Head Pose Estimation Based on Multivariate Label Distribution

Geng, Xin; Xia, Yu

doi:10.1109/cvpr.2014.237

Cited by 138 publications

(47 citation statements)

References 16 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…μ y l x , can be viewed as a label distribution over the label spaceỸ. For label distribution learning (LDL) [10], [11], [12], the distribution information 1 In other words, given two instances {x, z} and two labels {y l , ym}, based on RLI degree we are only modeling and interested in the relative magnitude between μ is assumed to be available while for multi-label learning the RLI information needs to be further inferred. In this paper, RELIAB learns from multi-label data in two basic stages, i.e.…”

Section: The Reliab Approachmentioning

confidence: 99%

Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-label Learning

Zhang

Geng

2015

2015 IEEE International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

In multi-label learning, each training example is represented by a single instance while associated with multiple labels, and the task is to predict a set of relevant labels for the unseen instance. Existing approaches learn from multi-label data by assuming equal labeling-importance, i.e. all the associated labels are regarded to be relevant while their relative importance for the training example are not differentiated. Nonetheless, this assumption fails to reflect the fact that the importance degree of each associated label is generally different, though the importance information is not explicitly accessible from the training examples. In this paper, we show that effective multi-label learning can be achieved by leveraging the implicit relative labeling-importance (RLI) information. Specifically, RLI degrees are formalized as multinomial distribution over the label space, which are estimated by adapting an iterative label propagation procedure. After that, the multi-label prediction model is learned by fitting the estimated multinomial distribution as regularized with popular multi-label empirical loss. Comprehensive experiments clearly validate the usefulness of leveraging implicit RLI information to learn from multi-label data.

show abstract

Section: The Reliab Approachmentioning

confidence: 99%

Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-label Learning

Zhang

Geng

2015

2015 IEEE International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…In Table 2 we list the performance of other recent methods, as reported in [13] for yaw angles. The comparison shows that we achieve state-of-the art performance with the pixel-based segmentation method for both MAE and accuracy metrics, while we rank third when switching to the superpixel-based approach.…”

Section: Resultsmentioning

confidence: 99%

“…Multivariate Label Distribution (MLD) [13] is a state of the art algorithm which uses HOG features and introduces the idea of soft labels: rather than explicit hard labels, every image is associated with a label distribution. To the best of our knowledge, this is the best performing method to date.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Head pose estimation through multi-class face segmentation

Khan

Mauro²,

Migliorati

et al. 2017

2017 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

The aim of this work is to explore the usefulness of face semantic segmentation for head pose estimation. We implement a multi-class face segmentation algorithm and we train a model for each considered pose. Given a new test image, the probabilities associated to face parts by the different models are used as the only information for estimating the head orientation. A simple algorithm is proposed to exploit such probabilites in order to predict the pose. The proposed scheme achieves competitive results when compared to most recent methods, according to mean absolute error and accuracy metrics. Moreover, we release and make publicly available a face segmentation dataset 1 consisting of 294 images belonging to 13 different poses, manually labeled into six semantic regions, which we used to train the segmentation models.

show abstract

“…In most previous work [Geng, 2016;Geng and Xia, 2014;Geng et al, 2013], the description degree is regarded as a form of conditional probability, i.e., d y x = P (y|x), and a parametric model p(y|x; θ) is learned. However, there is some correlation among the labels in this work, e.g., when one rater gives a certain rating, it is highly possible that the other raters will give the ratings similar to the former rating; take the absolute rating into consideration, one rater may rate slightly different because of the order of showing pictures or some other influence factors that mentioned before.…”

Section: Structural Label Distribution Learningmentioning

confidence: 99%

Sense Beauty by Label Distribution Learning

Ren¹,

Geng²

2017

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Beauty is always an attractive topic in the human society, not only artists and psychologists, but also scientists have been searching for an answer -what is beautiful. This paper presents an approach to learning the human sense toward facial beauty. Different from previous study, the human sense is represented by a label distribution, which covers the full range of beauty ratings and indicates the degree to which each beauty rating describes the face. The motivation is that the human sense of beauty is generally quite subjective, thus it might be inappropriate to represent it with a single scalar, as most previous work does. Therefore, we propose a method called Beauty Distribution Transformation (BDT) to covert the k-wise ratings to label distributions and propose a learning method called Structural Label Distribution Learning (SLDL) based on structural Support Vector Machine to learn the human sense of facial beauty.

show abstract

Head Pose Estimation Based on Multivariate Label Distribution

Abstract: Abstract

Cited by 138 publications

References 16 publications

Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-label Learning

Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-label Learning

Head pose estimation through multi-class face segmentation

Sense Beauty by Label Distribution Learning

Contact Info

Product

Resources

About