Vivere Ingegneria è lieta di informarvi che Mercoledì 23 Maggio alle ore 15 in aula C340 (Ed.7) si terrà un seminario in ambito “Computer Vision e Intelligenza Artificiale ” dal titolo “Modeling Attention and Capabilities of Humans and Algorithms in Vision Tasks” tenuto dal Prof. Stan Sclaroff della Boston University (USA).
Saranno riconosciuti 1 CFU agli studenti di:
– Ingegneria Informatica 2° anno (LM) e Fuori Corso (LM)
A conclusione del seminario gli studenti dovranno inviare una relazione conclusiva necessaria per l’attribuzione dei crediti formativi universitari.
N.B. Il seminario sarà in inglese.
Per iscriversi basta compilare il seguente MODULO.
Titolo: Modeling Attention and Capabilities of Humans and Algorithms in Vision Tasks
In this talk, I will report on our group’s work on methods for modeling the attention and capabilities of humans and deep learning methods in image and video analysis tasks. We have developed algorithms for (1) modeling what humans and deep neural networks (CNNs, RNNs) find salient in images and video, (2) teaching models to imitate humans’ ability to rapidly estimate the number of prominent items in an image at-a-glance, and (3) predicting when an algorithm or human can more reliably undertake an image labeling task. I will also report on our group’s work on methods for adapting and personalizing facial and hand gesture recognition via hierarchical Bayesian neural networks. We have developed fast, scalable algorithms for inferring the posterior distribution over all network weights in the hierarchy and for adapting our gesture models to new subjects when a small number of subject-specific personalization data is available.
Stan Sclaroff is a Professor in the Department of Computer Science at Boston University (BU). He served as the Chair of the BU Department of Computer Science from 2007-2013, and now serves as Associate Dean of the Faculty, for Mathematical and Computational Sciences, in BU’s College of Arts and Sciences. His research interests are in the areas of tracking, video-based analysis of human motion and gesture, shape matching and recognition, visual saliency and attention models, “explainable” deep learning, as well as image/video database indexing, retrieval, and data mining methods. He is a Fellow of the IEEE and IAPR. He received his PhD from MIT in 1995.