This inventor holds 2 USPTO granted patents. Top assignee: Google Inc.. Active years: 2019-2020.
Company Filing History:
Years Active: 2019-2020
Title: Innovations of Yang Xian in Video Coding
Introduction
Yang Xian is an accomplished inventor based in Forest Hills, NY (US). He has made significant contributions to the field of video coding, holding a total of 2 patents. His work focuses on enhancing the efficiency of video encoding through advanced machine learning techniques.
Latest Patents
Yang Xian's latest patents include "Multi-level machine learning-based early termination in partition search for video coding." This invention describes classifiers that determine whether to partition a block in a frame during prediction using recursive partitioning. Blocks of training video frames are encoded to generate encoded blocks. Training instances are created for these blocks, which include feature values extracted from each encoded block and a label indicating whether the block is partitioned into smaller blocks. The classifiers are trained for different block sizes, using the training instances as input to a machine-learning process. The output of these classifiers plays a crucial role in deciding whether input blocks are partitioned during the encoding of video sequences.
Career Highlights
Yang Xian is currently employed at Google Inc., where he continues to innovate in the realm of video technology. His expertise in machine learning and video coding has positioned him as a key player in his field.
Collaborations
Yang has collaborated with notable coworkers such as Yunqing Wang and Xintong Han, contributing to various projects that push the boundaries of video encoding technology.
Conclusion
Yang Xian's innovative work in video coding exemplifies the intersection of machine learning and practical applications in technology. His contributions are paving the way for more efficient video encoding methods, showcasing the importance of innovation in this rapidly evolving field.