Multipath Convolutional-Recursive Neural Networks for Object Recognition - Intelligent Information Processing VII (IIP 2014) Access content directly
Conference Papers Year : 2014

Multipath Convolutional-Recursive Neural Networks for Object Recognition

Shuqiang Jiang
  • Function : Author
  • PersonId : 990811
Xinhang Song
  • Function : Author
  • PersonId : 990812
Luis Herranz
  • Function : Author
  • PersonId : 990813
Zhiping Shi
  • Function : Author
  • PersonId : 990793

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.
Fichier principal
Vignette du fichier
978-3-662-44980-6_30_Chapter.pdf (577.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01383341 , version 1 (18-10-2016)

Licence

Attribution

Identifiers

Cite

Xiangyang Li, Shuqiang Jiang, Xinhang Song, Luis Herranz, Zhiping Shi. Multipath Convolutional-Recursive Neural Networks for Object Recognition. 8th International Conference on Intelligent Information Processing (IIP), Oct 2014, Hangzhou, China. pp.269-277, ⟨10.1007/978-3-662-44980-6_30⟩. ⟨hal-01383341⟩
128 View
257 Download

Altmetric

Share

Gmail Facebook X LinkedIn More