Hand Pose Ensemble Learning Based on Grouping Features of Hand Point Sets

Zhu, Tianqiang; Sun, Yi; Ma, Xiaohong; Lin, Xiangbo

doi:10.1109/iccvw.2019.00347

Cited by 5 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moon et al [23] converted the 3D hand and human pose estimation problem from a depth map to a voxel-to-voxel prediction, which used a 3D voxelized grid and estimated the per-voxel likelihood of each key-point. Zhu et al [24] used the point set method, proposed an adaptive pooling for the network to select features by itself, and proposed an integration strategy that made total use of hand features. Moreover, Rong et al [7] used Fourier descriptors to recover the depth information of hand gestures from the depth map.…”

Section: Related Workmentioning

confidence: 99%

InterNet+: A Light Network for Hand Pose Estimation

Liu

Jiang

Sun

et al. 2021

Sensors

View full text Add to dashboard Cite

Hand pose estimation from RGB images has always been a difficult task, owing to the incompleteness of the depth information. Moon et al. improved the accuracy of hand pose estimation by using a new network, InterNet, through their unique design. Still, the network still has potential for improvement. Based on the architecture of MobileNet v3 and MoGA, we redesigned a feature extractor that introduced the latest achievements in the field of computer vision, such as the ACON activation function and the new attention mechanism module, etc. Using these modules effectively with our network, architecture can better extract global features from an RGB image of the hand, leading to a greater performance improvement compared to InterNet and other similar networks.

show abstract

Section: Related Workmentioning

confidence: 99%

InterNet+: A Light Network for Hand Pose Estimation

Liu

Jiang

Sun

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Zhu et al [103] utilized a modified version of the PointNet++ [104] architecture, as well as an ensemble strategy, where they proposed n possible poses for a hand point cloud and weighted them, in order to get the final predicted 3D joint locations. They also presented a data augmentation method that divided the hand point cloud into 16 parts based on Euler distance and then bent the fingers according to kinematics constraints, thus creating a new gesture.…”

Section: D Representation Utilizationmentioning

confidence: 99%

A Comprehensive Study on Deep Learning-Based 3D Hand Pose Estimation Methods

et al. 2020

View full text Add to dashboard Cite

The field of 3D hand pose estimation has been gaining a lot of attention recently, due to its significance in several applications that require human-computer interaction (HCI). The utilization of technological advances, such as cost-efficient depth cameras coupled with the explosive progress of Deep Neural Networks (DNNs), has led to a significant boost in the development of robust markerless 3D hand pose estimation methods. Nonetheless, finger occlusions and rapid motions still pose significant challenges to the accuracy of such methods. In this survey, we provide a comprehensive study of the most representative deep learning-based methods in literature and propose a new taxonomy heavily based on the input data modality, being RGB, depth, or multimodal information. Finally, we demonstrate results on the most popular RGB and depth-based datasets and discuss potential research directions in this rapidly growing field.

show abstract

“…Ensemble learning is the process to train multiple models and combine into a single result. The spotlights to ensemble methods, even until recently from numerous application fields [1][2][3][4], are derived from their superior predictive performances compared to that of a single model. This high performance of the ensemble results primarily from the diversity of the multiple models.…”

Section: Introductionmentioning

confidence: 99%

Auxiliary Class Based Multiple Choice Learning

Kim¹,

Jung²,

Park³

2021

Preprint

View full text Add to dashboard Cite

The merit of ensemble learning lies in having different outputs from many individual models on a single input, i.e., the diversity of the base models. The high quality of diversity can be achieved when each model is specialized to different subsets of the whole dataset. Moreover, when each model explicitly knows to which subsets it is specialized, more opportunities arise to improve diversity. In this paper, we propose an advanced ensemble method, called Auxiliary class based Multiple Choice Learning (AMCL), to ultimately specialize each model under the framework of multiple choice learning (MCL). The advancement of AMCL is originated from three novel techniques which control the framework from different directions: 1) the concept of auxiliary class to provide more distinct information through the labels, 2) the strategy, named memory-based assignment, to determine the association between the inputs and the models, and 3) the feature fusion module to achieve generalized features. To demonstrate the performance of our method compared to all variants of MCL methods, we conduct extensive experiments on the image classification and segmentation tasks. Overall, the performance of AMCL exceeds all others in most of the public datasets trained with various networks as members of the ensembles.Inheriting the concept of the oracle loss, [6] applied MCL to ensembles of deep neural networks with a trainable algorithm and named stochastic multiple choice learning (sMCL). Since each specialized model takes the loss only from a certain set of examples, overconfident predictions to unassigned examples occur by nature. To address this overconfidence issue, a series of progressive methods are introduced. [7] added a regularization term to the oracle loss in order to coerce the predictive Preprint. Under review.

show abstract

Hand Pose Ensemble Learning Based on Grouping Features of Hand Point Sets

Cited by 5 publications

References 31 publications

InterNet+: A Light Network for Hand Pose Estimation

InterNet+: A Light Network for Hand Pose Estimation

A Comprehensive Study on Deep Learning-Based 3D Hand Pose Estimation Methods

Auxiliary Class Based Multiple Choice Learning

Contact Info

Product

Resources

About