Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization
文献类型:会议论文
作者 | Chen YZ(陈云泽)2,3; Mengjuan Chen2; Rui Wu1; Jiagang Zhu2; Zheng Zhu2; Qingyi Gu2 |
出版日期 | 2020 |
会议日期 | 2020/07/09 |
会议地点 | virtual conference |
英文摘要 | Boundary localization is a key component of most temporal action localization frameworks for untrimmed video. Deep-learning methods have brought remarkable progress in this field due to large-scale annotated datasets (e.g., THUMOS14 and ActivityNet). However, natural ambiguity exists for labeling an accurate action boundaries with such datasets. In this paper, we propose a method to model this uncertainty. Specifically, we construct a Gaussian model for predicting the uncertainty variance of the boundary. The captured variance is further used to select more reliable proposals and to refine proposal boundaries by variance voting during post-processing. For most existing one- and two-stage frameworks, more accurate boundaries and reliable proposals can be obtained without additional computation. For the one-stage decoupled single-shot temporal action detection (Decouple-SSAD) framework, we first apply the adaptive pyramid feature fusion method to fuse its features of different scales and optimize its structure. Then, we introduce the uncertainty based method and improve state-of-the-art mAP@0.5 value from 37.9% to 41.6% on THUMOS14. Moreover, for the two-stage proposal–proposal interaction through a graph convolutional network (P-GCN), with such uncertainty method, we also gain significant improvements on both THUMOS14 and ActivityNet v1.3 datasets. |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/52384] |
专题 | 精密感知与控制研究中心_精密感知与控制 |
作者单位 | 1.Horizon Robotics Beijing, China 2.Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences Beijing, China 3.School of Artificial Intelligence, University of Chinese Academy of Sciences Beijing, China |
推荐引用方式 GB/T 7714 | Chen YZ,Mengjuan Chen,Rui Wu,et al. Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization[C]. 见:. virtual conference. 2020/07/09. |
入库方式: OAI收割
来源:自动化研究所
其他版本
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。