In previous machine learning based fast intra mode decision algorithms for screen content videos, feature design is a key task and it is always difficult to obtain distinguishable features. In this paper, the idea of interaction of features is introduced to fast video coding algorithm, and a fast intra mode decision algorithm based on feature cross is proposed for screen content videos. The numeric features and category features are designed based on the characteristics of screen content videos, and the adaptive factorization network (AFN) is improved and adopted to carry out feature interaction to designed features, and output distinguishable features. The experimental results show that for AI (All Intra) configuration, compared with standard VVC/H.266, the coding time is reduced by 29.64% and the BD rate is increased only by 1.65%.
Zhi LIU
North China University of Technology
Siyuan ZHANG
North China University of Technology
Xiaohan GUAN
North China University of Technology
Mengmeng ZHANG
North China University of Technology,Beijing Union University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Zhi LIU, Siyuan ZHANG, Xiaohan GUAN, Mengmeng ZHANG, "A Fast Intra Mode Decision Algorithm in VVC Based on Feature Cross for Screen Content Videos" in IEICE TRANSACTIONS on Fundamentals,
vol. E107-A, no. 1, pp. 178-181, January 2024, doi: 10.1587/transfun.2023EAL2013.
Abstract: In previous machine learning based fast intra mode decision algorithms for screen content videos, feature design is a key task and it is always difficult to obtain distinguishable features. In this paper, the idea of interaction of features is introduced to fast video coding algorithm, and a fast intra mode decision algorithm based on feature cross is proposed for screen content videos. The numeric features and category features are designed based on the characteristics of screen content videos, and the adaptive factorization network (AFN) is improved and adopted to carry out feature interaction to designed features, and output distinguishable features. The experimental results show that for AI (All Intra) configuration, compared with standard VVC/H.266, the coding time is reduced by 29.64% and the BD rate is increased only by 1.65%.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2023EAL2013/_p
Copy
@ARTICLE{e107-a_1_178,
author={Zhi LIU, Siyuan ZHANG, Xiaohan GUAN, Mengmeng ZHANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Fast Intra Mode Decision Algorithm in VVC Based on Feature Cross for Screen Content Videos},
year={2024},
volume={E107-A},
number={1},
pages={178-181},
abstract={In previous machine learning based fast intra mode decision algorithms for screen content videos, feature design is a key task and it is always difficult to obtain distinguishable features. In this paper, the idea of interaction of features is introduced to fast video coding algorithm, and a fast intra mode decision algorithm based on feature cross is proposed for screen content videos. The numeric features and category features are designed based on the characteristics of screen content videos, and the adaptive factorization network (AFN) is improved and adopted to carry out feature interaction to designed features, and output distinguishable features. The experimental results show that for AI (All Intra) configuration, compared with standard VVC/H.266, the coding time is reduced by 29.64% and the BD rate is increased only by 1.65%.},
keywords={},
doi={10.1587/transfun.2023EAL2013},
ISSN={1745-1337},
month={January},}
Copy
TY - JOUR
TI - A Fast Intra Mode Decision Algorithm in VVC Based on Feature Cross for Screen Content Videos
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 178
EP - 181
AU - Zhi LIU
AU - Siyuan ZHANG
AU - Xiaohan GUAN
AU - Mengmeng ZHANG
PY - 2024
DO - 10.1587/transfun.2023EAL2013
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E107-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2024
AB - In previous machine learning based fast intra mode decision algorithms for screen content videos, feature design is a key task and it is always difficult to obtain distinguishable features. In this paper, the idea of interaction of features is introduced to fast video coding algorithm, and a fast intra mode decision algorithm based on feature cross is proposed for screen content videos. The numeric features and category features are designed based on the characteristics of screen content videos, and the adaptive factorization network (AFN) is improved and adopted to carry out feature interaction to designed features, and output distinguishable features. The experimental results show that for AI (All Intra) configuration, compared with standard VVC/H.266, the coding time is reduced by 29.64% and the BD rate is increased only by 1.65%.
ER -