Presentation

Valentine Bernasconi is a Ph.D. fellow at the Digital Visual Studies center hosted by the University of Zurich.

Strongly interested in the field of art and new technologies, she received an education in computer science and art history from the University of Fribourg before accomplishing a first master degree in Multimedia Design and 3D technologies at Brunel University London. She then naturally came across the new field of study of Digital Humanities and pursued a master in the domain at the Ecole Polytechnique Fédérale de Lausanne (EPFL). During her training, she was able to discover the importance of new research tools based on similar patterns in art history and the range of new research questions it allows. It is also while working on her master thesis at the EPFL+Ecal Lab that she approached the complex question of artificial intelligence, between myth and real applications, and the understanding of the digital image in the eye of the machine. Since September 2020, she has been working on her doctoral project at the Digital Visual Studies in Zurich.

Her research is focused on the role of the hand in the narrative system of pictorial representations of early modern times, its evolution over the course of that period and its automated recognition thanks to automated human pose estimation tools. Through her research, she is confronted with questions regarding the value of artificial intelligence tools in the art historical domain and the position of the digital humanist, between the application of new technologies and the real understanding of the core subjects approached.

As part of her research process, she is working on the Pose Annotation Project for Artworks (PAPA), which aims to create a proper machine learning training dataset for artistic material.

Furthermore, she recently worked on the creation of a browsing tool, Gestures for Artwork Browsing (GAB). Based on a gesture input, it proposes a new way to engage with a collection of painted hands and better understand gestures used in paintings from Early Modern Time, in direct confrontation with contemporaneous ones. It is based on such tools that the research aims to better frame the use of specific gestures in specific context or across iconography and their evolution in time.

Projects

1. Computational and Historical Analysis of Hands and Gestures in Early Modern Art
2. PAPA - Pose Annotation Project for Artworks
3. GAB - Gestures for Artwork Browsing

Publications

• Bernasconi, Valentine, Negueruela del Castillo, Darío. Pose Annotation Project for Artworks: A participatory annotation platform for automated body pose estimation in art. In Baillot, Anne, Tasovac, Toma, Scholger, Walter, & Vogeler, Georg. (2023, July 1). Digital Humanities 2023: Book of Abstracts. Digital Humanities 2023. Collaboration as Opportunity. (DH2023), Graz, Austria; p. 169. https://doi.org/10.5281/zenodo.7961822
• Bernasconi, Valentine, Eva Cetinić, and Leonardo Impett. 2023. "A Computational Approach to Hand Pose Recognition in Early Modern Paintings" Journal of Imaging 9, no. 6: 120. https://doi.org/10.3390/jimaging9060120
• Bernasconi, Valentine. A new gesture-based browsing experience for art historical research. In Book of Conference Abstracts for Digital Humanities 2022 [Abstract]; 25-29 July 2022, The University of Tokyo, Japan; p. 425. https://dh2022.dhii.asia/dh2022bookofabsts.pdf
• Bernasconi, Valentine. (2022). GAB - Gestures for Artworks Browsing. In 27th International Conference on Intelligent User Interfaces (IUI ’22 Companion), March 22–25, 2022, Helsinki, Finland. ACM, New York, NY, USA, 5 pages. https://doi.org/10.1145/3490100.3516470

Conferences

• Changing perceptions. Decoding Early Modern painted hand gestures through computer vision.
  Kommunikationstechniken im Wandel. Alternatives Schreiben, Lesen und Kommunizieren in der Vormoderne. Changing Communication Techniques, International Workshop, May 4, 2023, online
• The Reality Behind Working with Body Pose Estimation in Paintings: Another Truth.
  From Hype to Reality: Artificial Intelligence in the Study of Art and Culture, 20 - 21 April 2023, Digital Society Initiative, University of Zurich, Rämistrasse 69 Zurich, Switzerland
• Remonter le temps : nouvelles perceptions de la représentation picturale de la main à travers celle du chercheur.
  Les Entretiens de la Fondation Maison Borel, VIIe édition, Autour de la notion de filiation artistique Dialogue avec Elizabeth Prettejohn, October 21, 2022, Université de Neuchâtel, Switzerland
• Augmenting art history: a new story of the painted hand.
  DARIAH-CH Study Day October 20, 2022, Università della Svizzera italiana, Mendrisio, Switzerland. - BEST POSTER AWARD
• Imperfect tools – When uncertainties of automated recognition reveal pictorial peculiarities.
  as part of the symposium Unexpected realities: how uncertainty and imperfection influence perception and interpretation in digital visual studies, VSAC 2022, Amsterdam, Netherlands
• A new gesture-based browsing experience for art historical research.
  Digital Humanities Conference 2022, Tokyo, Japan
• Understanding body and hand gestures through the lens of computational methods.
  Body posture and art, University of Ghent, Belgium, mai 2022
• Voir autrement. Aperçu du langage de la main dans la représentation picturale à travers l’Europe d’hier grâce aux technologies d’aujourd’hui.
  Séminaire : Fortunes et circulations des images en Europe, Centre IMAGO, Paris, mai 2022
• Missing annotations: towards automated gesture recognition in artworks
  Digital Images, Metadata and Cultural Heritage Objects, DH-CH 2021, Summer School, 07-09 June 2021, Istituto Svizzero a Roma, Rome, Italy

Contact

valentine.bernasconi[at]uzh.ch