Jinan, China

Xiang Liu

This inventor holds 1 USPTO granted patent. Top assignee: Shandong Normal University. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Xiang Liu. Retrieved from https://idiyas.com/inventor/xiang-liu-w0c8pr8l

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile


Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

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

Title: Xiang Liu: Inventor in Computer Vision

Introduction

Xiang Liu is an inventor based in Jinan, China. His work includes a patented approach to recognizing human interactive behavior using computer vision and multi-view comparison.

Latest Patents

Liu is associated with 1 patent: “Method and System for Identifying Human Interactive Behavior Based on Multi-View Comparison.” The invention describes a method for analyzing video by tracking human-joint positions and building a spatio-temporal skeleton graph. A graph convolutional neural network adaptively removes edges or nodes to create enhanced views. Using the information bottleneck principle, the method balances differences between those views and the original graph while retaining information useful for behavior recognition. The resulting multi-view representation is then used to identify human interactive behavior.

Career Highlights

Liu is associated with Shandong Normal University. His patent focuses on applying graph-based learning and multi-view representations to a computer-vision task.

Collaborations

The provided information lists Lei Lyu and Chen Pang as Liu’s coworkers.

Conclusion

Xiang Liu’s patent presents a graph-based, multi-view method for recognizing human interactive behavior, reflecting his work in computer vision at Shandong Normal University.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…