燕山大学学报2025，Vol.49Issue(1)：83-94,12.DOI:10.3969/j.issn.1007-791X.2025.01.009
双流运动建模-循环一致性对齐小样本动作识别算法
Two-stream motion modeling and cycle consistency alignment for few-shot action recognition
摘要
Abstract
To address the challenge of aligning videos posed by different spatio-temporal distributions of actions,which subsequently affects the accuracy of video recognition in various scenarios,a few-shot action recognition method is proposed to model and align the two-stream features through motion modeling and cycle consistency alignment.This method bases on the high-dimensional representation of motion by modeling and aligning the dual-scale features of global frames and local patch.Firstly,a motion modeling framework based on the two-stream features is designed to reshape the spatio-temporal relationship of action representations in video sequences,achieving precise localization and semantic capture of video actions.Furthermore,to facilitate the learning of spatio-temporal correspondences between actions,the cycle consistency alignment module is introduced,which can efficiently align video actions using soft nearest neighbor and significantly improve the misalignment issues.Lastly,the model combined with attention-based temporal cross matching module to infer and classify the action categories.The experimental results demonstrate this method achieves recognition accuracies of 68.6%,77.7% and 96.9% on SSv2,HMDB51 and UCF101,respectively,and could effectively recognize video actions.关键词
小样本学习/动作识别/双流网络/注意力机制/循环一致性对齐Key words
few-shot learning/action recognition/two-stream network/attention mechanism/cycle consistency alignment分类
计算机与自动化引用本文复制引用
胡正平,董佳伟,王昕宇..双流运动建模-循环一致性对齐小样本动作识别算法[J].燕山大学学报,2025,49(1):83-94,12.基金项目
国家自然科学基金资助项目(61771420,62001413) （61771420,62001413）
河北省自然科学基金资助项目(F2024203069) （F2024203069）
