基于边界敏感网络的时序行为候选生成算法 | |
Alternative Title | Temporal action proposal generation algorithm based on boundary sensitive network |
高松1,2,3; 王宏玉1,2,4; 邹风山4; 宋吉来4 | |
Department | 其他 |
Source Publication | 科学技术与工程
![]() |
ISSN | 1671-1815 |
2019 | |
Volume | 19Issue:26Pages:260-264 |
Contribution Rank | 1 |
Funding Organization | 国家重点研发计划(2017YFF0107800) |
Keyword | 人体行为检测 时序行为候选 深度学习 卷积神经网络 |
Abstract | 针对视频序列中人体行为检测的问题,提出一种基于边界敏感网络的时序行为候选生成算法,在原有边界敏感网络的基础上通过对时序评估模块和候选评估模块引入更深层的卷积神经网络,进而对视频特征有更好的表达。同时在后处理阶段,在NMS(non-maximum suppression)算法中引入新的置信度分数高斯加权衰减方法。实验结果表明,该算法可以有效提高行为检测问题中时序行为候选生成任务的召回率。在公开数据集Activity Net上,提出的方法在保证生成相同数量候选的同时有更高的平均召回率。 |
Other Abstract | Aiming at the problem of human action detection in video sequences,a temporal action proposal generation algorithm based on boundary sensitive network was proposed. Based on the original boundary sensitive network, a deeper convolutional neural network was introduced into the temporal evaluation module and the proposal evaluation module,thus to better express the characteristic of the video. At the same time,in the post-processing stage,nonmaximum suppression ( NMS) algorithm was improved by introducing a new confidence score Gaussian weighted attenuation method. The experimental results show that the proposed algorithm can effectively improve the recall of the temporal action proposal generation task in the human action detection problem. On the open dataset ActivityNet,the proposed method has a higher average recall rate while ensuring the same number of candidates are generated. |
Language | 中文 |
Document Type | 期刊论文 |
Identifier | http://ir.sia.cn/handle/173321/25867 |
Collection | 其他 |
Corresponding Author | 王宏玉 |
Affiliation | 1.中国科学院沈阳自动化研究所机器人学国家重点实验室 2.中国科学院机器人与智能制造创新研究院 3.中国科学院大学 4.沈阳新松机器人自动化股份有限公司 |
Recommended Citation GB/T 7714 | 高松,王宏玉,邹风山,等. 基于边界敏感网络的时序行为候选生成算法[J]. 科学技术与工程,2019,19(26):260-264. |
APA | 高松,王宏玉,邹风山,&宋吉来.(2019).基于边界敏感网络的时序行为候选生成算法.科学技术与工程,19(26),260-264. |
MLA | 高松,et al."基于边界敏感网络的时序行为候选生成算法".科学技术与工程 19.26(2019):260-264. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
基于边界敏感网络的时序行为候选生成算法.(1615KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | View Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment