Jian-Jin Li

Jian-Jin Li

Auto-generated profile, based on publicly available information

Jian-Jin Li

Université Clermont Auvergne, Clermont-Ferrand, France

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
26 February 2021 in IEEE Access
Verified
Journal Article
Open access
HDHao Ding
Hao Ding
RTRuixin Tao
Ruixin Tao
JSJing Sun
Jing Sun
JLJin Liu
Jin Liu
FZFan Zhang
Fan Zhang
JLJianjin Li
Jianjin Li
With the development of communication networks and the widespread use of mobile terminals, videos are increasingly shared and distributed among mobile users. During the process, the video is recompressed to a certain file size on the sending side and sent to the receiving side via the server. This makes robust video watermark with low complexity to resist recompression attacks become an important issue to address. The proposed video watermarking method in this article is specially designed for resisting recompression attacks when quantization parameter (QP) is greatly increased. In the proposed method, by using the texture information and motion information of video, the invariance of video content under different quantization parameters could be found to help improve the anti-recompression attack ability of video watermark. Moreover, the proposed framework does not use a location map which has security risk to locate the watermark. It aims at finding the optimal location of watermark embedding adaptively according to the feature of video content itself. The experiment results indicate that the proposed video watermarking method can not only achieve greater robustness against recompression attack but also effectively limit the degradation in video perceptual quality.

27 February 2020 in IEEE Access
Verified
Journal Article
Open access
JCJean Connier
Jean Connier
HZhaiying zhou
haiying zhou
CVChristophe De Vaulx
Christophe De Vaulx
JLJian-Jin Li
Jian-Jin Li
HSHongling Shi
Hongling Shi
KHKun Mean Hou
Kun Mean Hou
The last few years have seen substantial progress in the field of smart objects (SOs): their number, diversity, performance and pervasiveness have all been quickly increasing and this evolution is expected to continue. To the best of our knowledge, little work has been made to leverage this abundance of resources to develop assistive devices for Visually Impaired People (VIP). However, we believe that SOs can both enhance traditional assistive functions (i.e. obstacle detection, navigation) and offer new ways of interacting with the environment. After describing spatial and non-spatial perceptive functions enabled by SOs, this article presents the SO2SEES, a system designed to be an interface between its user and neighboring SOs. The SO2SEES allows VIP to query surrounding SOs in an intuitive manner, relying on knowledge bases distributed on Internet of Things (IoT) cloud platforms and the SO2SEES’s own backend. To evaluate and validate the exposed concepts, we have developed a simple working implementation of the SO2SEES system using semantic web standards. A controlled-environment test scenario has been built around this early SO2SEES system to demonstrate its feasibility. As future works, we plan to conduct field experiments of this first prototype with VIP end users.

10 September 2025 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
HDHao Ding
Hao Ding
JSJing Sun
Jing Sun
RLRui Long
Rui Long
XJXiaoping Jiang
Xiaoping Jiang
HSHongling Shi
Hongling Shi
JLJian-Jin Li
Jian-Jin Li
The objective of visible-infrared person re-identification is to accurately match pedestrian images captured in different modalities. Since these images are taken from varying viewpoints by different cameras, the cross-modal detection task must address both modality discrepancies and camera variations. Many existing approaches primarily focus on minimizing inter-modality differences to enhance retrieval accuracy, often overlooking the impact of camera viewpoint differences. To tackle these challenges, this article introduces a hierarchical feature decoupling network. First, the network decouples and extracts camera-related and camera-irrelated features separately to mitigate the effects of camera variations. Second, it addresses modality differences by extracting modality-independent features. Additionally, an adversarial decoupling loss is employed to further disentangle identity-irrelevant information from identity-relevant features, thereby boosting the system’s accuracy and robustness. Extensive experiments conducted on the SYSU-MM01 and RegDB datasets validate the effectiveness of the proposed method.

3 July 2018 in IET Cyber-Physical Systems: Theory & Applications
Verified
Journal Article
Open access
PDF file
Xiaoyuan LuoXiaoyuan Luo
Xiaoyuan Luo
JLJianjin Li
Jianjin Li
ZJZhongping Jiang
Zhongping Jiang
Cyber‐physical systems are pervasive in every walk of life. The safety performances of these systems are threatened by external malicious attacks and unforeseen failures. In terms of grid structural characteristics and graph theory, this study proposes a new framework to solve the problem of structural vulnerability which is caused by undetectable attacks in power grids. Based on the linear continuous‐time descriptor system model, the digraph associated with structural matrix model for power grid is introduced in detail. To analyse the attack detectability in digraph, a series of basic properties are proposed about digraphs of structural power grids. Then an algorithm is proposed for obtaining the positions of the detection outputs to ensure left‐invertible and observability for grid systems. In addition, an algorithm for judging whether there exists a structural vulnerability for the arrangement of the attack inputs and outputs of power grids is proposed, by which one can find disjoint paths if there exists structural vulnerability. Finally, some examples are shown to verify the effectiveness of the proposed algorithms.