Automatic Generation of a Coherent Story from a Set of Images

Zainy M. Malakan

doi:10.26182/7sr6-am61

Automatic Generation of a Coherent Story from a Set of Images

Zainy M. Malakan

School of Physics, Mathematics and Computing

Research output: Thesis › Doctoral Thesis

167 Downloads (Pure)

Abstract

This dissertation explores vision and language (V&L) algorithms. While (V&L) succeeds in image and video captioning tasks, the dynamic Visual Storytelling Task (VST) remains challenging. VST demands coherent stories from a set of images, requiring grammatical accuracy, flow, and style. The dissertation addresses these challenges. Chapter 2 presents a framework utilizing an advanced language model. Chapters 3 and 4 introduce novel techniques that integrate rich visual representation to enhance generated stories. Chapter 5 introduces a new storytelling dataset with a comprehensive analysis. Chapter 6 proposes a state-of-the-art Transformer-based model for generating coherent and informative story descriptions from image sets.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	The University of Western Australia
Supervisors/Advisors	Mian, Ajmal, Supervisor Hassan, Mubashar, Supervisor
Award date	9 Jan 2024
DOIs	https://doi.org/10.26182/7sr6-am61
Publication status	Unpublished - 2024

Access to Document

10.26182/7sr6-am61

DOCTOR OF PHILOSOPHY - ALJAWY Zainy Mohsen Malakan - 2023_
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

Cite this

@phdthesis{9b738ab488c7400ea08ad3ccb79ef291,

title = "Automatic Generation of a Coherent Story from a Set of Images",

abstract = "This dissertation explores vision and language (V&L) algorithms. While (V&L) succeeds in image and video captioning tasks, the dynamic Visual Storytelling Task (VST) remains challenging. VST demands coherent stories from a set of images, requiring grammatical accuracy, flow, and style. The dissertation addresses these challenges. Chapter 2 presents a framework utilizing an advanced language model. Chapters 3 and 4 introduce novel techniques that integrate rich visual representation to enhance generated stories. Chapter 5 introduces a new storytelling dataset with a comprehensive analysis. Chapter 6 proposes a state-of-the-art Transformer-based model for generating coherent and informative story descriptions from image sets.",

keywords = "Storytelling, Sequential Vision Understanding, Computer Vision",

author = "Malakan, {Zainy M.}",

year = "2024",

doi = "10.26182/7sr6-am61",

language = "English",

school = "The University of Western Australia",

}

TY - BOOK

T1 - Automatic Generation of a Coherent Story from a Set of Images

AU - Malakan, Zainy M.

PY - 2024

Y1 - 2024

N2 - This dissertation explores vision and language (V&L) algorithms. While (V&L) succeeds in image and video captioning tasks, the dynamic Visual Storytelling Task (VST) remains challenging. VST demands coherent stories from a set of images, requiring grammatical accuracy, flow, and style. The dissertation addresses these challenges. Chapter 2 presents a framework utilizing an advanced language model. Chapters 3 and 4 introduce novel techniques that integrate rich visual representation to enhance generated stories. Chapter 5 introduces a new storytelling dataset with a comprehensive analysis. Chapter 6 proposes a state-of-the-art Transformer-based model for generating coherent and informative story descriptions from image sets.

AB - This dissertation explores vision and language (V&L) algorithms. While (V&L) succeeds in image and video captioning tasks, the dynamic Visual Storytelling Task (VST) remains challenging. VST demands coherent stories from a set of images, requiring grammatical accuracy, flow, and style. The dissertation addresses these challenges. Chapter 2 presents a framework utilizing an advanced language model. Chapters 3 and 4 introduce novel techniques that integrate rich visual representation to enhance generated stories. Chapter 5 introduces a new storytelling dataset with a comprehensive analysis. Chapter 6 proposes a state-of-the-art Transformer-based model for generating coherent and informative story descriptions from image sets.

KW - Storytelling

KW - Sequential Vision Understanding

KW - Computer Vision

U2 - 10.26182/7sr6-am61

DO - 10.26182/7sr6-am61

M3 - Doctoral Thesis

ER -

Automatic Generation of a Coherent Story from a Set of Images

Abstract

Access to Document

Fingerprint

Cite this