Event Tubelet Compressor: Generating Compact Representations for Event-Based Action Recognition

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息会议信息基础信息归属信息摘要

成果类型：

会议论文

作者：

Xie, Bochen;Deng, Yongjian;Shao, Zhanpeng;Liu, Hai;Xu, Qingsong;...

通讯作者：

Li, YF

作者机构：

[Li, Youfu; Xie, Bochen] City Univ Hong Kong, Dept Mech Engn, Hong Kong, Peoples R China.

[Deng, Yongjian] Beijing Univ Technol, Coll Comp Sci, Beijing, Peoples R China.

[Shao, Zhanpeng] Hunan Normal Univ, Coll Informat Sci & Engn, Changsha, Peoples R China.

[Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.

[Xu, Qingsong] Univ Macau, Dept Electromech Engn, Macau, Peoples R China.

通讯机构：

[Li, YF ] C

City Univ Hong Kong, Dept Mech Engn, Hong Kong, Peoples R China.

语种：

英文

关键词：

event camera;representation learning;self-attention mechanism;human action recognition

期刊：

2022 7TH INTERNATIONAL CONFERENCE ON CONTROL, ROBOTICS AND CYBERNETICS, CRC

年：

2022

页码：

12-16

会议名称：

7th International Conference on Control, Robotics and Cybernetics (CRC)

会议时间：

DEC 15-17, 2022

会议地点：

Guangdong Ocean Univ, Sch Mech & Power Engn, Zhanjiang, PEOPLES R CHINA

会议主办单位：

Guangdong Ocean Univ, Sch Mech & Power Engn

出版地：

345 E 47TH ST, NEW YORK, NY 10017 USA

出版者：

IEEE

ISBN：

978-1-6654-7306-4

DOI：

10.1109/CRC55853.2022.10041200

基金类别：

Research Grants Council of Hong Kong [CityU 11213420]; National Natural Science Foundation of China [61873220, 62173286, 62203024]; Science and Technology Development Fund, Macau [0022/2019/AKP]

机构署名：

本校为其他机构

院系归属：

国家数字化学习工程技术研究中心

摘要：

Event cameras asynchronously capture pixel-level intensity changes in scenes and output a stream of events. Compared with traditional frame-based cameras, they can offer competitive imaging characteristics: low latency, high dynamic range, and low power consumption. It means that event cameras are ideal for vision tasks in dynamic scenarios, such as human action recognition. The best-performing event-based algorithms convert events into frame-based representations and feed them into existing learning models. However, generating informative frames for long-duration event streams is still a chal...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

Event Tubelet Compressor: Generating Compact Representations for Event-Based Action Recognition

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问