Cargando…
Proposals Generation for Weakly Supervised Object Detection in Artwork Images
Object Detection requires many precise annotations, which are available for natural images but not for many non-natural data sets such as artworks data sets. A solution is using Weakly Supervised Object Detection (WSOD) techniques that learn accurate object localization from image-level labels. Stud...
Autores principales: | Milani, Federico, Pinciroli Vago, Nicolò Oreste, Fraternali, Piero |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9410216/ https://www.ncbi.nlm.nih.gov/pubmed/36005458 http://dx.doi.org/10.3390/jimaging8080215 |
Ejemplares similares
-
Comparing CAM Algorithms for the Identification of Salient Image Features in Iconography Artwork Analysis
por: Pinciroli Vago, Nicolò Oreste, et al.
Publicado: (2021) -
Instance-Level Contrastive Learning for Weakly Supervised Object Detection
por: Zhang, Ming, et al.
Publicado: (2022) -
Towards Generating and Evaluating Iconographic Image Captions of Artworks
por: Cetinic, Eva
Publicado: (2021) -
A hybrid generative adversarial network for weakly-supervised cloud detection in multispectral images
por: Li, Jun, et al.
Publicado: (2022) -
Artworks as dichotomous objects: implications for the scientific study of aesthetic experience
por: Pepperell, Robert
Publicado: (2015)