stat441w18/Image Question Answering using CNN with Dynamic Parameter Prediction: Difference between revisions
Jump to navigation
Jump to search
(testing out sub-sectioning) |
(trying subsections again) |
||
Line 1: | Line 1: | ||
'''''Image Question Answering using CNN with Dynamic Parameter Prediction''''' | '''''Image Question Answering using CNN with Dynamic Parameter Prediction''''' | ||
= Presented by = | |||
Rosie Zou, Kye Wei, Glen Chalatov, Ameer Dharamshi | Rosie Zou, Kye Wei, Glen Chalatov, Ameer Dharamshi | ||
= Introduction = | |||
= Problem Setup (in words) = | == Problem Setup (in words) == | ||
= Previous and Related Works = | == Previous and Related Works == | ||
As mentioned in the earlier section, one of the major goals in computer vision is to achieve holistic understanding. While relatively new interest in the computer vision community, Image Question Answering already has a growing number of researchers working on this problem. | As mentioned in the earlier section, one of the major goals in computer vision is to achieve holistic understanding. While relatively new interest in the computer vision community, Image Question Answering already has a growing number of researchers working on this problem. | ||
= Problem Setup (in mathematical terms) = | == Problem Setup (in mathematical terms) == | ||
= Mathematical Background = | |||
== CNNs == | |||
== GRUs and RNNs == | |||
= | = Model = | ||
== VGGNet == | |||
= | == Parameter Prediction Network == | ||
== Hashing == | |||
= | |||
= Parameter Prediction Network = | |||
= Hashing = | |||
= Model Summary = | = Model Summary = | ||
== Training and Results == | |||
===Training === | |||
==Training == | ==== Error Reduction ==== | ||
= Error Reduction = | ==== Pre-trained GRUs ==== | ||
= Pre-trained GRUs = | ==== Fine-tuning ==== | ||
= Fine-tuning= | === Results === | ||
== Results == | |||
= Critique= | = Critique= |
Revision as of 01:40, 15 March 2018
Image Question Answering using CNN with Dynamic Parameter Prediction
Presented by
Rosie Zou, Kye Wei, Glen Chalatov, Ameer Dharamshi
Introduction
Problem Setup (in words)
Previous and Related Works
As mentioned in the earlier section, one of the major goals in computer vision is to achieve holistic understanding. While relatively new interest in the computer vision community, Image Question Answering already has a growing number of researchers working on this problem.