Mengjun Leng

Title: Innovations of Mengjun Leng in Video Codec Technology

Introduction

Mengjun Leng is an accomplished inventor based in San Jose, CA. He has made significant contributions to the field of video compression technology. His innovative work focuses on enhancing the efficiency of video streaming through advanced neural network techniques.

Latest Patents

Mengjun Leng holds a patent for a "Streaming Neural Network Video Codec System and Method." This invention leverages temporal redundancy by processing video frames in a rolling window fashion. By encoding video frames using information from multiple frames and transmitting only essential codewords, the system ensures efficient compression with reduced computational overhead. Resiliency to lost codewords is achieved by training with random masks on one or more codewords, making the decoder robust to packet losses. These techniques have improved compression efficiency and significantly reduced the average operations required per frame, allowing for real-time, high-quality video streaming. He has 1 patent to his name.

Career Highlights

Mengjun Leng is currently employed at Cisco Technology, Inc., where he continues to develop innovative solutions in video technology. His work has been instrumental in advancing the capabilities of video streaming systems.

Collaborations

Mengjun has collaborated with notable colleagues, including Samer Lutfi Hijazi and Rafal Pilarczyk, contributing to the success of various projects within the company.

Conclusion

Mengjun Leng's contributions to video codec technology exemplify the impact of innovative thinking in enhancing real-time video streaming. His work continues to shape the future of video communication.