Scene understanding based on visual and text data

In this project, the concept of scene understanding with visual and text data will be applied to the task of video captioning, and its effectiveness would be evaluated. A new dataset of videos and its accompanying captions, which aims to be an improvement over current datasets, will be collected for...

Full description

Saved in:

Bibliographic Details
Main Author:	Ong, Randal Ren Tai
Other Authors:	Mao Kezhi
Format:	Final Year Project
Language:	English
Published:	2019
Subjects:	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Online Access:	http://hdl.handle.net/10356/77701
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-77701
record_format	dspace
spelling	sg-ntu-dr.10356-777012023-07-07T17:49:36Z Scene understanding based on visual and text data Ong, Randal Ren Tai Mao Kezhi School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems In this project, the concept of scene understanding with visual and text data will be applied to the task of video captioning, and its effectiveness would be evaluated. A new dataset of videos and its accompanying captions, which aims to be an improvement over current datasets, will be collected for training and analysis. After which, it will be put through a baseline for training and analysis. The output metrics and captions will be observed and recorded to gauge if the numbers correlate with human judgement, and whether would they be accurate or not. The possible reasons for the accuracy will also be analysed and perhaps proposed for future work as well. Bachelor of Engineering (Electrical and Electronic Engineering) 2019-06-04T04:37:14Z 2019-06-04T04:37:14Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77701 en Nanyang Technological University 32 p. application/pdf
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
spellingShingle	DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems Ong, Randal Ren Tai Scene understanding based on visual and text data
description	In this project, the concept of scene understanding with visual and text data will be applied to the task of video captioning, and its effectiveness would be evaluated. A new dataset of videos and its accompanying captions, which aims to be an improvement over current datasets, will be collected for training and analysis. After which, it will be put through a baseline for training and analysis. The output metrics and captions will be observed and recorded to gauge if the numbers correlate with human judgement, and whether would they be accurate or not. The possible reasons for the accuracy will also be analysed and perhaps proposed for future work as well.
author2	Mao Kezhi
author_facet	Mao Kezhi Ong, Randal Ren Tai
format	Final Year Project
author	Ong, Randal Ren Tai
author_sort	Ong, Randal Ren Tai
title	Scene understanding based on visual and text data
title_short	Scene understanding based on visual and text data
title_full	Scene understanding based on visual and text data
title_fullStr	Scene understanding based on visual and text data
title_full_unstemmed	Scene understanding based on visual and text data
title_sort	scene understanding based on visual and text data
publishDate	2019
url	http://hdl.handle.net/10356/77701
_version_	1772828881716248576

Scene understanding based on visual and text data

Similar Items