11 May 2018
Time: 4:00 - 6:00pm
Venue: Bancroft road teaching rooms BR 4.02 followed by drinks reception in the Computer Science Informatics Hub.
Computational Metrics of Visual Aesthetics
We are increasingly producing and consuming digitally created or mediated visual content. Computational models of visual aesthetics could potentially transform the way in which humans interact with computers and navigate through available visual content. They are challenging to develop due to the lack of functional and interpretable metrics, noise in naturally occurring data sets, and unreliable self-reported data due to the different interpretations of embedded content. Early work in psychology on art and visual perception (Birkhoff '33, Arnheim’74) identified concepts like symmetry, rhythm, contrast, etc. that correspond to cross-domain features of visual aesthetics. In this talk, I will present a process for modeling aesthetic evaluation of visual artifacts or experiences through preference elicitation on synthetic data across domains. Specifically, I will show results in the domains of photographic composition and full-body gestural performance (dance). I will then discuss issues related to the design of experiments for data collection, feature modeling and selection, and applications of machine learning algorithms for learning preferences. Finally, I will conclude with a vision for how this work contributes to the broader goal of developing intelligent systems with the ability to interpret and create visual narratives.
4.00-5.00pm – Seminar in Bancroft road teaching rooms BR 4.02
5.00-6.00pm – Drinks reception in the Informatics Hub ( Computer Science)
If you wish to attend please ensure you have signed up via Eventbrite so we can ensure enough catering is supplied.
Bio: Arnav Jhala, associate professor of computer science, joined NC State in August 2016 as Director of the Chancellor’s Faculty Excellence Cluster in Visual Narrative, and as the co-director of the Digital Games Research Initiative. Jhala’s research group investigates computational methods that are useful in representing and mediating human interpretation and communication of narrative in interactive visual media, such as film and games. The Jhala research group uses symbolic and probabilistic tools to construct coherent visual discourse, and apply generative techniques to interpret and collaboratively create visual narratives. Past projects include development of games for eliciting aesthetic preferences in domains such as photographic composition, aesthetics of play for highly skilled game players, and gestural aesthetics of dance.
Jhala holds a Ph.D. in computer science from NC State and bachelor’s degree in computer engineering from Gujarat University in India. Prior to joining NC State, Jhala served as one of the founding faculty members of the Computational Media Department at University of California, Santa Cruz. He has worked at a variety of institutions including the IT University of Copenhagen, University of Southern California’s Institute for Creative Technologies, Duke University’s Talent Identification Program(TIP), Virtual Heroes Inc. — a leading serious games developer, and the Indian Space Research Organization’s Space Applications Center.