Vortrag

ONLINE-ANGEBOT: Predicting Human Eye Fixations via Deep Learning-based Saliency Models

Wann
Montag, 11. Januar 2021
16 bis 18 Uhr

Wo
Via Webex (see Kontakt Box)

Veranstaltet von
SFB-TRR 161

Vortragende Person/Vortragende Personen:
Dr. Marcella Cornia, University of Modena and Reggio Emilia, Italy

Diese Veranstaltung ist Teil der Veranstaltungsreihe „SFB-TRR 161 Lecture Series“.

Abstract:

When human observers look at an image, attentive mechanisms drive their gaze towards salient regions. Emulating such ability has been studied for more than 80 years by neuroscientists and by computer vision researchers, while in the last few years, thanks to the large spread of deep learning, saliency prediction models have achieved considerable improvement. The first part of the talk will provide an overview of saliency prediction architectures and show the results on the most important benchmarks for the task. The use of multi-level features and recurrent attentive mechanisms will be discussed and their effectiveness in emulating human eye fixation mechanisms will be demonstrated. The last part of the talk will be focused on the application of saliency information to improve other computer vision problems, such as image captioning.

Biography:

Marcella Cornia received the M.Sc. degree in Computer Engineering and the Ph.D. degree in Information and Communication Technologies from the University of Modena and Reggio Emilia in 2016 and 2020, respectively. She is currently a postdoctoral researcher at the University of Modena and Reggio Emilia. She works under the supervision of Prof. Rita Cucchiara on Deep Learning and Computer Vision. She has authored or coauthored more than 20 publications in scientific journals and international conference proceedings. Her research interests include visual saliency prediction, image and video captioning, and multimedia technologies for cultural heritage. She regularly serves as a Reviewer for international conferences and journals.