seminars |
filter: |
list | browse |
id : |
916
|
type : |
MSc_Thesis
|
dateandtime : |
2019-12-13 09:30:00
|
duration : |
90 min.
|
|
Recommended duration for PhD thesis is 90 minutes, for other seminar types, it is 60 minutes. The duration specified here is used to reserve the room.
|
place : |
A105
|
|
Please check room availability from Room Scheduling page. You must use the same room name as used in the scheduling page if you want to automatically reserve the room.
|
departmental : |
yes
|
title : |
Learning an Embedding Space for All Modalities
|
author : |
OGUL CAN ERYUKSEL
|
supervisors : |
ASSOC.PROF.DR.SINAN KALKAN
|
|
Supervisors field is applicable especially for a Thesis Defense
|
company : |
Computer Engineering Dept. Middle East Technical Univ.
|
country : |
Turkey
|
abstract : |
Thanks to advances in deep learning, striking results have been obtained in translation between different image modalities or spaces; e.g. using Generative Adversarial Networks, one can create a highly realistic colorized image of a black and white image, or daylight version of a nightlight image. However, existing studies generally tackle the problem in pairs and therefore, ignore the common information that are shared across different image modalities. In this thesis, a method that can create an embedding space shared by all different image modalities is proposed. The embedding space is constructed by employing pairs of modalities. Such a modality allows extracting a scene representation that is shared by all image modalities. Once learned, the space allows making zero-shot translations between two modalities for which paired data is not available. Moreover, a new modality can be easily integrated into the model easily, making it scalable.
|
biography : |
|
download slides : |
|
|
[ ]check this to delete slides
|
slidesFilename : |
|
|
slidesFilename is the name of downloadable file, and will be automatically filled when you upload a new file. You may change the name also.
|
links : |
|
notificationSent : |
final
|