Semantic Frames and Visual Scenes: Learning Semantic Role Inventories from Image and Video Descriptions.
Ekaterina ShutovaAndreas WundsamHelen YannakoudakisPublished in: *SEM (2017)
Keyphrases
- semantic roles
- visual scene
- input image
- image data
- visual context
- image collections
- multiscale
- image content
- video frames
- image classification
- low level
- image retrieval
- image features
- video sequences
- high level
- real time
- spatial information
- eye tracking
- image structure
- image regions
- spatial relations
- key frames
- domain ontology
- video data
- search engine