Chengying Gao

Chengying Gao

Auto-generated profile, based on publicly available information

Chengying Gao

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
24 October 2018 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
YCY. R. Cui
Y. R. Cui
QLQ. Liu
Q. Liu
CGC. Y. Gao
C. Y. Gao
ZSZhuo Su
Zhuo Su

24 September 2020
Verified
Book Chapter
Closed access
PDF file
JGJibin Gao
Jibin Gao
WZWei-Shi Zheng
Wei-Shi Zheng
JPJia-Hui Pan
Jia-Hui Pan
CGChengying Gao
Chengying Gao
YWYaowei Wang
Yaowei Wang
JLJianhuang Lai
Jianhuang Lai

21 February 2019 in ACM Transactions on Sensor Networks
Verified
Journal Article
Open access
QNQun Niu
Qun Niu
MLMingkuan Li
Mingkuan Li
SHSuining He
Suining He
CGChengying Gao
Chengying Gao
SCS. -H. Gary Chan
S. -H. Gary Chan
XLXiaonan Luo
Xiaonan Luo
Image-based indoor localization has aroused much interest recently because it requires no infrastructure support. Previous approaches on image-based localization, due to their computation and storage requirements, often process queries at servers. This does not scale well, incurs round-trip delay, and requires constant network connectivity. Many also require users to manually confirm the shortlisted matched landmarks, which is inconvenient, slow, and prone to selection error. To overcome these limitations, we propose a h ighly a utomated (in terms of image confirmation after taking images) i mage-based l ocalization algorithm (HAIL), distributed in mobile devices. HAIL achieves resource efficiency (in terms of storage and processing) by keeping only distinguishing visual features for each landmark, and employing the efficient k-d tree to search for features. It further utilizes motion sensors and map constraints to enhance the localization accuracy without user operation. We have implemented HAIL on Android platforms and conducted extensive experiments in a food plaza and a premium shopping mall. Experimental results show that it achieves much higher localization accuracy (reducing the localization error by more than 20%) and computation efficiency (by more than 40% in time) as compared with the state-of-the-art approaches.

1 October 2021 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
RCRuizhi Cao
Ruizhi Cao
HMHaoran Mo
Haoran Mo
CGChengying Gao
Chengying Gao

14 April 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LHLifeng Huang
Lifeng Huang
CGChengying Gao
Chengying Gao
NLNing Liu
Ning Liu
Although adversarial examples pose a serious threat to deep neural networks, most transferable adversarial attacks are ineffective against black-box defense models. This may lead to the mistaken belief that adversarial examples are not truly threatening. In this paper, we propose a novel transferable attack that can defeat a wide range of black-box defenses and highlight their security limitations. We identify two intrinsic reasons why current attacks may fail, namely data-dependency and network-overfitting. They provide a different perspective on improving the transferability of attacks. To mitigate the data-dependency effect, we propose the Data Erosion method. It involves finding special augmentation data that behave similarly in both vanilla models and defenses, to help attackers fool robustified models with higher chances. In addition, we introduce the Network Erosion method to overcome the network-overfitting dilemma. The idea is conceptually simple: it extends a single surrogate model to an ensemble structure with high diversity, resulting in more transferable adversarial examples. Two proposed methods can be integrated to further enhance the transferability, referred to as Erosion Attack (EA). We evaluate the proposed EA under different defenses that empirical results demonstrate the superiority of EA over existing transferable attacks and reveal the underlying threat to current robust models. Codes will be publicly available.

27 May 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XLXiao Liang
Xiao Liang
WLWensheng Li
Wensheng Li
LHLifeng Huang
Lifeng Huang
CGChengying Gao
Chengying Gao
A wonderful piece of music is the essence and soul of dance, which motivates the study of automatic music generation for dance. To create appropriate music from dance, cross-modal correlations between dance and music such as rhythm and style, should be considered. However, existing dance-to-music methods have difficulties in achieving rhythmic alignment and stylistic matching simultaneously. Additionally, the diversity of generated samples is limited due to the lack of available paired data. To address these issues, we propose DanceComposer, a novel dance-to-music framework, which generates rhythmically and stylistically consistent multi-track music from dance videos. DanceComposer features a Progressive Conditional Music Generator (PCMG) that gradually incorporates rhythm and style constraints, enabling both rhythmic alignment and stylistic matching. To enhance style control, we introduce a Shared Style Module (SSM) that learns cross-modal features as stylistic constraints. This allows the PCMG can be trained on extensive music-only data and diversifies generated pieces. Quantitative and qualitative results show that our method surpasses the state-of-the-art in overall music quality, rhythmic consistency, and stylistic consistency.