Discriminative model

Known as: Conditional model 
Discriminative models, also called conditional models, are a class of models used in machine learning for modeling the dependence of an unobserved… (More)
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2016
Highly Cited
2016
This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and… (More)
  • figure 2
  • figure 3
  • figure 4
  • table 1
  • figure 5
Is this relevant?
Highly Cited
2011
Highly Cited
2011
Person re-identification, i.e., recognizing a single person across spatially disjoint cameras, is an important task in visual… (More)
Is this relevant?
Highly Cited
2008
Highly Cited
2008
This paper describes a discriminatively trained, multiscale, deformable part model for object detection. Our system achieves a… (More)
Is this relevant?
Highly Cited
2008
Highly Cited
2008
We present a modified form of the maximum mutual information (MMI) objective function which gives improved results for… (More)
  • table 1
  • table 3
  • table 4
  • table 2
  • table 5
Is this relevant?
Highly Cited
2005
Highly Cited
2005
  • Zhuowen Tu
  • Tenth IEEE International Conference on Computer…
  • 2005
In this paper, a new learning framework - probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 5
  • figure 6
Is this relevant?
Highly Cited
2004
Highly Cited
2004
Discriminative models have been preferred over generative models in many machine learning problems in the recent past owing to… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
Highly Cited
2003
Highly Cited
2003
In this work we present Discriminative Random Fields (DRFs), a discriminative framework for the classification o f image regions… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table 1
Is this relevant?
Highly Cited
2003
Highly Cited
2003
Although discriminatively trained classifiers are usually more accurate when labeled training data is abundant, previous work has… (More)
  • figure 1
  • figure 2
Is this relevant?
Highly Cited
2002
Highly Cited
2002
In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not… (More)
  • figure 1
  • figure 3
  • figure 2
  • table 1
Is this relevant?
Highly Cited
1998
Highly Cited
1998
Discriminative model combination is a new approach in the field of automatic speech recognition, which aims at an optimal… (More)
  • table 1
Is this relevant?