Guosong Zhu

Guosong Zhu

Auto-generated profile, based on publicly available information

Guosong Zhu

Network and Data Security Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
24 August 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
GZGuosong Zhu
Guosong Zhu
ZQZhiguang Qin
Zhiguang Qin
Yi DingYi Ding
Yi Ding
YLYao Liu
Yao Liu
ZQZhiguang Qin
Zhiguang Qin
As a popular research topic in computer vision, video frame interpolation is widely used in video processing tasks. However, this task is often limited by slow processing speed or high memory consumption in practical applications. To address these drawbacks, a frame interpolation network focusing on motion regions named MFNet is proposed, which consists of a sampler for adaptive and efficient separation of motion regions from the background, a fine-grained module for direct approximation of intermediate streams, and a lightweight module for bi-directional optical stream fusion. Extensive experiments show that our MFNet achieves optimal accuracy on some frame interpolation tasks and is much faster than other state-of-the-art methods. In addition, transplantation of the core components of MFNet to other frame interpolation networks can significantly improve the performance.

11 November 2014 in Molecular Medicine Reports
Verified
Journal Article
Open access
PDF file
GLGangjian Luo
Gangjian Luo
GZGuosong Zhu
Guosong Zhu
DYDongdong Yuan
Dongdong Yuan
WYWeifeng Yao
Weifeng Yao
XCXinjin Chi
Xinjin Chi
ZHZiqing Hei
Ziqing Hei
Acute lung injury (ALI) induced by liver transplantation is detrimental to patient survival, and therapeutic strategies remain limited. Thus, the protective effects of propofol, a commonly used anesthetic with antioxidative and anti‑inflammatory properties, were investigated in the present study on ALI induced by orthotopic autologous liver transplantation (OALT). The protective mechanism of propofol was determined to be associated with the inhibition of NADPH oxidase, by comparing its effects with the positive controls apocynin (AP; an NADPH oxidase inhibitor) and N‑acegysteine (NAC; a scavenger of reactive oxygen species). The results demonstrated that two proteins (p47phox and gp91phox) of the NADPH oxidase system presented increased expression in rats with ALI induced by OALT, thus leading to increased activation of the oxidative stress and inflammatory reactions. Preconditioning with NAC or AP eliminated this increase, suggesting that antioxidative treatment, particularly with inhibitors of NADPH oxidase, is a promising protective strategy against ALI induced by OALT. Propofol preconditioning at a high (100 mg/kg) or low (50 mg/kg) dose promoted similar protective effects, with the high‑dose propofol producing a more marked effect than the low dose. The results suggested that propofol may protect against ALI induced by OALT, the mechanism of which may involve a reduced oxidative stress and inflammatory reaction mediated by NADPH oxidase inhibition.

1 June 2025 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
GZGuosong Zhu
Guosong Zhu
ZQZhiguang Qin
Zhiguang Qin
LYLinfang Yu
Linfang Yu
Yi DingYi Ding
Yi Ding
ZQZhiguang Qin
Zhiguang Qin
Feature matching is widely applied in the image processing field. However, both traditional feature matching methods and previous deep learning-based methods struggle to accurately match the features with severe deformations and large displacements, particularly in gastroscopy scenario. To fill this gap, an effective feature matching framework named TransMatch is proposed, which addresses the largely displacements issue by matching features with global information leveraged via Transformer structure. To address the severe deformation of features, an effective bridging strategy with a novel bidirectional quadratic interpolation network is employed. This bridging strategy decomposes and simplifies the matching of features undergoing severe deformations. A deblurring module for gastroscopy scenario is specifically designed to address the potential blurriness. Experiments have illustrated that proposed method achieves state-of-the-art performance of feature matching and frame interpolation in gastroscopy scenario. Moreover, a large-scale gastroscopy dataset is also constructed for multiple tasks.

1 January 2026 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
ZMZeping Ma
Zeping Ma
XZXudong Zhang
Xudong Zhang
YHYunfan Hu
Yunfan Hu
GLGuoyu Li
Guoyu Li
GZGuosong Zhu
Guosong Zhu
ZQZhiguang Qin
Zhiguang Qin

1 January 2026 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
GZGuosong Zhu
Guosong Zhu
ZMZeping Ma
Zeping Ma
ZQZhiguang Qin
Zhiguang Qin
Yi DingYi Ding
Yi Ding
ZQZhiguang Qin
Zhiguang Qin

1 January 2026 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
GLGuoyu Li
Guoyu Li
YYYang Yu
Yang Yu
GZGuosong Zhu
Guosong Zhu
ZMZeping Ma
Zeping Ma
JZJunzhi Zhu
Junzhi Zhu
ZQZhiguang Qin
Zhiguang Qin