.png){kind=icon}
返回
Decoupled and boosted learning for skeleton-based dynamic hand gesture recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110536.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the development of cost-effective depth sensors, skeleton -based dynamic hand gesture recognition has made significant progress. Existing methods mostly utilize a single model to learn all spatial-temporal features. Meanwhile, they cannot effectively boost key features and make use of multi -scale features. In this paper, we propose a lightweight dual -stream framework, which consists of a temporal mutual boosted stream (TMB-Stream) and a spatial self -boosted stream (SSB-Stream). In the TMB-Stream, we design a hybrid attention module (HAM) to boost important motion features from temporal sequences, which is composed of a multi -scale multi -head attention module (MMAM) and a spatial-temporal attention module (STAM). In the SSB-Stream, we present a self -boosted learning manner to promote the performance of the spatial stream. Specifically, we design a multi -scale auto -encoder (MAE), which can use limited skeleton data to extract and boost spatial latent features by minimizing the gap between original and reconstructed skeleton images. In addition, we propose a multi -scale fusion module (MFM) to effectively fuse multi -scale features in stages. Experimental results show that our lightweight framework yields satisfactory performance on SHREC'17 Track and DHG-14/28 datasets, as well as very competitive performance on FPHA dataset.
Keyword:
Hand gesture recognition
Decoupled skeleton representation
Boosted learning
Multi-scale features
Attention mechanism
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Relation-mining self-attention network for skeleton-based human action recognition.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Normalize d e dge convolutional networks for skeleton-based hand gesture recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏3D hand pose and shape estimation from RGB images for keypoint-based hand gesture recognition基于关键点手势识别的RGB图像的3D手部姿态和形状估计PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Mask-guided multiscale feature aggregation network for hand gesture recognition基于Mask引导的多尺度特征聚合网络的手势识别PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏MFA-Net: Motion Feature Augmented Network for Dynamic Hand Gesture Recognition from Skeletal DataSENSORSOAAI
SENSORSIF3.5
OAAI分享收藏 没有更多内容
没有更多内容