Audio-visual annotation graphs for guiding lens-based scene exploration.
Moonisa AhsanFabio MartonRuggero PintusEnrico GobbettiPublished in: Comput. Graph. (2022)
Keyphrases
- audio visual
- visual data
- multi modal
- video scene
- visual information
- temporal context
- video sequences
- video summarization
- multimedia
- three dimensional
- person authentication
- audio visual speech recognition
- metadata
- multi stream
- image sequences
- image annotation
- contextual information
- high dimensional
- input image
- moving objects
- human actions
- visual features
- low level
- image data
- multimedia data
- feature space
- data analysis
- object recognition
- data sets