Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web.
Shugao MaSarah Adel BargalJianming ZhangLeonid SigalStan SclaroffPublished in: CoRR (2015)
Keyphrases
- action recognition
- human actions
- action classification
- recognizing human actions
- recognizing actions
- static images
- mid level
- bag of features
- recognition of human actions
- action detection
- view invariant
- activity recognition
- video dataset
- bag of words
- body parts
- web images
- image collections
- three dimensional
- human pose
- human detection
- image annotation
- test images
- input image
- object recognition
- computer vision
- image features
- image retrieval
- low level descriptors
- image classification
- low level
- action recognition in videos
- space time interest points