Yu Xiang

Title: Innovations of Yu Xiang in Object Detection Technology

Introduction

Yu Xiang is an accomplished inventor based in Palo Alto, CA (US). He has made significant contributions to the field of computer vision, particularly in object detection technologies. His innovative approach utilizes advanced neural network architectures to enhance the accuracy and efficiency of object detection systems.

Latest Patents

Yu Xiang holds a patent for a groundbreaking invention titled "Subcategory-aware convolutional neural networks for object detection." This patent presents a computer-implemented method for detecting objects using subcategory-aware convolutional neural networks (CNNs). The method involves generating object region proposals from an image through a region proposal network (RPN) that incorporates subcategory information. It also includes classifying and refining these proposals using an object detection network (ODN) that performs object category classification, subcategory classification, and bounding box regression simultaneously. The input to both the RPN and ODN is an image pyramid, and each network features a layer designed to extrapolate features for detecting object categories with scale variations.

Career Highlights

Yu Xiang is currently employed at NEC Corporation, where he continues to develop innovative solutions in the realm of artificial intelligence and machine learning. His work has positioned him as a key player in advancing the capabilities of object detection systems.

Collaborations

Yu has collaborated with notable colleagues, including Wongun Choi and Yuanqing Lin, who share his passion for pushing the boundaries of technology in their respective fields.

Conclusion

Yu Xiang's contributions to object detection technology through his innovative patent demonstrate his expertise and commitment to advancing the field. His work at NEC Corporation and collaborations with fellow inventors further highlight his impact on the industry.