.png){kind=icon}
返回
Improved skeleton-based activity recognition using convolutional block attention module
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2024.109231.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Inferring human activities from the skeletons extracted from activity photos or videos is a fundamental yet important issue in the research community of computer vision. Current skeletonbased activity recognition methods have accomplished this task by extracting features in either spatial or temporal perspective, or combining both views; however, the extracted features lack further after -processing like feature augmentation. Aiming at the above shortcomings, this article presents a new human activity recognition approach based on human skeleton data, named Convolutional Block Attention Module -based Spatial Temporal Convolutional Network (CBAMSTGCN). To enhance the discriminative validity of the generated features, we leverage the attention mechanism to weight feature units within each dimension by introducing two attention modules designed in terms of different aspects into the model architecture. Specifically, the original feature map of an activity sample is adaptively refined by the convolutional block attention module, where two separate attention maps obtained with regard to spatial and channel dimensions are adopted to generate the corresponding attended feature maps. Evaluation results on the Kinetics benchmark dataset showed that the proposed model has improved 1.76 % and 2.43 % according to top -1 and top -5 metrics, respectively, compared to the conventional baseline model. Further ablation experiments proved that both channel and spatial attention modules contribute to the model performance.
Keyword:
Activity recognition
Deep learning
Attention
Graph convolutional network
Skeleton
期刊
C
IF:
4.9
论文数:
6.7K
被引数:
1.3W
机构
引用论文
Meta-learning meets the Internet of Things: Graph prototypical models for sensor-based human activity recognition.png)
INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏分享收藏Skeleton-based human activity recognition using ConvLSTM and guided feature learningSOFT COMPUTING
OAAI
SOFT COMPUTINGIF2.5
OAAI分享收藏Predicting STI Positivity in US Cisgender Women Using Electronic Resources利用电子资源预测美国顺性别女性的STI阳性结果
PREAI
分享收藏Intraoperative fluorescence diagnosis using 5-aminolevulinic acid in surgical treatment of children with recurrent neuroepithelial tumors术中荧光诊断在儿童复发性神经上皮肿瘤手术治疗中的应用（5-氨基乙酰丙酸）OAAI
OAAI分享收藏LSTM Networks Using Smartphone Data for Sensor-Based Human Activity Recognition in Smart Homes使用智能手机数据的LSTM网络用于智能家居中基于传感器的人体活动识别SENSORS
OAAI
SENSORSIF3.5
OAAI分享收藏
查看更多内容