Leveraging semantic saliency maps for query-specific video summarization.
Kemal CizmecilerErkut ErdemAykut ErdemPublished in: Multim. Tools Appl. (2022)
Keyphrases
- video summarization
- saliency map
- low level features
- visual attention model
- query specific
- visual saliency
- video frames
- visual attention
- higher level
- video content
- audio visual
- high level
- visual features
- query expansion
- semantic information
- low level
- video data
- relevance feedback
- key frames
- image representation
- event detection
- surveillance videos
- human visual system
- visual information
- semantic similarity
- input image
- image retrieval
- image annotation
- language model
- object recognition
- natural images
- video retrieval
- video sequences
- wordnet
- video surveillance
- training set
- multiscale