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.
EnglishSeveral applications benefit from learning coupled representations able to describe data from multiple sources. For instance, cross-domain dictionary learning methods demonstrated to be particularly effective. In this paper we introduce Multi-Paced Dictionary Learning (MPDL) and propose an instantiation of it under the framework of cross-domain dictionary learning. MPDL is inspired by previous works on self-paced learning, a framework able to enhance the accuracy of conventional learning models by presenting the training data in a meaningful order, i.e. easy samples are provided first. However, most of existing self-paced learning methods only consider a single modality, while MPDL is specifically designed to assess the learning pace when data from multiple sources are available. We present the model and propose an efficient algorithm to learn the dictionaries and codes. The approach is validated via experiments on two different tasks, namely cross-media retrieval and sketch-to-photo face recognition, using publicly available datasets.
Multi-Paced Dictionary Learning for cross-domain retrieval and recognition / Xu, Dan; Song, Jingkuan; Alameda-Pineda, Xavier; Ricci, Elisa; Sebe, Nicu. - (2016), pp. 3228-3233. ((Intervento presentato al convegno ICPR 2016 tenutosi a Cancún, México nel 4th-8th December 2016 [10.1109/ICPR.2016.7900132].
| Titolo: | Multi-Paced Dictionary Learning for cross-domain retrieval and recognition | |
| Autori: | Xu, Dan; Song, Jingkuan; Alameda-Pineda, Xavier; Ricci, Elisa; Sebe, Nicu | |
| Autori Unitn: | ||
| Titolo del volume contenente il saggio: | 2016 23rd International Conference on Pattern Recognition, ICPR 2016 | |
| Luogo di edizione: | Piscataway, NJ | |
| Casa editrice: | Institute of Electrical and Electronics Engineers Inc. | |
| Anno di pubblicazione: | 2016 | |
| Codice identificativo Scopus: | 2-s2.0-85019093749 | |
| Codice identificativo WOS: | WOS:000406771303036 | |
| ISBN: | 9781509048472 978-1-5090-4848-9 | |
| Handle: | http://hdl.handle.net/11572/193370 | |
| Citazione: | Multi-Paced Dictionary Learning for cross-domain retrieval and recognition / Xu, Dan; Song, Jingkuan; Alameda-Pineda, Xavier; Ricci, Elisa; Sebe, Nicu. - (2016), pp. 3228-3233. ((Intervento presentato al convegno ICPR 2016 tenutosi a Cancún, México nel 4th-8th December 2016 [10.1109/ICPR.2016.7900132]. | |
| Appare nelle tipologie: | 04.1 Saggio in atti di convegno (Paper in Proceedings) |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| 07900132.pdf | Versione editoriale (Publisher’s layout) | Tutti i diritti riservati (All rights reserved) | Administrator |
http://hdl.handle.net/11572/193370
Copyright © 2022