A mixed generative-discriminative framework for pedestrian classification

@article{Enzweiler2008AMG,
  title={A mixed generative-discriminative framework for pedestrian classification},
  author={M. Enzweiler and D. Gavrila},
  journal={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2008},
  pages={1-8}
}
  • M. Enzweiler, D. Gavrila
  • Published 2008
  • Mathematics, Computer Science
  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
This paper presents a novel approach to pedestrian classification which involves utilizing the synthesized virtual samples of a learned generative model to enhance the classification performance of a discriminative model. Our generative model captures prior knowledge about the pedestrian class in terms of a number of probabilistic shape and texture models, each attuned to a particular pedestrian pose. Active learning provides the link between the generative and discriminative model, in the… Expand
106 Citations
Integrated pedestrian classification and orientation estimation
  • M. Enzweiler, D. Gavrila
  • Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
  • 88
  • PDF
Pedestrian detection by scene dependent classifiers with generative learning
  • 3
  • PDF
Integration of Generative Learning and Multiple Pose Classifiers for Pedestrian Detection
  • 5
  • Highly Influenced
  • PDF
Multi-stage Contextual Deep Learning for Pedestrian Detection
  • 137
  • PDF
Learning a multiview part-based model in virtual world for pedestrian detection
  • 5
  • PDF
Virtual and Real World Adaptation for Pedestrian Detection
  • 158
  • PDF
Spatiotemporal Stacked Sequential Learning for Pedestrian Detection
  • 11
  • PDF
Learning appearance in virtual scenarios for pedestrian detection
  • 176
  • Highly Influenced
  • PDF
Contextual boost for pedestrian detection
  • Yuanyuan Ding, J. Xiao
  • Computer Science
  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
  • 75
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
A Generative-Discriminative Hybrid Method for Multi-View Object Detection
  • DongQing Zhang, S. Chang
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
  • 23
  • PDF
Learning Generative Models via Discriminative Approaches
  • Zhuowen Tu
  • Computer Science
  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
  • 100
  • PDF
Generative versus discriminative methods for object recognition
  • 190
  • PDF
Principled Hybrids of Generative and Discriminative Models
  • 315
  • PDF
An Experimental Study on Pedestrian Classification
  • S. Munder, D. Gavrila
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2006
  • 617
  • PDF
Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification
  • 98
  • PDF
Active Learning with Gaussian Processes for Object Categorization
  • 309
  • PDF
A Trainable System for Object Detection
  • 1,355
  • Highly Influential
  • PDF
Pedestrian detection in crowded scenes
  • B. Leibe, E. Seemann, B. Schiele
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
  • 889
  • PDF
Virtual sample generation for template-based shape matching
  • D. Gavrila, J. Giebel
  • Mathematics, Computer Science
  • Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
  • 42
...
1
2
3
4
...