Visual Attention Model for Name Tagging in Multimodal Social Media.
Di LuLeonardo NevesVitor CarvalhoNing ZhangHeng JiPublished in: ACL (1) (2018)
Keyphrases
- visual attention model
- social media
- visual attention
- biologically inspired
- saliency map
- video abstraction
- video summarization
- human perception
- audio visual
- social networks
- multi modal
- eye tracking
- similarity measurement
- metadata
- image processing
- information retrieval
- real time
- human visual system
- high frequency
- vision system
- video sequences
- feature extraction
- salient regions
- computer vision