You-Do, I-Learn: Discovering Task Relevant Objects and their Modes of Interaction from Multi-User Egocentric Video.
Dima DamenTeesid LeelasawassukOsian HainesAndrew CalwayWalterio W. Mayol-CuevasPublished in: BMVC (2014)
Keyphrases
- multi user
- multi touch
- virtual world
- video images
- smart spaces
- augmented reality
- multi granularity
- multimedia objects
- single user
- virtual environment
- multiple users
- multimedia
- user interface
- d objects
- video data
- dynamic scenes
- human computer interaction
- video sequences
- real time
- video analysis
- video streams
- video content
- stationary camera
- moving objects
- smart objects
- image processing
- video summarization
- event detection
- visual saliency
- visual data
- virtual space
- video clips
- collaborative writing
- multiple access
- video frames
- activity recognition
- objects in video sequences