Learning two-pathway convolutional neural networks for categorizing scene images

@article{Bai2016LearningTC,
  title={Learning two-pathway convolutional neural networks for categorizing scene images},
  author={Shuang Bai and Zhaohong Li and Jianjun Hou},
  journal={Multimedia Tools and Applications},
  year={2016},
  volume={76},
  pages={16145-16162}
}
Scenes are closely related to the kinds of objects that may appear in them. Objects are widely used as features for scene categorization. On the other hand, landscapes with more spatial structures of scenes are representative of scene categories. In this paper, we propose a deep learning based algorithm for scene categorization. Specifically, we design two-pathway convolutional neural networks for exploiting both object attributes and spatial structures of scene images. Different from… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

SUN database: Large-scale scene recognition from abbey to zoo

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Recognizing indoor scenes

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

ImageNet: A large-scale hierarchical image database

  • CVPR 2009
  • 2009
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Scene labeling with LSTM recurrent neural networks

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 1 EXCERPT

A Hybrid Holistic/Semantic Approach for Scene Classification

  • 2014 22nd International Conference on Pattern Recognition
  • 2014
VIEW 1 EXCERPT

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops
  • 2014
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…