TY - GEN
T1 - Study on the Vulnerability of Video Retargeting Method for Generated Videos by Deep Learning Model
AU - Kim, Aro
AU - Kim, Dong Hwi
AU - Park, Sang Hyo
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85169295806&partnerID=8YFLogxK
U2 - 10.1109/ICUFN57995.2023.10201216
DO - 10.1109/ICUFN57995.2023.10201216
M3 - Conference contribution
AN - SCOPUS:85169295806
T3 - International Conference on Ubiquitous and Future Networks, ICUFN
SP - 834
EP - 836
BT - ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks
PB - IEEE Computer Society
T2 - 14th International Conference on Ubiquitous and Future Networks, ICUFN 2023
Y2 - 4 July 2023 through 7 July 2023
ER -