Adaptive multi-view feature selection for human motion retrieval.pdfVIP

Signal Processing 120 (2016) 691–701 Contents lists available at ScienceDirect Signal Processing journal homepage: /locate/sigpro Adaptive multi-view feature selection for human motion retrieval Zhao Wang a, Yinfu Feng b, Tian Qi b, Xiaosong Yang a,n, Jian J. Zhang a a Bournemouth University, Poole Dorset BH12, United Kingdom b School of Computer Science, Zhejiang University, Hangzhou 310027, PR China a r t i c l e i n f o a b s t r a c t Article history: Human motion retrieval plays an important role in many motion data based applications. Received 7 September 2014 In the past, many researchers tended to use a single type of visual feature as data Received in revised form representation. Because different visual feature describes different aspects about motion 21 November 2014 data, and they have dissimilar discriminative power with respect to one particular class of Accepted 24 November 2014 Available online 3 December 2014 human motion, it led to poor retrieval performance. Thus, it would be beneficial to combine multiple visual features together for motion data representation. In this article, Keywords: we present an Adaptive Multi-view Feature Selection (AMFS) method for human motion Human motion retrieval retrieval. Specifically, we first use a local linear regression model to automatically learn Feature selection