Robust action recognition under viewpoint changes has received considerable attention recently. To this end, self-similarity matrices (SSMs) have been found to be effective view-invariant action descriptors. To enhance the performance of SSM-based methods, we propose multitask linear discriminant analysis (LDA), a novel multitask learning framework for multiview action recognition that allows for the sharing of discriminative SSM features among different views (i.e., tasks). Inspired by the mathematical connection between multivariate linear regression and LDA, we model multitask multiclass LDA as a single optimization problem by choosing an appropriate class indicator matrix. In particular, we propose two variants of graph-guided multitask LDA: 1) where the graph weights specifying view dependencies are fixed a priori and 2) where graph weights are flexibly learnt from the training data. We evaluate the proposed methods extensively on multiview RGB and RGBD video data sets, and experimental results confirm that the proposed approaches compare favorably with the state-of-the-art.

Multi-task Linear Discriminant Analysis for View Invariant Action Recognition / Yan, Yan; Ricci, Elisa; Subramanian, Ramanathan; Liu, Gaowen; Sebe, Niculae. - In: IEEE TRANSACTIONS ON IMAGE PROCESSING. - ISSN 1057-7149. - 2014, 23:12(2014), pp. 5599-5611. [10.1109/TIP.2014.2365699]

Multi-task Linear Discriminant Analysis for View Invariant Action Recognition

Yan, Yan;Ricci, Elisa;Subramanian, Ramanathan;Liu, Gaowen;Sebe, Niculae
2014-01-01

Abstract

Robust action recognition under viewpoint changes has received considerable attention recently. To this end, self-similarity matrices (SSMs) have been found to be effective view-invariant action descriptors. To enhance the performance of SSM-based methods, we propose multitask linear discriminant analysis (LDA), a novel multitask learning framework for multiview action recognition that allows for the sharing of discriminative SSM features among different views (i.e., tasks). Inspired by the mathematical connection between multivariate linear regression and LDA, we model multitask multiclass LDA as a single optimization problem by choosing an appropriate class indicator matrix. In particular, we propose two variants of graph-guided multitask LDA: 1) where the graph weights specifying view dependencies are fixed a priori and 2) where graph weights are flexibly learnt from the training data. We evaluate the proposed methods extensively on multiview RGB and RGBD video data sets, and experimental results confirm that the proposed approaches compare favorably with the state-of-the-art.
2014
12
Yan, Yan; Ricci, Elisa; Subramanian, Ramanathan; Liu, Gaowen; Sebe, Niculae
Multi-task Linear Discriminant Analysis for View Invariant Action Recognition / Yan, Yan; Ricci, Elisa; Subramanian, Ramanathan; Liu, Gaowen; Sebe, Niculae. - In: IEEE TRANSACTIONS ON IMAGE PROCESSING. - ISSN 1057-7149. - 2014, 23:12(2014), pp. 5599-5611. [10.1109/TIP.2014.2365699]
File in questo prodotto:
File Dimensione Formato  
TIP2014.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.45 MB
Formato Adobe PDF
4.45 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/98180
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 146
  • ???jsp.display-item.citation.isi??? 137
social impact