Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation

Ning, Guanghan; Zhi, Zhang; He, Zhihai

doi:10.48550/arxiv.1705.02407

Cited by 5 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Chu et al 2016b;2016a) creatively pointed out that exploring the relationships between feature maps of joints was more beneficial than modeling structures on score maps, because the former preserved substantially richer descriptions of body joints. To impose prior, (Ning, Zhang, and He 2017) introduced the learned projections with a fractal network. Furthermore, (Chen et al 2017) and (Chou, Chien, and Chen 2017) performed a generative adversarial network to better capture the structure dependency.…”

Section: Related Workmentioning

confidence: 99%

A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation

Chen

et al. 2018

AAAI

View full text Add to dashboard Cite

Accurate keypoint localization of human pose needs diversified features: the high level for contextual dependencies and the low level for detailed refinement of joints. However, the importance of the two factors varies from case to case, but how to efficiently use the features is still an open problem. Existing methods have limitations in preserving low level features, adaptively adjusting the importance of different levels of features, and modeling the human perception process. This paper presents three novel techniques step by step to efficiently utilize different levels of features for human pose estimation. Firstly, an inception of inception (IOI) block is designed to emphasize the low level features. Secondly, an attention mechanism is proposed to adjust the importance of individual levels according to the context. Thirdly, a cascaded network is proposed to sequentially localize the joints to enforce message passing from joints of stand-alone parts like head and torso to remote joints like wrist or ankle. Experimental results demonstrate that the proposed method achieves the state-of-the-art performance on both MPII and LSP benchmarks.

show abstract

Section: Related Workmentioning

confidence: 99%

A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation

Chen

et al. 2018

AAAI

View full text Add to dashboard Cite

show abstract

“…MPII Human Pose [1] for instance, is a dataset specifically designed for 2D human pose estimation containing 25, 000 images with over 40, 000 people with annotated body joints. Many human pose estimators make use of this rich dataset and achieve impressive results with average accuracies around 90% [21,3,20,4]. All of the mentioned deep learning approaches work on single color images and estimate 2D human poses.…”

Section: Human Pose Estimationmentioning

confidence: 99%

Vision-Based Fallen Person Detection for the Elderly

Solbach¹,

Tsotsos²

2017

Preprint

View full text Add to dashboard Cite

Falls are serious and costly for elderly people. The Centers for Disease Control and Prevention of the US reports that millions of older people, 65 and older, fall each year at least once. Serious injuries such as; hip fractures, broken bones or head injury, are caused by 20% of the falls. The time it takes to respond and treat a fallen person is crucial. With this paper we present a new , non-invasive system for fallen people detection. Our approach uses only stereo camera data for passively sensing the environment. The key novelty is a human fall detector which uses a CNN based human pose estimator in combination with stereo data to reconstruct the human pose in 3D and estimate the ground plane in 3D. Furthermore, our system consists of a reasoning module which formulates a number of measures to reason whether a person is fallen. We have tested our approach in different scenarios covering most activities elderly people might encounter living at home. Based on our extensive evaluations, our systems shows high accuracy and almost no miss-classification. To reproduce our results, the implementation is publicly available to the scientific community.

show abstract

“…Multiperson Pose Estimation Recent methods have made great progress improving human pose estimation in images in particular for single person pose estimation [50,48,52,40,8,5,41,4,14,19,34,26,7,49,44]. For multiperson pose, prior and concurrent work can be categorized as either top-down or bottom-up.…”

Section: Related Workmentioning

confidence: 99%

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Newell¹,

Huang²,

Deng³

2016

Preprint

View full text Add to dashboard Cite

We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-person pose estimation, instance segmentation, and multi-object tracking. Usually the grouping of detections is achieved with multi-stage pipelines, instead we propose an approach that teaches a network to simultaneously output detections and group assignments. This technique can be easily integrated into any state-of-the-art network architecture that produces pixel-wise predictions. We show how to apply this method to both multi-person pose estimation and instance segmentation and report state-of-the-art performance for multi-person pose on the MPII and MS-COCO datasets.

show abstract

Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation

Cited by 5 publications

References 0 publications

A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation

A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation

Vision-Based Fallen Person Detection for the Elderly

Associative Embedding: End-to-End Learning for Joint Detection and Grouping

Contact Info

Product

Resources

About