河南科技大学学报（自然科学版）2026，Vol.47Issue(3)：54-62,72,10.DOI:10.15926/j.cnki.issn1672-6871.2026.03.006
基于时序一致性调整网络的动作分割方法
Action Segmentation with Temporal Consistency Adjustment Network
摘要
Abstract
Objectives Aiming at the problems of insufficient recognition of tail actions caused by long-tail distribution in temporal action segmentation,as well as mis-segmentation and over-segmentation resulting from existing methods that tend to ignore temporal dependencies between actions.Methods A temporal action segmentation method based on a temporal consistency adjustment network is proposed.Built upon an action segmentation backbone,the method constructs a temporal exchange self-supervised module to enhance the recognition ability of tail actions,designs a dynamic temporal adjustment module to learn the dependencies between actions,and introduces a segmental nearest class mean module to alleviate over-segmentation.Results Experimental results on the 50Salads and Breakfast datasets show that the proposed method achieves certain improvements on most metrics.Conclusions The method can effectively address the issues of long-tail distribution and temporal consistency.关键词
时序动作分割/长尾分布/时序一致性/逻辑值调整Key words
action segmentation/long-tailed distribution/temporal consistency/logit adjustment分类
信息技术与安全科学引用本文复制引用
刘向龙,张启,张建设,冀治航..基于时序一致性调整网络的动作分割方法[J].河南科技大学学报（自然科学版）,2026,47(3):54-62,72,10.基金项目
国家自然科学基金项目(62176113) （62176113）
河南省科技攻关项目(252102221019) （252102221019）
南昌航空大学无损检测技术教育部重点实验室开放基金 （）
