The THUMOS challenge on action recognition for videos "in the wild".
Haroon IdreesAmir Roshan ZamirYu-Gang JiangAlex GorbanIvan LaptevRahul SukthankarMubarak ShahPublished in: Comput. Vis. Image Underst. (2017)
Keyphrases
- action recognition
- human actions
- video dataset
- action classification
- recognition of human actions
- recognizing human actions
- ucf sports
- human activities
- static images
- view invariant
- motion features
- spatio temporal interest points
- action detection
- recognizing actions
- space time interest points
- activity recognition
- human detection
- action recognition in videos
- bag of words
- mid level features
- spatial temporal
- body parts
- human object interactions
- bag of features
- motion capture data
- human pose
- motion history images
- computer vision
- mid level
- view invariant action recognition
- depth sensors
- video surveillance
- spatio temporal
- video sequences
- action primitives
- max margin
- low level descriptors
- human motion
- key frames
- machine learning