Encoding Feature Maps of CNNs for Action Recognition

Xiaojiang Peng 1 Cordelia Schmid 1
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.
Type de document :
Autre publication
CVPR'15 International Workshop and Competition on Action Recognition with a Large Number of Classes. 2015
Liste complète des métadonnées


https://hal.inria.fr/hal-01236843
Contributeur : Thoth Team <>
Soumis le : jeudi 10 décembre 2015 - 16:43:43
Dernière modification le : lundi 21 décembre 2015 - 12:02:39
Document(s) archivé(s) le : samedi 29 avril 2017 - 02:32:32

Fichier

thumos15_f2_xpeng.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01236843, version 1

Collections

Citation

Xiaojiang Peng, Cordelia Schmid. Encoding Feature Maps of CNNs for Action Recognition. CVPR'15 International Workshop and Competition on Action Recognition with a Large Number of Classes. 2015. <hal-01236843>

Partager

Métriques

Consultations de
la notice

781

Téléchargements du document

717