The School of Computer Science at the University of Windsor is pleased to present…  

Colloquium Presentation by Dr. Yalda Mohsenzadeh 

Understanding, Predicting, and Controlling Image Memorability with Representation Learning 

Date: Friday November 25, 2022

Time: 11:00am – 12:00pm

Location: Erie Hall, Room 3123

Reminders: Two-part attendance mandatory, arrive 5-10 minutes prior to event starting – LATECOMERS WILL NOT BE ADMITTED once the door has been closed and the presentation has begun. Please be respectful of the presenter by NOT knocking on the door for admittance.

Abstract: 

Everyday, we are bombarded with hundreds of images on our smart phone, on television, or in print. Recent work shows that images differ in their memorability, some stick in our mind while others are fade away quickly, and this phenomenon is consistent across people. While it has been shown that memorability is an intrinsic feature of an image, still it is largely unknown what features make images memorable. In this talk, I will present a series of our studies which aim to address this question by proposing a fast representation learning approach to modify and control the memorability of images. The proposed method can be employed in photograph editing applications for social media, learning aids, or advertisement purposes.

Keywords: Image Memorability, Deep Neural Networks (DNNs), Generative Adversarial Networks (GANs), Representation Learning

Biography: 

Dr. Yalda Mohsenzadeh is an Assistant Professor in the Department of Computer Science and Western Institute for Neuroscience at the University of Western Ontario. She is also a faculty member of the Vector Institute for Artificial Intelligence. From 2016 to 2019, Yalda was a postdoctoral associate in the Computer Science and Artificial Intelligence Lab (CSAIL) and McGovern Institute for Brain Research at MIT, Cambridge, MA, USA. Prior to that (2014 to 2016), she was a postdoctoral fellow in the Center for Vision Research at York University, Toronto, ON, Canada. Yalda received her PhD in statistical machine learning in 2014 from Amirkabir University of Technology, Tehran, Iran. Her research is interdisciplinary, spanning computer vision, deep learning, machine learning and their application in cognitive computational neuroscience and medical imaging with a successful track record of collaboration with industry sectors.