Encoding Feature Maps of CNNs for Action Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Other Publications Year : 2015

Encoding Feature Maps of CNNs for Action Recognition

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.
Fichier principal
Vignette du fichier
thumos15_f2_xpeng.pdf (305.56 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01236843 , version 1 (10-12-2015)

Identifiers

  • HAL Id : hal-01236843 , version 1

Cite

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

Share

Gmail Facebook Twitter LinkedIn More