Open AccessPartwise bag‐of‐words‐based multi‐task learning for human action recognition
Author(s) -
Liu AnAn,
Su Yuting,
Gao Zan,
Hao Tong,
Yang ZhaoXuan,
Zhang Zhe
Publication year - 2013
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2013.1481
Subject(s) - computer science , artificial intelligence , action recognition , task (project management) , bag of words model , machine learning , pattern recognition (psychology) , multi task learning , support vector machine , graph , feature learning , transfer of learning , action (physics) , representation (politics) , engineering , theoretical computer science , class (philosophy) , physics , systems engineering , quantum mechanics , politics , law , political science
Proposed is a human action recognition method by partwise bag‐of‐words (BoW)‐based multi‐task learning. The authors present partwise BoW representation and furthermore formulate the action recognition task as a joint multi‐task learning problem by transfer learning penalised by a graph structure and sparsity to discover latent correlation and boost performances. A large‐scale experiment shows that this method can significantly improve performance over the standard BoW + SVM method. Moreover, the proposed method can achieve competing performances against the state‐of‐the‐art methods for human action recognition in an effective and easy to follow way.