Appearance Fusion of Multiple Cues for Video Co-localization.
Koteswar Rao JerripothulaPublished in: CoRR (2020)
Keyphrases
- multiple cues
- visual cues
- video data
- visual tracking
- multimedia
- sensor fusion
- video sequences
- object tracking
- data fusion
- appearance model
- foreground regions
- video frames
- video segmentation
- low level
- key frames
- particle filter
- image fusion
- video analysis
- video surveillance
- similarity measure
- human pose
- moving camera
- human actions
- mobile robot