Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps.
Pingping ZhangWei LiuDong WangYinjie LeiHongyu WangHuchuan LuPublished in: Pattern Recognit. (2020)
Keyphrases
- object tracking
- spatial temporal
- saliency map
- multiscale
- natural images
- video sequences
- visual attention
- video frames
- spatial and temporal
- temporal information
- video shots
- mean shift
- particle filter
- image sequences
- input image
- spatio temporal
- appearance model
- moving objects
- human visual system
- action recognition
- computer vision
- visual features
- sparse representation
- partial occlusion
- image representation
- human actions
- feature points
- space time
- video data
- video streams
- spatial information
- image processing
- eye movements
- image content
- contextual information
- higher order
- feature extraction
- low level features
- high level
- multimedia