Jingjing Shen

Title: Innovations by Jingjing Shen

Introduction

Jingjing Shen is a prominent inventor based in Cambridge, GB. She has made significant contributions to the field of technology, particularly in image processing and neural networks. With a total of 7 patents to her name, her work continues to influence advancements in various applications.

Latest Patents

One of her latest patents is titled "Model fitting using keypoint regression." This innovation involves predicting keypoints in an image, where predictions are generated for each keypoint as a 2D random variable, normally distributed with location (x, y) and standard deviation sigma. A neural network is trained to maximize a log-likelihood that samples from each of the predicted keypoints equal a ground truth. The trained neural network can then predict keypoints of an image without generating a heatmap.

Another notable patent is "Repairing image depth values for an object with a light absorbing surface." This system is designed to detect and track the three-dimensional pose of an object, such as a head-mounted display device, in a color image using an accessible three-dimensional model of the object. The system utilizes the three-dimensional pose to repair pixel depth values associated with a region of the object that absorbs light emitted by a time-of-flight depth sensor. As a result, a color-depth image can be produced that does not include dark holes on and around the region of the object.

Career Highlights

Jingjing Shen is currently employed at Microsoft Technology Licensing, LLC, where she continues to innovate and develop new technologies. Her work has garnered attention for its practical applications and contributions to the field.

Collaborations

Throughout her career, she has collaborated with notable colleagues, including Thomas Joseph Cashman and Erroll William Wood. These partnerships have further enhanced her research and development efforts.

Conclusion

Jingjing Shen's contributions to technology through her patents and innovations demonstrate her expertise and commitment to advancing the field. Her work continues to pave the way for future developments in image processing and neural networks.