Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation

Johnson, Samuel; Everingham, Mark

doi:10.5244/c.24.12

Cited by 787 publications

(670 citation statements)

References 26 publications

Supporting

Mentioning

666

Contrasting

Order By: Relevance

“…Recent pose estimation systems [15][16][17][18][19][20] have universally adopted ConvNets as their main building block, largely replacing hand-crafted features and graphical models; this strategy has yielded drastic improvements on standard benchmarks [1,21,22].…”

Section: Arxiv:160306937v2 [Cscv] 26 Jul 2016mentioning

confidence: 99%

Stacked Hourglass Networks for Human Pose Estimation

Newell

Yang

Deng

2016

Lecture Notes in Computer Science

4,259

4,081

View full text Add to dashboard Cite

Abstract. This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods. Keywords: Human Pose Estimation

show abstract

Section: Arxiv:160306937v2 [Cscv] 26 Jul 2016mentioning

confidence: 99%

Stacked Hourglass Networks for Human Pose Estimation

Newell

Yang

Deng

2016

Lecture Notes in Computer Science

4,259

4,081

View full text Add to dashboard Cite

show abstract

“…This section reports the results of our experiments on the proposed method using the Image Parse dataset [9] and the Leeds Sports Pose dataset [10]. The Image Parse dataset contains 305 images with pose annotation in total.…”

Section: Resultsmentioning

confidence: 99%

“…In contrast to our earlier work [12], [13], this paper presents additional experimental results with a larger dataset (i.e., Leeds Sports Pose [10]) and a pose estimation method using deep neural networks [11].…”

Section: Introductionmentioning

confidence: 94%

See 1 more Smart Citation

Occluded Appearance Modeling with Sample Weighting for Human Pose Estimation

Kawana

Ukita

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper proposes a method for human pose estimation in still images. The proposed method achieves occlusion-aware appearance modeling. Appearance modeling with less accurate appearance data is problematic because it adversely affects the entire training process. The proposed method evaluates the effectiveness of mitigating the influence of occluded body parts in training sample images. In order to improve occlusion evaluation by a discriminatively-trained model, occlusion images are synthesized and employed with non-occlusion images for discriminative modeling. The score of this discriminative model is used for weighting each sample in the training process. Experimental results demonstrate that our approach improves the performance of human pose estimation in contrast to base models. key words: human pose estimation, pictorial structure models, occlusion

show abstract

“…It is unlikely they will scale to extract arbitrary 3D poses. Contrary to this, in the domain of 2D pose estimation current state-of -the-art methods have been shown capable of detecting poses that are much more varied [3,8,14]. This has been achieved using generative models built around the Pictorial Structures representation [10].…”

Section: Introductionmentioning

confidence: 99%

Entropy Driven Hierarchical Search for 3D Human Pose Estimation

Daubney

Xie

2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

In this work a hierarchical approach is presented to efficiently estimate 3D pose from single images. To achieve this the body is represented as a graphical model and optimized stochastically. The use of a graphical representation allows message passing to ensure individual parts are not optimized using only local image information, but from information gathered across the entire model. In contrast to existing methods the posterior distribution is represented parametrically. A different model is used to approximate the conditional distribution between each connected part. This permits measurements of the Entropy, which allows an adaptive sampling scheme to be employed that ensures that parts with the largest uncertainty are allocated a greater proportion of the available resources. At each iteration the estimated pose is updated dependent on the Kullback Leibler (KL) divergence measured between the posterior and the set of samples used to approximate it. This is shown to improve performance and prevent over fitting when small numbers of particles are being used. A quantitative comparison is made using the HumanEva dataset that demonstrates the efficacy of the presented method.

show abstract

Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation

Cited by 787 publications

References 26 publications

Stacked Hourglass Networks for Human Pose Estimation

Stacked Hourglass Networks for Human Pose Estimation

Occluded Appearance Modeling with Sample Weighting for Human Pose Estimation

Entropy Driven Hierarchical Search for 3D Human Pose Estimation

Contact Info

Product

Resources

About