Spatio-Temporal Frames in a Bag-of-Visual-Features Approach for Human Actions Recognition.
Ana Paula Brandão LopesRodrigo Silva OliveiraJussara Marques de AlmeidaArnaldo de Albuquerque AraújoPublished in: SIBGRAPI (2009)
Keyphrases
- human actions
- visual features
- key frames
- recognizing actions
- motion features
- action recognition
- image classification
- spatio temporal
- visual information
- visual content
- image retrieval
- image annotation
- low level
- image search
- image collections
- view invariant
- keywords
- human activities
- recognition of human actions
- bag of features
- global features
- activity recognition
- visual data
- low level features
- semantic concepts
- feature extraction
- action recognition in videos
- human pose
- video frames
- information retrieval
- space time
- moving objects
- video shots
- object recognition
- three dimensional
- text classification
- active learning
- face recognition
- multimedia