Knowledge Commons of Institute of Automation,CAS
Anchor-free temporal action localization via Progressive Boundary-aware Boosting | |
Tang, Yepeng1; Wang, Weining2![]() ![]() | |
发表期刊 | Information Processing & Management
![]() |
2022-11 | |
卷号 | 60期号:1页码:103141 |
摘要 | Enormous untrimmed videos from the real world are difficult to analyze and manage. Temporal action localization algorithms can help us to locate and recognize human activity clips in untrimmed videos. Recently, anchor-free temporal action localization methods have gained increasing attention due to small computational costs and no complex hyperparameters of pre-set anchors. Although the performance has been significantly improved, most existing anchor-free temporal action localization methods still suffer from inaccurate action boundary predictions. In this paper, we want to alleviate the above problem through boundary refinement and temporal context aggregation. To this end, a novel Progressive Boundary-aware Boosting Network (PBBNet) is proposed for anchor-free temporal action localization. The PBBNet consists of three main modules: Temporal Context-aware Module (TCM), Instance-wise Boundary-aware Module (IBM), and Frame-wise Progressive Boundary-aware Module (FPBM). The TCM aggregates the temporal context information and provides features for the IBM and the FPBM. The IBM generates multi-scale video features to predict action results coarsely. Compared with IBM, the FPBM focuses on instance features corresponding to action predictions and uses more supervision information for boundary regression. Given action results from IBM, the FPBM uses a progressive boosting strategy to refine the boundary predictions multiple times with supervision from weak to strong. Extensive experiments on three benchmark datasets THUMOS14, ActivityNet-v1.3 and HACS show our PPBNet outperforms all existing anchor-free methods. Further, our PPBNet achieves state-of-the-art performance (72.5% mAP at tIoU = 0.5) on THUMOS14 dataset. |
关键词 | Temporal action localization Anchor-free Video understanding |
学科门类 | 工学 ; 工学::计算机科学与技术(可授工学、理学学位) |
收录类别 | SCI |
语种 | 英语 |
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 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51598 |
专题 | 紫东太初大模型研究中心 |
通讯作者 | Zhang, Chunjie |
作者单位 | 1.北京交通大学 2.中国科学院自动化研究所 3.华中科技大学 |
推荐引用方式 GB/T 7714 | Tang, Yepeng,Wang, Weining,Yang, Yanwu,et al. Anchor-free temporal action localization via Progressive Boundary-aware Boosting[J]. Information Processing & Management,2022,60(1):103141. |
APA | Tang, Yepeng,Wang, Weining,Yang, Yanwu,Zhang, Chunjie,&Liu, Jing.(2022).Anchor-free temporal action localization via Progressive Boundary-aware Boosting.Information Processing & Management,60(1),103141. |
MLA | Tang, Yepeng,et al."Anchor-free temporal action localization via Progressive Boundary-aware Boosting".Information Processing & Management 60.1(2022):103141. |
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 | ||
Anchor-free temporal(1559KB) | 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