Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Sang-hyo Park"'
Publikováno v:
IET Computer Vision, Vol 18, Iss 6, Pp 745-758 (2024)
Abstract The authors propose a compression strategy for a 3D human pose estimation model based on a transformer which yields high accuracy but increases the model size. This approach involves a pruning‐guided determination of the search range to ac
Externí odkaz:
https://doaj.org/article/73a359104af54036b73da2c2ea94479d
Autor:
Aro Kim, Seung-taek Woo, Minho Park, Dong-hwi Kim, Hanshin Lim, Soon-heung Jung, Sangwoon Kwak, Sang-hyo Park
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2024, Iss 1, Pp 1-20 (2024)
Abstract In the video compression industry, video compression tailored to machine vision tasks has recently emerged as a critical area of focus. Given the unique characteristics of machine vision, the current practice of directly employing convention
Externí odkaz:
https://doaj.org/article/5127105087e847289b927b5d68f733d9
Autor:
Sang-hyo Park
Publikováno v:
ICT Express, Vol 5, Iss 2, Pp 136-140 (2019)
While motion estimation (ME) efficiently compresses video data by reducing temporal redundancy between frames, it does so at the cost of computational complexity. In particular, the complexity of sub-pixel ME (SME) greatly limits fast video encoding
Externí odkaz:
https://doaj.org/article/2830ed64badb4038b953f2a04789a0b8
Autor:
Sang-Hyo Park, Je-Won Kang
Publikováno v:
IEEE Access, Vol 7, Pp 158075-158084 (2019)
In this paper, we propose a fast encoding method to facilitate an affine motion estimation (AME) process in versatile video coding (VVC) encoders. The recently-launched VVC project for next-generation video coding standardization far outperforms the
Externí odkaz:
https://doaj.org/article/1af52ab864bb434b8ff12bd04c79e009
Autor:
Sang-Hyo Park, Je-Won Kang
Publikováno v:
IEEE Access, Vol 7, Pp 172597-172605 (2019)
This paper presents a fast encoding method for versatile video coding (VVC) using an early determination scheme that skips redundant multi-type tree (MTT) pruning. MTT consists of binary and ternary trees (TTs) with traditional quadtrees and has rece
Externí odkaz:
https://doaj.org/article/2d56b16bcfc14108afead34a4c50b4a3
Publikováno v:
Sensors, Vol 22, Iss 17, p 6328 (2022)
In this paper, we propose an object-cooperated decision method for efficient ternary tree (TT) partitioning that reduces the encoding complexity of versatile video coding (VVC). In most previous studies, the VVC complexity was reduced using decision
Externí odkaz:
https://doaj.org/article/8f2afdd429cd45efa387fa98e04b9298
Publikováno v:
Applied Sciences, Vol 11, Iss 17, p 7803 (2021)
Since high quality realistic media are widely used in various computer vision applications, image compression is one of the essential technologies to enable real-time applications. Image compression generally causes undesired compression artifacts, s
Externí odkaz:
https://doaj.org/article/90a94fa2a1d043e08a4c0bb5e910d668
Autor:
Jungwon Lee, Sang-hyo Park
Publikováno v:
Journal of Computing Science and Engineering. 17:13-19
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4ca7c4a95a658aa90e36414e491ffb5
https://doi.org/10.5626/jcse.2023.17.1.13
https://doi.org/10.5626/jcse.2023.17.1.13
Autor:
Kavita Arjun Bhosale, Sang-Hyo Park
Publikováno v:
Journal of Computing Science and Engineering. 16:185-193
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a72f5442b915088427cf71c2d5e9106a
https://doi.org/10.5626/jcse.2022.16.4.185
https://doi.org/10.5626/jcse.2022.16.4.185
Autor:
Jaehyun Bae, Sang-hyo Park
Publikováno v:
Journal of Electronic Imaging. 32
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c02d0998bacf48d876dd9b268ce276ff
https://doi.org/10.1117/1.jei.32.2.023012
https://doi.org/10.1117/1.jei.32.2.023012