Encoding Feature Maps of CNNs for Action RecognitionReport as inadecuate




Encoding Feature Maps of CNNs for Action Recognition - Download this document for free, or read online. Document in PDF available to download.

1 LEAR - Learning and recognition in vision Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble

Abstract : 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.





Author: Xiaojiang Peng - Cordelia Schmid -

Source: https://hal.archives-ouvertes.fr/



DOWNLOAD PDF




Related documents