|
|||||
|
|
| 基于注意力机制的时间分组深度网络行为识别算法 | |
| 引用本文： | 胡正平,刁鹏成,张瑞雪,李淑芳,赵梦瑶. 基于注意力机制的时间分组深度网络行为识别算法[J]. 模式识别与人工智能, 2019, 32(10): 892-900. DOI: 10.16451/j.cnki.issn1003-6059.201910003 |
| 作者姓名： | 胡正平 刁鹏成 张瑞雪 李淑芳 赵梦瑶 |
| 作者单位： | 1.燕山大学 信息科学与工程学院 秦皇岛 066004; 2.燕山大学 河北省信息传输与信号处理重点实验室 秦皇岛 066004 |
| 基金项目： | 国家自然科学基金面上项目(No.61771420)、河北省自然科学基金项目(No.F2016203422)资助 |
| 摘 要： | 受人脑视觉感知机制启发,在深度学习框架下提出基于注意力机制的时间分组深度网络行为识别算法.针对局部时序信息在描述持续时间较长的复杂动作上的不足,使用视频分组稀疏抽样策略,以更低的成本进行视频级时间建模.在识别阶段引入通道注意力映射,进一步利用全局特征信息和捕捉分类兴趣点,执行通道特征重新校准,提高网络的表达能力.实验表明,文中算法在UCF101、HMDB51数据集上的识别准确率较高. |
| 关 键 词： | 行为识别 深度学习 卷积神经网络 注意力 |
| 收稿时间： | 2018-06-17 |
Temporal Group Deep Network Action Recognition Algorithm Based on Attention Mechanism |
|
| HU Zhengping,DIAO Pengcheng,ZHANG Ruixue,LI Shufang,ZHAO Mengyao. Temporal Group Deep Network Action Recognition Algorithm Based on Attention Mechanism[J]. Pattern Recognition and Artificial Intelligence, 2019, 32(10): 892-900. DOI: 10.16451/j.cnki.issn1003-6059.201910003 | |
| Authors: | HU Zhengping DIAO Pengcheng ZHANG Ruixue LI Shufang ZHAO Mengyao |
| Affiliation: | 1.School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004; 2.Hebei Key Laboratory of Information Transmission and Signal Processing, Yanshan University, Qinhuangdao 066004 |
| Abstract: | Inspired by the mechanism of human visual perception, a temporal group deep network action recognition algorithm based on attention mechanism is proposed under the framework of deep learning. Aiming at the deficiency of local temporal information in describing complex actions with a long duration, the video packet sparse sampling strategy is employed to conduct video level time modeling at a lower cost. In the recognition stage, channel attention mapping is introduced to further utilize global feature information and capture classified interest points, and channel feature recalibration is performed to improve the expression ability of the network. Experimental results on UCF101 and HMDB51 datasets show that the recognition accuracy of the proposed algorithm is high. |
| Keywords: | Action Recognition Deep Learning Convolutional Neural Network Attention |
| 点击此处可从《模式识别与人工智能》浏览原始摘要信息 | |
| 点击此处可从《模式识别与人工智能》下载全文 | |