Saliency-Informed Spatio-Temporal Vector of Locally Aggregated Descriptors and Fisher Vectors for Visual Action Recognition.
Zheming ZuoDaniel OrganisciakHubert P. H. ShumLongzhi YangPublished in: BMVC (2018)
Keyphrases
- action recognition
- fisher vectors
- bag of features
- visual classification
- action recognition in videos
- human actions
- spatio temporal
- view invariant
- image classification
- visual features
- human detection
- activity recognition
- recognition of human actions
- bag of words
- computer vision
- person re identification
- scene classification
- visual information
- moving objects
- space time
- low level descriptors
- spatial and temporal
- saliency map
- visual words
- human activities
- low level
- object recognition
- image sequences
- multiple features
- visual attention
- image representation
- image features
- feature space