Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Learning features of intermediate complexity for the recognition of biological motion

Sigala, R., Serre T, Poggio, T., & Giese, M. (2005). Learning features of intermediate complexity for the recognition of biological motion. ICANN 2005. Lecture notes in computer science ISSN 0302-9743, 241-246.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Sigala, R1, Autor           
Serre T, Poggio, T, Autor
Giese, M2, Autor           
Duch, Herausgeber
W., Herausgeber
Kacprzyk, J., Herausgeber
Oja, E., Herausgeber
Zadrozny, S., Herausgeber
Affiliations:
1Department Physiology of Cognitive Processes, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497798              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Humans can recognize biological motion from strongly impoverished stimuli, like point-light displays. Although the neural mechanism underlying this robust perceptual process have not yet been clarified, one possible explanation is that the visual system extracts specific motion features that are suitable for the robust recognition of both normal and degraded stimuli. We present a neural model for biological motion recognition that learns robust mid-level motion features in an unsupervised way using a neurally plausible memory-trace learning rule. Optimal mid-level features were learnt from image motion sequences containing a walker with, or without background motion clutter. After learning of the motion features, the detection performance of the model substantially increases, in particular in presence of clutter. The learned mid-level motion features are characterized by horizontal opponent motion, where this feature type arises more frequently for the training stimuli without motion clutter. The learned features are consistent with recent psychophysical data that indicates that opponent motion might be critical for the detection of point light walkers.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2005-09
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: ISBN: 978-3-540-28752-0
URI: http://www.ibspan.waw.pl/ICANN-2005/
DOI: 10.1007/11550822_39
BibTex Citekey: 5537
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 15th International Conference on Artificial Neural Networks
Veranstaltungsort: Warsaw, Poland
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: ICANN 2005. Lecture notes in computer science ISSN 0302-9743
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Berlin, Germany : Springer
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 241 - 246 Identifikator: -