Inproceedings3957: Unterschied zwischen den Versionen
Xi5455 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Posthumus |ErsterAutorVorname=Etienne }} {{Publikation Author |Rank=2 |Author=Hans Brandhorst }} {{Publikation…“) |
Xi5455 (Diskussion | Beiträge) K (Added PDF.) |
||
Zeile 22: | Zeile 22: | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=This paper describes our experience in combining a large corpus of material that was classified manually over decades of Art His- torical and Book History research using the ICONCLASS [4] subject clas- sification system with heuristics based on a current state-of-the-art neu- ral network (CLIP from OpenAI), leveraging visual similarity to provide suggestions for automated classification of cultural heritage content. The effectiveness of the approach is demonstrated through an evaluation of the underlying extreme multi-label classification problem. [4] https://iconclass.org/ | |Abstract=This paper describes our experience in combining a large corpus of material that was classified manually over decades of Art His- torical and Book History research using the ICONCLASS [4] subject clas- sification system with heuristics based on a current state-of-the-art neu- ral network (CLIP from OpenAI), leveraging visual similarity to provide suggestions for automated classification of cultural heritage content. The effectiveness of the approach is demonstrated through an evaluation of the underlying extreme multi-label classification problem. [4] https://iconclass.org/ | ||
+ | |Download=The_Art_Historian_s_Bicycle_Becomes_an_E_Bike_POSTHUMUS_VisART2022.pdf | ||
|Forschungsgruppe=Information Service Engineering | |Forschungsgruppe=Information Service Engineering | ||
}} | }} |
Aktuelle Version vom 31. Oktober 2022, 09:40 Uhr
The Art Historian’s Bicycle Becomes an E-Bike
The Art Historian’s Bicycle Becomes an E-Bike
Published: 2022
Buchtitel: ECCV: European Conference on Computer Vision
Reihe: Lecture Notes in Computer Science
Verlag: Springer
Referierte Veröffentlichung
Note: VISART 2022 (Workshop at the European Conference of Computer Vision (ECCV))
BibTeX
Kurzfassung
[[Abstract::This paper describes our experience in combining a large corpus of material that was classified manually over decades of Art His- torical and Book History research using the ICONCLASS [4] subject clas- sification system with heuristics based on a current state-of-the-art neu- ral network (CLIP from OpenAI), leveraging visual similarity to provide suggestions for automated classification of cultural heritage content. The effectiveness of the approach is demonstrated through an evaluation of the underlying extreme multi-label classification problem. [4] https://iconclass.org/]]
Download: Media:The_Art_Historian_s_Bicycle_Becomes_an_E_Bike_POSTHUMUS_VisART2022.pdf
Information Service Engineering