Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, mos...Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, most existing deep learning based recognition frameworks are not optimized for action in the surveillance videos. In this paper, we propose a novel method to deal with the recognition of different types of actions in outdoor surveillance videos. The proposed method first introduces motion compensation to improve the detection of human target. Then, it uses three different types of deep models with single and sequenced images as inputs for the recognition of different types of actions. Finally, predictions from different models are fused with a linear model. Experimental results show that the proposed method works well on the real surveillance videos.展开更多
文摘Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, most existing deep learning based recognition frameworks are not optimized for action in the surveillance videos. In this paper, we propose a novel method to deal with the recognition of different types of actions in outdoor surveillance videos. The proposed method first introduces motion compensation to improve the detection of human target. Then, it uses three different types of deep models with single and sequenced images as inputs for the recognition of different types of actions. Finally, predictions from different models are fused with a linear model. Experimental results show that the proposed method works well on the real surveillance videos.
文摘针对中文网络安全领域缺乏公开数据集和有效的命名实体识别(Named Entity Recognition,NER)方法,提出一种融合汉字多源信息的网络安全NER方法。通过构建数据集中所有字符的偏旁和字频向量表,增强了中文字向量的特征表达能力,嵌入到改进的词汇融合模型中进行字向量与词向量的融合,输入到条件随机场(Conditional Random Fields,CRF)进行解码。实验结果表明,该方法在保持较快解码速度和占用较低计算机资源的情况下,在网络安全数据集上,其准确率、召回率和F1值分别为0.8649、0.8402和0.8523,均优于现有模型,能够为后续网络安全知识图谱的构建提供支撑。