Discriminative Feature Learning for Video Semantic Segmentation

@article{Zhang2014DiscriminativeFL,
  title={Discriminative Feature Learning for Video Semantic Segmentation},
  author={Han Zhang and Kai Jiang and Yu Zhang and Qing Zhang Li and Changqun Xia and Xiaowu Chen},
  journal={2014 International Conference on Virtual Reality and Visualization},
  year={2014},
  pages={321-326}
}
In this paper, we propose a novel deep learning based method for video semantic segmentation. Specially, we utilize 3D convolution neural network (3D CNN) to learn discriminative hierarchical features from spatial-temporal volumes for accurate pixel labelling. The learned features are capable of capturing both appearance and motion information. To align the pixel labels along real object boundaries, as well as maintain local consistency, we further perform graph-cut on a graph constructed on… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 26 references

Semi-supervised video segmentation using tree structured graphical models.

IEEE transactions on pattern analysis and machine intelligence • 2013
View 6 Excerpts
Highly Influenced

Temporally consistent multi-class video-object segmentation with the Video Graph-Shifts algorithm

2011 IEEE Workshop on Applications of Computer Vision (WACV) • 2011
View 6 Excerpts
Highly Influenced

Label propagation in video sequences

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition • 2010
View 4 Excerpts
Highly Influenced

Propagating multi-class pixel labels throughout video frames

2010 Western New York Image Processing Workshop • 2010
View 4 Excerpts
Highly Influenced

Efficient Multilevel Brain Tumor Segmentation With Integrated Bayesian Model Classification

IEEE Transactions on Medical Imaging • 2008
View 4 Excerpts
Highly Influenced

Bilayer Segmentation of Live Video

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) • 2006
View 4 Excerpts
Highly Influenced

A Video Representation Using Temporal Superpixels

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013
View 3 Excerpts

Learning Hierarchical Features for Scene Labeling

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2013
View 2 Excerpts