Skip to search form Skip to main content You are currently offline. Some features of the site may not work correctly. DOI: Felzenszwalb and David A. Felzenszwalb , David A.
|Published (Last):||27 October 2010|
|PDF File Size:||19.60 Mb|
|ePub File Size:||1.33 Mb|
|Price:||Free* [*Free Regsitration Required]|
Skip to Main Content. A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. Use of this web site signifies your agreement to the terms and conditions. Personal Sign In.
It also outperforms the best results in the challenge in ten out of twenty categories. The system relies heavily on deformable parts. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL challenge.
Our system also relies heavily on new methods for discriminative training. We combine a margin-sensitive approach for data mining hard negative examples with a formalism we call latent SVM. However, a latent SVM is semi-convex and the training problem becomes convex once latent information is specified for the positive examples.
We believe that our training methods will eventually make possible the effective use of more latent information such as hierarchical grammar models and models involving latent three dimensional pose. Article :. DOI: Need Help?
A discriminatively trained, multiscale, deformable part model