Heterogeneous discriminant analysis for cross-view action recognition.pdfVIP

Neurocomputing 191 (2016) 286–295 Contents lists available at ScienceDirect Neurocomputing journal homepage: /locate/neucom Heterogeneous discriminant analysis for cross-view action recognition Wanchen Sui, Xinxiao Wu n, Yang Feng, Yunde Jia Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing 100081, PR China article info Article history: Received 10 August 2015 Received in revised form 9 December 2015 Accepted 15 January 2016 Communicated by Yongzhen Huang Available online 18 February 2016 Keywords: Cross-view action recognition Transfer learning Discriminant analysis Heterogeneous domain adaption abstract We propose an approach of cross-view action recognition, in which the samples from different views are represented by features with different dimensions. Inspired by linear discriminant analysis (LDA), we introduce a discriminative common feature space to bridge the source and target views. Two different projection matrices are learned to respectively map the action data from two different views into the common space by simultaneously maximizing the similarity of intra-class samples, minimizing the similarity of inter-class samples and reducing the mismatch between data distributions of two views. In addition, the locality information is incorporated into the discriminant analysis as a constraint to make the discriminant function smooth on the data manifold. Our method is neither restricted to the corresponding action instances in the two views nor restricted to a speci?c type of feature. We evaluate our approach on the IXMAS multi-view action dataset and N-UCLA dataset. The experimental results demonstrate the effectiveness of our method. 2016 Elsevier B.V. All rights reserved. 1. Introduction Human action recognition in videos plays an important role in computer vision due to its wide applications in human–computer interaction, smart surveillance, and video retrieval. In order to accura