Scene labeling with LSTM recurrent neural networks

@article{Byeon2015SceneLW,
  title={Scene labeling with LSTM recurrent neural networks},
  author={Wonmin Byeon and Thomas M. Breuel and Federico Raue and Marcus Liwicki},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={3547-3555}
}
This paper addresses the problem of pixel-level segmentation and classification of scene images with an entirely learning-based approach using Long Short Term Memory (LSTM) recurrent neural networks, which are commonly used for sequence classification. We investigate two-dimensional (2D) LSTM networks for natural scene images taking into account the complex spatial dependencies of labels. Prior methods generally have required separate classification and image segmentation stages and/or pre- and… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 144 CITATIONS, ESTIMATED 44% COVERAGE

DeLS-3 D : Deep Localization and Segmentation with a 3 D Semantic Map

  • 2018
VIEW 13 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Hierarchically Gated Deep Networks for Semantic Segmentation

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition

  • ArXiv
  • 2018
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Deep Contextual Recurrent Residual Networks for Scene Labeling

  • Pattern Recognition
  • 2018
VIEW 6 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Learning deep representations for semantic image parsing: a comprehensive overview

  • Frontiers of Computer Science
  • 2018
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Object Detection with Deep Learning: A Review

  • IEEE transactions on neural networks and learning systems
  • 2018
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 14 Highly Influenced Citations

  • Averaged 43 Citations per year over the last 3 years

  • 16% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 21 REFERENCES

Learning Hierarchical Features for Scene Labeling

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2013
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Breuel . Supervised texture segmentation using 2 d lstm networks

M. T.
  • 2014

Coli obert . Recurrent convolutional neu ­ ral networks for scene labeling

P. Pinheiro, R.
  • 2014

Deepface : Closing the gap to humanlevel performance in face verifica ­ tion

M. Yang Y. Taigman, M. Ranzato, L. Wolf.
  • Computer Vision and Pattern Recognition
  • 2014

Supervised texture segmentation using 2D LSTM networks

  • 2014 IEEE International Conference on Image Processing (ICIP)
  • 2014
VIEW 1 EXCERPT

Texture Classification Using 2D LSTM Networks

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

Convolutional - recursive deep learning for 3 d object classifi ­ cation

B. Huval R. Socher, C. D. Manning, A. Y. Ng
  • 2012

Similar Papers

Loading similar papers…