Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Learning Multi-scale Representations for Material Classification

Li, W., & Fritz, M. (2014). Learning Multi-scale Representations for Material Classification. Retrieved from http://arxiv.org/abs/1408.2938.

Item is

Dateien

einblenden: Dateien
ausblenden: Dateien
:
arXiv:1408.2938.pdf (Preprint), 3MB
Name:
arXiv:1408.2938.pdf
Beschreibung:
File downloaded from arXiv at 2014-11-13 15:15
OA-Status:
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Li, Wenbin1, Autor           
Fritz, Mario1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG,Computer Science, Neural and Evolutionary Computing, cs.NE
 Zusammenfassung: The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors. In computer vision, success stories of learned features have been predominantly reported for object recognition tasks. In this paper, we investigate if and how feature learning can be used for material recognition. We propose two strategies to incorporate scale information into the learning procedure resulting in a novel multi-scale coding procedure. Our results show that our learned features for material recognition outperform hand-crafted descriptors on the FMD and the KTH-TIPS2 material classification benchmarks.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2014-08-13
 Publikationsstatus: Online veröffentlicht
 Seiten: 8 p.
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: arXiv: 1408.2938
URI: http://arxiv.org/abs/1408.2938
BibTex Citekey: li14multiscale
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: