features
- semantic information
- video retrieval
- key frames
- image content
- image collections
- natural language processing
- video data
- semantic gap
- d objects
- mobile devices
- concept detection