Toward Unsupervised Visual Reasoning: Do Off-the-Shelf Features Know How to Reason?

Autor: Monika Wysoczanska, Tom Monnier, Tomasz Trzcinski, David Picard

Publikováno v: IEEE Access, Vol 12, Pp 76367-76378 (2024)

Recent advances in visual representation learning allowed for the construction of a plethora of powerful features that are ready to use for numerous downstream tasks. Contrary to existing representation evaluations typically based on image or pixel-w

Externí odkaz: https://doaj.org/article/297e4dc099694f6285cd3ebc5051520e

Spatially-Consistent Feature Matching and Learning for Heritage Image Analysis

Autor: Xi Shen, Robin Champenois, Shiry Ginosar, Ilaria Pastrolin, Morgane Rousselot, Oumayma Bounou, Tom Monnier, Spyros Gidaris, François Bougard, Pierre-Guillaume Raverdy, Marie-Françoise Limon, Christine Bénévent, Marc Smith, Olivier Poncet, K. Bender, Béatrice Joyeux-Prunel, Elizabeth Honig, Alexei A. Efros, Mathieu Aubry

Publikováno v: International Journal of Computer Vision
International Journal of Computer Vision, Springer Verlag, 2022, ⟨10.1007/s11263-022-01576-x⟩
International Journal of Computer Vision, 2022, ⟨10.1007/s11263-022-01576-x⟩

International audience; Progress in the digitization of cultural assets leads to online databases that become too large for a human to analyze. Moreover, some analyses might be challenging, even for experts. In this paper, we explore two applications

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9389fb7d297f4218f63abcfbd5ebe6f
https://doi.org/10.1007/s11263-022-01576-x

A Web Application for Watermark Recognition

Autor: Pierre-Guillaume Raverdy, François Bougard, Marie-Françoise Limon-Bonnet, Xi Shen, Oumayma Bounou, Tom Monnier, Mathieu Aubry, Marc H. Smith, Christine Benevent, Ilaria Pastrolin, Olivier Poncet

Publikováno v: Journal of Data Mining and Digital Humanities
Journal of Data Mining and Digital Humanities, Episciences.org, 2020, Atelier Digit_Hum (45), pp.33. ⟨10.46298/jdmdh.6220⟩
Journal of Data Mining and Digital Humanities, Episciences.org, 2020, 24 (45), pp.33. ⟨10.46298/jdmdh.6220⟩
Journal of Data Mining and Digital Humanities, 2020, Atelier Digit_Hum (45), pp.33. ⟨10.46298/jdmdh.6220⟩
Journal of Data Mining and Digital Humanities, Vol Atelier Digit_Hum, Iss Data deluge: which skills for wich data? (2020)

The study of watermarks is a key step for archivists and historians as it enables them to reveal the origin of paper. Although highly practical, automatic watermark recognition comes with many difficulties and is still considered an unsolved challeng

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae39b7973829ec7a4bdfbb6d8b5bb50a
https://hal.inria.fr/hal-02513038