Representing visual appearance by video Brownian covariance descriptor for human action recognition.
Piotr Tadeusz BilinskiMichal KoperskiSlawomir BakFrançois BrémondPublished in: AVSS (2014)
Keyphrases
- visual appearance
- action recognition
- human actions
- visual features
- visual content
- human pose
- video sequences
- key frames
- video content
- image retrieval
- video data
- video streams
- space time
- multimedia
- video retrieval
- video frames
- multimedia data
- keypoints
- video surveillance
- computer vision
- spatial and temporal
- text classification
- image classification
- low level
- random fields
- object recognition
- feature extraction