Novel Artistic Scene-Centric Datasets for Effective Transfer Learning in Fragrant Spaces

Liu S, Huang H, Zinnen M, Maier A, Christlein V (2025)

Publication Type: Conference contribution

Publication year: 2025

Journal

Lecture Notes in Computer Science Springer Verlag

Publisher: Springer Nature

City/Town: Cham

Pages Range: 161-176

Conference Proceedings Title: Computer Vision – ECCV 2024 Workshops

Event location: Mailand IT

ISBN: 9783031915710

DOI: 10.1007/978-3-031-91572-7_10

Abstract

Olfaction is often overlooked in cultural heritage studies, while examining historical depictions of olfactory scenes can offer valuable insights into the role of smells in history. The main challenge arises from the lack of published datasets with scene annotations for historical artworks, especially in artistic fragrant spaces. We introduce a novel artistic scene-centric dataset consisting of 4541 artworks and categorized across 170 distinct physical scene categories. We show that a transfer-learning approach using weakly labeled training data can remarkably improve the classification of fragrant spaces and, more generally, artistic scene depictions. This work lays a foundation for further exploration of olfactory spaces recognition and broadens the classification of physical scenes to the realm of fine art. All images and labels are released as the ArtPlaces dataset at https://zenodo.org/records/13371280.

Authors with CRIS profile

Mathias Zinnen Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung) Vincent Christlein Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Liu, S., Huang, H., Zinnen, M., Maier, A., & Christlein, V. (2025). Novel Artistic Scene-Centric Datasets for Effective Transfer Learning in Fragrant Spaces. In Computer Vision – ECCV 2024 Workshops (pp. 161-176). Mailand, IT: Cham: Springer Nature.

MLA:

Liu, Shumei, et al. "Novel Artistic Scene-Centric Datasets for Effective Transfer Learning in Fragrant Spaces." Proceedings of the Computer Vision – ECCV 2024 Workshops, Mailand Cham: Springer Nature, 2025. 161-176.

BibTeX: Download