CINECA IRIS Institutional Research Information System
IRIS è l'Anagrafe della ricerca dell'Università degli Studi di Trento, e ha lo scopo di raccogliere, documentare, conservare e diffondere, anche ad accesso aperto, la produzione scientifica degli autori afferenti all'Università degli Studi di Trento.
EnglishRobust 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]
| Titolo: | Multi-task Linear Discriminant Analysis for View Invariant Action Recognition | |
| Autori: | Yan, Yan; Ricci, Elisa; Subramanian, Ramanathan; Liu, Gaowen; Sebe, Niculae | |
| Autori Unitn: | ||
| Titolo del periodico: | IEEE TRANSACTIONS ON IMAGE PROCESSING | |
| Anno di pubblicazione: | 2014 | |
| Numero e parte del fascicolo: | 12 | |
| Codice identificativo Scopus: | 2-s2.0-84913555064 | |
| Codice identificativo WOS: | WOS:000345514300004 | |
| Digital Object Identifier (DOI): | http://dx.doi.org/10.1109/TIP.2014.2365699 | |
| Handle: | http://hdl.handle.net/11572/98180 | |
| Citazione: | 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] | |
| Appare nelle tipologie: | 03.1 Articolo su rivista (Journal article) |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| TIP2014.pdf | Versione editoriale (Publisher’s layout) | Tutti i diritti riservati (All rights reserved) | Administrator |
http://hdl.handle.net/11572/98180
Copyright © 2022