Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Spatiotemporal Distilled Dense-Connectivity Network for Video Action Recognition | |
Wangli Hao; Zhaoxiang Zhang | |
发表期刊 | Pattern Recognition |
2019 | |
卷号 | 10期号:20页码:100-130 |
摘要 | Two-stream convolutional neural networks show great promise for action recognition tasks. However, most two-stream based approaches train the appearance and motion subnetworks independently, which may lead to the decline in performance due to the lack of interactions among two streams. To overcome this limitation, we propose a Spatiotemporal Distilled Dense-Connectivity Network (STDDCN) for video action recognition. This network implements both knowledge distillation and dense-connectivity (adapted from DenseNet). Using this STDDCN architecture, we aim to explore interaction strategies between appearance and motion streams along different hierarchies. Specifically, block-level dense connections between appearance and motion pathways enable spatiotemporal interaction at the feature representation |
关键词 | Two-stream Action Recognition Dense-connectivity Knowledge Distillation |
收录类别 | SCI |
七大方向——子方向分类 | 多模态智能 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23347 |
专题 | 模式识别国家重点实验室 智能感知与计算研究中心 |
通讯作者 | Zhaoxiang Zhang |
作者单位 | 1.Center of Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese 2.Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) 3.University of Chinese Academy of Sciences (UCAS) |
推荐引用方式 GB/T 7714 | Wangli Hao,Zhaoxiang Zhang. Spatiotemporal Distilled Dense-Connectivity Network for Video Action Recognition[J]. Pattern Recognition,2019,10(20):100-130. |
APA | Wangli Hao,&Zhaoxiang Zhang.(2019).Spatiotemporal Distilled Dense-Connectivity Network for Video Action Recognition.Pattern Recognition,10(20),100-130. |
MLA | Wangli Hao,et al."Spatiotemporal Distilled Dense-Connectivity Network for Video Action Recognition".Pattern Recognition 10.20(2019):100-130. |
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 | ||
Spatiotemporal disti(2496KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Wangli Hao]的文章 |
[Zhaoxiang Zhang]的文章 |
百度学术 |
百度学术中相似的文章 |
[Wangli Hao]的文章 |
[Zhaoxiang Zhang]的文章 |
必应学术 |
必应学术中相似的文章 |
[Wangli Hao]的文章 |
[Zhaoxiang Zhang]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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