Dynamic video mix-up for cross-domain action recognition | |
Han Wu1,2; Chunfeng Song2![]() | |
发表期刊 | Neurocomputing
![]() |
2022 | |
卷号 | 471期号:2022页码:358-368 |
摘要 | In recent years, action recognition has been extensively studied. For some general action datasets, such as UCF101 [1], the recognition accuracy in a specific domain can reach 95%. However, due to the existence of the domain-wise discrepancy, the performance of the model will be significantly reduced when deployed to realistic scenes. Therefore, to support the generalization of the action recognition model in practical scenes, the cross-domain problem should be addressed urgently. In this paper, we propose a cross-domain video data fusion mechanism to reduce the difference between domains. Our method is different from existing methods in two points: (1) Instead of performing mix-up at the feature-level, we propose to execute the mix-up directly at the input-level, which introduces more original information beyond the middle features. In addition, a progressive learning method is introduced for adaptive cross-domain fusion. (2) To make full use of the action class knowledge from the source domain, we also propose pseudo-label guided mix-up data learning. Note that only top-ranking confident pseudo labels are selected to ensure the stable similarity between the source and target domains. We evaluate the proposed method on two widely used cross-domain datasets, including the UCF101-HMDB51full and UCF-Olympic. Extensive experimental results have shown that the proposed method is effective and achieves the state-of-the-art performance. In the HMDB51(source domain)→ UCF101(target domain) direction, the accuracy of our method can reach 98.60%, which is 9.54% improvement over the existing state-of-the-art method. |
是否为代表性论文 | 否 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 多模态协同认知 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51613 |
专题 | 模式识别实验室 |
通讯作者 | Zhenyu Wang |
作者单位 | 1.School of Control and Computer Engineering, North China Electric Power University 2.Institute of Automation, Chinese Academy of Sciences (CASIA) 3.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS) 4.AIPARK |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Han Wu,Chunfeng Song,Shaolong Yue,et al. Dynamic video mix-up for cross-domain action recognition[J]. Neurocomputing,2022,471(2022):358-368. |
APA | Han Wu,Chunfeng Song,Shaolong Yue,Zhenyu Wang,Jun Xiao,&Yanyang Liu.(2022).Dynamic video mix-up for cross-domain action recognition.Neurocomputing,471(2022),358-368. |
MLA | Han Wu,et al."Dynamic video mix-up for cross-domain action recognition".Neurocomputing 471.2022(2022):358-368. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Dynamic video mix-up(2148KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论