Multimodal Saliency and Fusion for Movie Summarization Based on Aural, Visual, and Textual Attention.
Georgios EvangelopoulosAthanasia ZlatintsiAlexandros PotamianosPetros MaragosKonstantinos RapantzikosGeorgios SkoumasYannis AvrithisPublished in: IEEE Trans. Multim. (2013)
Keyphrases
- visual saliency
- visual attention
- saliency map
- selective attention
- visual perception
- video summarization
- visual representations
- focus of attention
- audio visual
- visual search
- visual information
- visual features
- multi modal
- scan path
- low level
- visual processing
- saliency model
- attention mechanism
- single modality
- information fusion
- eye fixations
- multimedia
- multimodal information
- fusion method
- human visual system
- cross modal
- multimodal fusion
- multimodal biometrics
- video search
- salient regions
- visual content
- vision system
- visual field
- multimodal interaction
- multi document summarization
- visual cues
- natural scenes
- natural images