[CTN] CTN Seminar: Yalda Mohsenzadeh (Western) Tuesday Nov 1 2:30

[Bryan Tripp]

Hi everyone,

Just a reminder about the talk tomorrow (details below). Hope to see you there.

Graduate students are invited to a virtual lunchtime meeting (lunch optional) with the speaker from 12-1:00 at this link: https://uwaterloo.zoom.us/j/99479545276?pwd=cEVwOGVkS2ppY09ZNzBRVUNjajRjZz09

For graduate students who haven't met with speakers before, here are a few tips for a more effective meeting: 1) Spend at least 5-10 minutes beforehand looking into the speaker's research and allow time for a closer look at any of their work that is of particular interest or relevance to you. 2) Think in advance of at least one question to ask them (e.g., on their research or on career advice). 3) Be ready with a <1-minute explanation of your own research in case you are asked.

Regards,
Bryan

Bryan Tripp, PhD
Associate Professor, Department of Systems Design Engineering
Core Member, Centre for Theoretical Neuroscience
University of Waterloo
________________________________
From: Bryan Tripp <bptripp at uwaterloo.ca>
Sent: Thursday, October 27, 2022 10:07 AM
To: CTN Mailing List General <ctn at artsservices.uwaterloo.ca>
Subject: CTN Seminar: Yalda Mohsenzadeh (Western) Tuesday Nov 1 2:30

Hi everyone,

Our next talk is coming up quickly. Yalda Mohsenzadeh will join us remotely from Western University's Brain and Mind Institute, next Tuesday at 2:30.

Regards,
Bryan

Link:  https://uwaterloo.zoom.us/j/97286329987?pwd=c3RMU1l5UFNzNmNUVkZwc3BMRkxDZz09

Talk Title: Understanding, Predicting, and Manipulating Image Memorability with Representation Learning

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’s 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.


Bryan Tripp, PhD
Associate Professor, Department of Systems Design Engineering
Core Member, Centre for Theoretical Neuroscience
University of Waterloo
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://artsservices.uwaterloo.ca/pipermail/ctn/attachments/20221031/1f3920f2/attachment.htm>