Yao Zhai

Title: Yao Zhai - Innovator in Object Detection Technology

Introduction

Yao Zhai is a prominent inventor based in Redmond, WA (US). He has made significant contributions to the field of object detection through his innovative work with deep neural networks. His expertise in this area has led to the development of a patented technology that enhances the accuracy and efficiency of object detection in images.

Latest Patents

Yao Zhai holds a patent for "Object detection based on a feature map of a convolutional neural network." This patent describes implementations that relate to object detection based on deep neural networks. The technology aims to determine the class and boundary of one or more objects within an input image. Specifically, it involves generating a plurality of channel groups from a feature map of an image, which includes a region corresponding to a first grid. A target feature map is then extracted from one of the channel groups associated with a cell of the first grid. The information related to an object within the region is determined based on this target feature map, which may include the class and/or boundary of the object. Yao Zhai has 1 patent to his name.

Career Highlights

Yao Zhai is currently employed at Microsoft Technology Licensing, LLC, where he continues to work on advancements in technology related to object detection. His role at Microsoft allows him to collaborate with other talented professionals in the field, contributing to innovative projects that push the boundaries of current technology.

Collaborations

Some of Yao Zhai's coworkers include Jingjing Fu and Yan Lu. Their collaborative efforts in research and development have further enhanced the capabilities of the technologies they work on.

Conclusion

Yao Zhai is a key figure in the realm of object detection technology, with a focus on deep neural networks. His contributions through his patent and work at Microsoft Technology Licensing, LLC, highlight his commitment to innovation in this critical area of technology.