{"id":12407,"date":"2018-05-20T19:57:23","date_gmt":"2018-05-20T17:57:23","guid":{"rendered":"http:\/\/www.vivereingegneria.com\/blog\/?p=12407"},"modified":"2018-05-21T08:24:09","modified_gmt":"2018-05-21T06:24:09","slug":"seminario-computer-vision-and-artificial-intelligence","status":"publish","type":"post","link":"https:\/\/www.vivereingegneria.com\/blog\/2018\/05\/seminario-computer-vision-and-artificial-intelligence\/","title":{"rendered":"Seminario – “Computer Vision and Artificial Intelligence”"},"content":{"rendered":"

Vivere Ingegneria \u00e8 lieta di informarvi che\u00a0Mercoled\u00ec 23 Maggio<\/strong> alle ore 15<\/strong> in aula C340<\/strong> (Ed.7<\/em>) si terr\u00e0 un seminario in ambito “Computer Vision e Intelligenza Artificiale\u00a0<\/em>” dal titolo “Modeling Attention and Capabilities of Humans and Algorithms in Vision Tasks<\/em>” tenuto dal Prof. Stan Sclaroff<\/strong> della Boston University (USA).<\/em><\/p>\n

Saranno riconosciuti 1 CFU\u00a0<\/strong> agli studenti di:
\n– Ingegneria Informatica 2\u00b0 anno (LM) e Fuori Corso (LM)<\/p>\n

A conclusione del seminario gli studenti\u00a0dovranno<\/strong>\u00a0inviare una\u00a0relazione<\/strong>\u00a0conclusiva necessaria\u00a0per l\u2019attribuzione dei crediti formativi universitari<\/strong>.
\nN.B.<\/strong> Il seminario sar\u00e0 in inglese.<\/p>\n

Per iscriversi basta compilare il seguente MODULO<\/a>.<\/em><\/p>\n

\"locandinastansclaroff\"<\/a>Speaker: Prof. Stan Sclaroff
\nAffiliation: CS Dep., Boston University, MA, USA<\/p>\n

Titolo: Modeling Attention and Capabilities of Humans and Algorithms in Vision Tasks<\/p>\n

Abstract:
\nIn this talk, I will report on our group\u2019s 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\u2019 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\u2019s 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.<\/p>\n

Bio:
\nStan 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\u2019s 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, \u201cexplainable\u201d 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.<\/p>\n

Website: http:\/\/www.cs.bu.edu\/fac\/sclaroff\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Vivere Ingegneria \u00e8 lieta di informarvi che\u00a0Mercoled\u00ec 23 Maggio alle ore 15 in aula C340 (Ed.7) si terr\u00e0 un seminario in ambito “Computer Vision e Intelligenza Artificiale\u00a0” 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\u00a0 agli studenti […]<\/p>\n","protected":false},"author":295,"featured_media":16319,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"tdm_status":"","tdm_grid_status":"","footnotes":""},"categories":[1,31,1658,57],"tags":[],"class_list":{"0":"post-12407","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-facolta","8":"category-ingegneria-informatica","9":"category-ing-informatica-e-delle-telecomunicazioni-ccs","10":"category-seminari"},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/posts\/12407","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/users\/295"}],"replies":[{"embeddable":true,"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/comments?post=12407"}],"version-history":[{"count":12,"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/posts\/12407\/revisions"}],"predecessor-version":[{"id":12420,"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/posts\/12407\/revisions\/12420"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/media\/16319"}],"wp:attachment":[{"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/media?parent=12407"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/categories?post=12407"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.vivereingegneria.com\/blog\/wp-json\/wp\/v2\/tags?post=12407"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}