Wei Xiang

Title: Innovations by Wei Xiang in Real-Time Object Detection and Semantic Segmentation

Introduction

Wei Xiang is an accomplished inventor based in Mountain View, CA (US). He has made significant contributions to the field of computer vision, particularly in real-time object detection and semantic segmentation. With a total of 2 patents, his work is at the forefront of technological advancements in this area.

Latest Patents

Wei Xiang's latest patents include a "System and method for real-time, simultaneous object detection and semantic segmentation" and "ThunderNet: a turbo unified network for real-time semantic segmentation." The first patent describes a system that utilizes a computing device with a processor and non-volatile memory. This system is designed to receive an image of a scene and process it using a neural network backbone to obtain a feature map. The feature map is then processed by an object detection module and a semantic segmentation module, both trained using a common loss function. The second patent outlines a system that processes an image through an encoder, pyramid pooling module, and decoder to achieve effective semantic segmentation.

Career Highlights

Wei Xiang has worked with notable companies such as Beijing Jingdong Shangke Information Technology Co., Ltd. and JD.com American Technologies Corporation. His experience in these organizations has contributed to his expertise in developing innovative solutions in the tech industry.

Collaborations

Some of Wei Xiang's coworkers include Hongda Mao and Chumeng Lyu. Their collaboration has likely fostered a creative environment that encourages innovation and the development of cutting-edge technologies.

Conclusion

Wei Xiang's contributions to real-time object detection and semantic segmentation demonstrate his commitment to advancing technology. His patents reflect a deep understanding of complex systems and a drive to innovate in the field of computer vision.