Temporal Action Detection with Dynamic Weights Based on Curriculum Learning
Chen YZ(陈云泽)1,2; He jiang1,2; Junrui Xiao1,2; Ding Li1,2; Qingyi Gu1
发表期刊Neurocomputing
2023
页码106-116
摘要

To enable temporal action localization, the computer needs to recognize the locations and classes of action instances in a video. The main challenge to temporal action detection is that the videos are often long and untrimmed, consisting of varying action content. Existing temporal action detection frameworks exhibit a gap between the training and testing phases, which is detrimental to model performance. Specifically, all positive samples are trained identically in the training phase. By contrast, in the testing phase, the positive samples with the best classification and localization scores are selected, while all others are suppressed. To mitigate this issue, we build an auxiliary branch to unify the training and testing procedures. In the construction of the auxiliary branch, we design a dynamic weighting strategy based on curriculum learning, where the weights of training samples are a combination of their classification and localization scores. Motivated by the speculation of curriculum learning, we emphasize the importance of classification and localization scores in different training stages. The classification score accounts for a higher proportion of the combined score in the early stages of the training process. As the epoch increases, the localization score gradually increases in proportion as well. The experimental results demonstrate that our methodology of curriculum-based learning enhances the performance of current action localization techniques. On THUMOS14, our technique outperforms the existing state of-the-art technique (57.6% vs 55.5%). And the performance on ActivityNet v1.3 (mAP@Avg) reaches 35.4%.

收录类别SCI
语种英语
WOS记录号WOS:000990128300001
七大方向——子方向分类图像视频处理与分析
国重实验室规划方向分类视觉信息处理
是否有论文关联数据集需要存交
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/52385
专题中科院工业视觉智能装备工程实验室_精密感知与控制
作者单位1.Institute of Automation, Chinese Academy of Sciences, East Zhongguancun Road, Haidian District, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Jingjia Road, Huairou District, Beijing, China
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
Chen YZ,He jiang,Junrui Xiao,et al. Temporal Action Detection with Dynamic Weights Based on Curriculum Learning[J]. Neurocomputing,2023:106-116.
APA Chen YZ,He jiang,Junrui Xiao,Ding Li,&Qingyi Gu.(2023).Temporal Action Detection with Dynamic Weights Based on Curriculum Learning.Neurocomputing,106-116.
MLA Chen YZ,et al."Temporal Action Detection with Dynamic Weights Based on Curriculum Learning".Neurocomputing (2023):106-116.
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
Temporal action dete(1252KB)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
[Chen YZ(陈云泽)]的文章
[He jiang]的文章
[Junrui Xiao]的文章
百度学术
百度学术中相似的文章
[Chen YZ(陈云泽)]的文章
[He jiang]的文章
[Junrui Xiao]的文章
必应学术
必应学术中相似的文章
[Chen YZ(陈云泽)]的文章
[He jiang]的文章
[Junrui Xiao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Temporal action detection with dynamic weights based on curriculum.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。