Mountain View, CA, United States of America

Xiang Yu

This inventor holds 46 USPTO granted patents and 9 published patent applications, primarily in Face Recognition Technology. Top assignees: Nec Corporation, Nec C Orporation, Nec Hong Kong Limited. Active years: 2018-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Xiang Yu. Retrieved from https://idiyas.com/inventor/xiang-yu-5nt2q5mv

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

USPTO Granted Patents = 46 

% Patents Active = 95.7

Average Co-Inventor Count = 3.7

ph-index = 3

Forward Citations = 88(Granted Patents)


Company Filing History:


Years Active: 2018-2026

Loading Chart...
Areas of Expertise:
Optical Encryption
Video Domain Adaptation
Face Recognition
Multimodal Analysis
Privacy Guarantees
Activity Recognition
Landmark Localization
Knowledge Distillation
Siamese Network
Object Recognition
Deep Learning
Surveillance Systems
46 patents (USPTO):Explore Patents

Title: Innovations and Contributions of Xiang Yu in Facial Recognition Technology

Introduction

Xiang Yu, based in Mountain View, CA, has made significant strides in the field of facial recognition technology. With 36 patents to his name, his contributions showcase the intersection of innovation and practical application in technological solutions.

Latest Patents

Among his latest inventions, Xiang Yu developed a "Face-aware person re-identification system." This cutting-edge method employs facial information for unsupervised person re-identification. The system extracts body features through a body feature extractor and head features via a head feature extractor. By outputting both body and head descriptor vectors and concatenating them, a model can generate a comprehensive descriptor vector for enhanced identification accuracy.

Another noteworthy patent involves "Domain generalized margin via meta-learning for deep face recognition." This method innovatively trains a model for face recognition by utilizing a series of training batches to establish a face recognition model. The approach involves calculating sample weights, updating model weights, and leveraging gradients for improved performance in subsequent iterations. These processes collectively enhance the efficiency and reliability of deep face recognition systems.

Career Highlights

Xiang Yu has contributed to prominent firms such as NEC Corporation and NEC Hong Kong Limited. His work in these companies has facilitated advancements in technology, particularly in the realm of facial recognition applications.

Collaborations

Throughout his career, Xiang has collaborated with renowned professionals in the field, including Manmohan Chandraker and Kihyuk Sohn. These partnerships have fostered innovative ideas and spurred advancements in technology through collaborative research and development.

Conclusion

Xiang Yu's dedication to innovation in facial recognition technology is evident through his numerous patents and collaborations. As advancements in this field continue to unfold, his contributions are likely to have a lasting impact on both the industry and society.

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…