Cheng Chen
Research Interests
Cheng Chen has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Shu Shi
Bytedance, San Diego, USA
1 shared publication - Wenpei Yin
Shanghai Jiaotong University
1 shared publication - Zhexiong Huang
Bytedance
1 shared publication
Latest Publications
- Open Access
- 15 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 34-44
AGiLE
As live streaming video continues to gain popularity, encoding efficiency remains a critical challenge. Current commercial systems limit the Group of Picture (GOP) length to optimize for spontaneous viewer access, but this often compromises encoding efficiency, especially for popular live streams with intricate background textures and minimal global motion. This paper introduces AGiLE (Adaptive GOP in Live video Encoding), an innovative solution that employs 'pseudo-GOP' to separate encoding efficiency from transmission needs. AGiLE is designed for easy industry adoption and includes a supervised-learning based algorithm for adaptive GOP selection. Our experiments on Douyin's popular live content indicate that AGiLE can reduce bandwidth usage by up to 3.48%, making it a promising solution for the future of live streaming.
- 15 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 34-44
Open AccessAGiLE
As live streaming video continues to gain popularity, encoding efficiency remains a critical challenge. Current commercial systems limit the Group of Picture (GOP) length to optimize for spontaneous viewer access, but this often compromises encoding efficiency, especially for popular live streams with intricate background textures and minimal global motion. This paper introduces AGiLE (Adaptive GOP in Live video Encoding), an innovative solution that employs 'pseudo-GOP' to separate encoding efficiency from transmission needs. AGiLE is designed for easy industry adoption and includes a supervised-learning based algorithm for adaptive GOP selection. Our experiments on Douyin's popular live content indicate that AGiLE can reduce bandwidth usage by up to 3.48%, making it a promising solution for the future of live streaming.