Shanghai, China

Linxi Jiang

This inventor holds 1 USPTO granted patent. Top assignee: Fudan University. Active years: 2020.


% Patents Active = 100.0

Average Co-Inventor Count = 3.0

ph-index = 1

Forward Citations = 8(Granted Patents)


Company Filing History:


Years Active: 2020

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Linxi Jiang: Innovator in Video Recognition Security

Introduction

Linxi Jiang is a prominent inventor based in Shanghai, China. He has made significant contributions to the field of video recognition security through his innovative patent. His work focuses on developing methods to enhance the robustness of video recognition models against adversarial attacks.

Latest Patents

Linxi Jiang holds a patent titled "Black-box adversarial attacks on videos." This patent outlines a method for generating black-box adversarial attacks on video recognition models. The process involves several steps, including passing input video frames into a public image model to obtain pixel-wise tentative perturbations, partitioning these perturbations into patches, and estimating the rectification weight required for each patch. The method iteratively applies projected gradient descent perturbation on the input video until an attack succeeds or a query limit is reached. This innovative approach aims to improve the security of video recognition systems.

Career Highlights

Linxi Jiang is affiliated with Fudan University, where he continues to advance his research in video recognition and security. His academic background and ongoing projects contribute to the development of cutting-edge technologies in this field.

Collaborations

Linxi Jiang collaborates with notable colleagues, including Yugang Jiang and Xingjun Ma. Their combined expertise fosters a productive research environment that enhances the quality and impact of their work.

Conclusion

Linxi Jiang's contributions to video recognition security through his innovative patent demonstrate his commitment to advancing technology in this critical area. His work not only addresses current challenges but also paves the way for future developments in video recognition systems.

Profile summary based on public USPTO records.
Please report any incorrect information to [email protected]
Loading…