Savova, V. ; Jäkel, F. ; Tenenbaum, J. B. (2009)
Grammar-based object representations in a scene parsing task.
Proceedings of the 31st Annual Meeting of the Cognitive Science Society / ed. by N. Taatge ; H. van Rijnn. Austin, TX
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
This paper addresses the nature of visual representations associated with complex structured objects, and the role of these representations in perceptual organization. We use a novel experimental paradigm to probe subjects intuitions about parsing a scene consisting of overlapping two-dimensional objects. The objects are generated from an abstract 2-dimensional image grammar, which specifies the set of possible configurations of object parts. We show that participants' performance on the task depends on prior experience with the object class, and based on structural cues. This indicates that structural representations exerted a top-down influence on parsing. To address the question of representation type, we used a computational model of object matching in conjunction with various probabilistic representational models. Our simulations indicate that grammar-based representations derived from the original grammars are superior to more restrictive exemplar-based representations in explaining human performance on this task, as well as to more inclusive, over-generalizing grammar-based representations.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2009 |
| Autor(en): | Savova, V. ; Jäkel, F. ; Tenenbaum, J. B. |
| Art des Eintrags: | Bibliographie |
| Titel: | Grammar-based object representations in a scene parsing task |
| Sprache: | Englisch |
| Publikationsjahr: | 2009 |
| Ort: | Austin, TX |
| Verlag: | Cognitive Science Society |
| Veranstaltungstitel: | Proceedings of the 31st Annual Meeting of the Cognitive Science Society / ed. by N. Taatge ; H. van Rijnn |
| Veranstaltungsort: | Austin, TX |
| URL / URN: | http://csjarchive.cogsci.rpi.edu/proceedings/2009/papers/150... |
| Kurzbeschreibung (Abstract): | This paper addresses the nature of visual representations associated with complex structured objects, and the role of these representations in perceptual organization. We use a novel experimental paradigm to probe subjects intuitions about parsing a scene consisting of overlapping two-dimensional objects. The objects are generated from an abstract 2-dimensional image grammar, which specifies the set of possible configurations of object parts. We show that participants' performance on the task depends on prior experience with the object class, and based on structural cues. This indicates that structural representations exerted a top-down influence on parsing. To address the question of representation type, we used a computational model of object matching in conjunction with various probabilistic representational models. Our simulations indicate that grammar-based representations derived from the original grammars are superior to more restrictive exemplar-based representations in explaining human performance on this task, as well as to more inclusive, over-generalizing grammar-based representations. |
| Fachbereich(e)/-gebiet(e): | 03 Fachbereich Humanwissenschaften 03 Fachbereich Humanwissenschaften > Institut für Psychologie 03 Fachbereich Humanwissenschaften > Institut für Psychologie > Modelle höherer Kognition |
| Hinterlegungsdatum: | 09 Jul 2018 09:15 |
| Letzte Änderung: | 12 Okt 2020 11:17 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum