Head pose estimation: Classification or regression?

Guo, Guodong; Fu, Yun; Dyer, Charles R.; Huang, Thomas S.

doi:10.1109/icpr.2008.4761081

Cited by 37 publications

(37 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since we are using the labels to define the neighborhood, this is a supervised enforcement of the data manifold constraint. Enforcing the manifold constraints have been shown to highly improve regression results in many applications [3,18,25,9]. However all these applications used vectorized representations of the raw intensity.…”

Section: Enforcing Manifold Locality Constraintmentioning

confidence: 99%

See 1 more Smart Citation

Regression from local features for viewpoint and pose estimation

Torki

Elgammal

2011

2011 International Conference on Computer Vision

View full text Add to dashboard Cite

In this paper we propose a framework for learning a regression function form a set of local features in an image. The regression is learned from an embedded representation that reflects the local features and their spatial arrangement as well as enforces supervised manifold constraints on the data. We applied the approach for viewpoint estimation on a Multiview car dataset, a head pose dataset and arm posture dataset. The experimental results show that this approach has superior results (up to 67% improvement) to the state-of-the-art approaches in very challenging datasets .

show abstract

Section: Enforcing Manifold Locality Constraintmentioning

confidence: 99%

“…In many of these problems, a regression function is learned from a vectorized representation of the input. For example, in head pose estimation, researchers typically learn regression from vectorized representation of the raw image intensity, e.g., [14,3,8,25,9].…”

Section: Introductionmentioning

confidence: 99%

Regression from local features for viewpoint and pose estimation

Torki

Elgammal

2011

2011 International Conference on Computer Vision

View full text Add to dashboard Cite

show abstract

“…The second is denoted by MLD-wJ, which uses the inter-pose weights defined by Eq. (6) The MLD methods are compared via five-fold crossvalidation with several state-of-the-art head pose estimation methods including linear/kernel PLS [11], linear/kernel SVM and linear/kernel SVR [9]. For each compared method, several parameter configurations are tested and the best performance is reported.…”

Section: Methodsmentioning

confidence: 99%

“…As a result, head pose estimation has become an important application of computer vision and pattern recognition. Accordingly, a lot of head pose estimation methods have been proposed in recent years, such as the nonlinear regression methods [17,8,19,9,11], the subspace embedding methods [18,12,4,14], and the special-feature-based methods [10,20,2,15].…”

Section: Introductionmentioning

confidence: 99%

Head Pose Estimation Based on Multivariate Label Distribution

Geng¹,

Xia

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

138

View full text Add to dashboard Cite

show abstract

“…Examples of such problems include age estimation from facial images [10,12,15,16,33,35], crowd counting [4,5,8,25], and human body/face pose (view angle) estimation [14,27,34]. Such a scalar value can vary continuously within a certain range but is often assumed to be discrete (e.g.…”

Section: Introductionmentioning

confidence: 99%