Study on the Vulnerability of Video Retargeting Method for Generated Videos by Deep Learning Model

Aro Kim, Dong Hwi Kim, Sang Hyo Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Text-to-video generation is getting attention and the generated videos can be used in many applications. However, it is uncertain whether existing deep learning techniques work well for generated videos. In this paper, we compose a study of how generated videos can be retargeted by deep learning models with the ratio of the main object preserved and looked for ways to improve the quality of the generated and retargeted video frames. Throughout the experiment, we discover the errors of video retargeting on the generated videos in the processes of segmentation, inpainting, and relocating.

Original languageEnglish
Title of host publicationICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks
PublisherIEEE Computer Society
Pages834-836
Number of pages3
ISBN (Electronic)9798350335385
DOIs
StatePublished - 2023
Event14th International Conference on Ubiquitous and Future Networks, ICUFN 2023 - Paris, France
Duration: 4 Jul 20237 Jul 2023

Publication series

NameInternational Conference on Ubiquitous and Future Networks, ICUFN
Volume2023-July
ISSN (Print)2165-8528
ISSN (Electronic)2165-8536

Conference

Conference14th International Conference on Ubiquitous and Future Networks, ICUFN 2023
Country/TerritoryFrance
CityParis
Period4/07/237/07/23

Fingerprint

Dive into the research topics of 'Study on the Vulnerability of Video Retargeting Method for Generated Videos by Deep Learning Model'. Together they form a unique fingerprint.

Cite this