Encoding Feature Maps of CNNs for Action Recognition

Xiaojiang Peng (1) , Cordelia Schmid (1)

1 LEAR - Learning and recognition in vision

We describe our approach for action classification in the THUMOS Challenge 2015. Our approach is based on two types of features, improved dense trajectories and CNN features. For trajectory features, we extract HOG, HOF, MBHx, and MBHy descriptors and apply Fisher vector encoding. For CNN features, we utilize a recent deep CNN model, VGG19, to capture appearance features and use VLAD encoding to encode/pool convolutional feature maps which shows better performance than average pooling of feature maps and full-connected activation features. After concatenating them, we train a linear SVM classifier for each class in a one-vs-all scheme.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Xiaojiang Peng, Cordelia Schmid. Encoding Feature Maps of CNNs for Action Recognition. 2015. ⟨hal-01236843⟩