Scale Coding Bag of Deep Features for Human Attribute and Action Recognition
Mach. Vis. Appl., Volume abs/1612.04884, Issue 1, 2018.
Action recognitionAttribute recognitionBag of deep features
Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed a...More
Full Text (Upload PDF)
PPT (Upload PPT)