Ying Chen

Ying Chen

Auto-generated profile, based on publicly available information

Ying Chen

Alibaba Group

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 April 2021 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
AZAoyang Zhang
Aoyang Zhang
QLQing Li
Qing Li
YCYing Chen
Ying Chen
XMXiaoteng Ma
Xiaoteng Ma
LZLonghao Zou
Longhao Zou
GMGabriel-Miro Muntean
Gabriel-Miro Muntean
Edge computing provides the potential to improve users’ Quality of Experience (QoE) in ever-increasing video delivery. However, existing edge-based solutions cannot fully utilize the edge computing power and storage capacity. This paper proposes VI deo S uper-resolution and CA ching (VISCA), an edge-assisted adaptive video streaming solution, which integrates super-resolution and edge caching to improve users’ QoE. We design a novel edge-based ABR algorithm that makes bitrate and video chunk source decisions by considering network conditions, QoE objectives, and edge resource availability jointly. VISCA utilizes super-resolution to enhance the cached low-quality video at the edge. The super-resolution models used are trained for the most popular videos only in order to achieve quality improvements with a fraction of the computation. A novel cache strategy is also adopted to maximize caching efficiency. To assess the performance of VISCA, an implemented prototype of VISCA was deployed in synthetic and real network contexts. Compared with the existing video streaming solutions, VISCA improves video quality by 28.2%-251.2% and reduces rebuffering time by 16.1%-95.6% in all considered scenarios.

3 November 2022
Verified
Book Chapter
Closed access
PDF file
CYCanqian Yang
Canqian Yang
MJMeiguang Jin
Meiguang Jin
YXYi Xu
Yi Xu
RZRui Zhang
Rui Zhang
YCYing Chen
Ying Chen
HLHuaida Liu
Huaida Liu

19 September 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
QLQing Li
Qing Li
YCYing Chen
Ying Chen
AZAoyang Zhang
Aoyang Zhang
YJYong Jiang
Yong Jiang
LZLonghao Zou
Longhao Zou
GMGabriel-Miro Muntean
Gabriel-Miro Muntean
In the context of the latest growing popularity of live video streaming, ensuring high video quality has become one of the most significant challenges faced by all live streaming platforms. Insufficient uplink bandwidth is an important factor that influences these live video transmissions, affecting their bitrate and latency and consequently the associated video streaming quality. This paper proposes a novel flexible super-resolution-based video coding and uploading framework (FlexSRVC) that improves the quality of live video streaming in limited uplink network bandwidth conditions. FlexSRVC includes a flexible video coding scheme, which compresses high-resolution key and non-key video frames to a lower bitrate in order to reduce the upload delay. A new flexible bitrate adaptation algorithm is also proposed to select dynamically the number of frames to be compressed and the compression ratio by jointly considering uplink network conditions and available cloud computing resources. Trace-driven emulations demonstrate that FlexSRVC provides the same quality while reducing up to 25% of the required bandwidth compared to the original encoding method (H.264). FlexSRVC improves users' QoE by at least 50% compared to a super resolution-based method which employs reconstruction of all video frames in uplink bandwidth constrained conditions.

4 February 2023 in arXiv
Verified
Preprint
Open access
PDF file
MZMeisong Zheng
Meisong Zheng
QXQunliang Xing
Qunliang Xing
MQMinglang Qiao
Minglang Qiao
MXMai Xu
Mai Xu
LJLai Jiang
Lai Jiang
YCYing Chen
Ying Chen
As a widely studied task, video restoration aims to enhance the quality of the videos with multiple potential degradations, such as noises, blurs and compression artifacts. Among video restorations, compressed video quality enhancement and video super-resolution are two of the main tacks with significant values in practical scenarios. Recently, recurrent neural networks and transformers attract increasing research interests in this field, due to their impressive capability in sequence-to-sequence modeling. However, the training of these models is not only costly but also relatively hard to converge, with gradient exploding and vanishing problems. To cope with these problems, we proposed a two-stage framework including a multi-frame recurrent network and a single-frame transformer. Besides, multiple training strategies, such as transfer learning and progressive training, are developed to shorten the training time and improve the model performance. Benefiting from the above technical contributions, our solution wins two champions and a runner-up in the NTIRE 2022 super-resolution and quality enhancement of compressed video challenges. Code is available at https://github.com/ryanxingql/winner-ntire22-vqe.

17 September 2024 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
JWJiahao Wu
Jiahao Wu
DDDexin Deng
Dexin Deng
YLYilin Li
Yilin Li
LYLu Yu
Lu Yu
KLKai Li
Kai Li
YCYing Chen
Ying Chen