Incorporating Audio Cues into Dialog and Action Scene Extraction.
Lei ChenShariq J. RizviM. Tamer ÖzsuPublished in: Storage and Retrieval for Media Databases (2003)
Keyphrases
- visual data
- d scene
- scene change detection
- video sequences
- multimedia
- fundamental problems in computer vision
- multimodal fusion
- image sequences
- multiple images
- depth cues
- video scene
- single image
- scene analysis
- scene understanding
- semantic context
- real scenes
- visual cues
- three dimensional
- complex scenes
- dynamic scenes
- human actions
- audio visual
- prosodic features
- object recognition
- moving objects
- information extraction
- conversational agents
- input image
- scene interpretation
- infrared
- audio signals
- visual context
- signal processing
- spoken dialog
- user interface
- visual information