Video-Based Human Action Recognition Using Spatial Pyramid Pooling and 3D Densely Convolutional Networks.
Wanli YangYimin ChenChen HuangMing-ke GaoPublished in: Future Internet (2018)
Keyphrases
- spatial pyramid
- image classification
- soft assignment
- image representation
- object classification
- scene recognition
- bag of words
- matching scheme
- sparse coding
- object class
- class specific
- bag of features
- visual words
- single feature
- object detection
- feature extraction
- machine learning
- multiple kernel learning
- semi supervised learning
- recognition rate
- visual vocabulary