A novel mid-level distinctive feature learning for action recognition via diffusion map

详细信息    查看全文

• 作者：Wanru Xu ; ^{11112063@bjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Zhenjiang Miao ^{zjmiao@bjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yi Tian ^{11112062@bjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Human action recognition ; Diffusion map ; Spatio-temporal structures ; Feature learning ; Feature fusion
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：19 December 2016
• 年：2016
• 卷：218
• 期：Complete
• 页码：185-196
• 全文大小：2100 K

文摘

Recent works have shown that mid-level feature is superior to low-level feature, which can not only improve discriminative power, but also enhance descriptive capability. In this paper, the classical STIP, spatial star-graph and temporal star-graph are first extracted to represent human action from multi-perspectives. Then a principled feature learning algorithm is proposed to embed these multi-cues into a unified space and enhance all low-level features using diffusion map. Unlike treating spatio-temporal patch as mid-level primitive, we use a graph to model different types of primitives, then apply graph partitioning to co-cluster them into visual-word clusters called mid-level distinctive feature, which can bridge the semantic gap across low-level features. Experimental results show that our approach can successfully classify human activities with higher accuracies both on single-person actions (KTH and UCF) and complex interactional activities (UT-Interaction and HMDB51).