Multipath Convolutional-Recursive Neural Networks for Object Recognition

Abstract : Extracting good representations from images is essential for many computer vision tasks. While progress in deep learning shows the importance of learning hierarchical features, it is also important to learn features through multiple paths. This paper presents Multipath Convolutional-Recursive Neural Networks(M-CRNNs), a novel scheme which aims to learn image features from multiple paths using models based on combination of convolutional and recursive neural networks (CNNs and RNNs). CNNs learn low-level features, and RNNs, whose inputs are the outputs of the CNNs, learn the efficient high-level features. The final features of an image are the combination of the features from all the paths. The result shows that the features learned from M-CRNNs are a highly discriminative image representation that increases the precision in object recognition.
Type de document :
Communication dans un congrès
Zhongzhi Shi; Zhaohui Wu; David Leake; Uli Sattler. 8th International Conference on Intelligent Information Processing (IIP), Oct 2014, Hangzhou, China. Springer, IFIP Advances in Information and Communication Technology, AICT-432, pp.269-277, 2014, Intelligent Information Processing VII. 〈10.1007/978-3-662-44980-6_30〉
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01383341
Contributeur : Hal Ifip <>
Soumis le : mardi 18 octobre 2016 - 14:57:33
Dernière modification le : mardi 18 octobre 2016 - 15:08:49

Fichier

978-3-662-44980-6_30_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Xiangyang Li, Shuqiang Jiang, Xinhang Song, Luis Herranz, Zhiping Shi. Multipath Convolutional-Recursive Neural Networks for Object Recognition. Zhongzhi Shi; Zhaohui Wu; David Leake; Uli Sattler. 8th International Conference on Intelligent Information Processing (IIP), Oct 2014, Hangzhou, China. Springer, IFIP Advances in Information and Communication Technology, AICT-432, pp.269-277, 2014, Intelligent Information Processing VII. 〈10.1007/978-3-662-44980-6_30〉. 〈hal-01383341〉

Partager

Métriques

Consultations de la notice

151

Téléchargements de fichiers

84