Company Filing History:
Years Active: 2021-2023
Title: Innovations of Meng Song in Icon Identification Technology
Introduction
Meng Song is an accomplished inventor based in La Jolla, California. He has made significant contributions to the field of graphical icon identification, holding three patents to his name. His work focuses on enhancing the accuracy and efficiency of identifying icons within images and video streams.
Latest Patents
One of Meng Song's latest patents is centered around machine-learned single image icon identification. This patent presents systems, devices, media, and methods for identifying graphical icons within an image or video stream. The systems and methods receive an image that includes a graphical icon. They identify a set of proposed regions of the image, with at least one proposed region containing the graphical icon. The systems extract a set of semantic features for each proposed region. Based on these features, the systems identify a set of proposed icons corresponding to the graphical icon in the image and determine a match between the graphical icon and at least one proposed icon.
Career Highlights
Meng Song is currently employed at Snap Inc., where he continues to innovate in the field of image processing and icon identification. His work has been instrumental in advancing the capabilities of visual recognition technologies.
Collaborations
Meng collaborates with talented individuals such as Harsh Agrawal and Xiaoyu Wang, who contribute to the innovative projects at Snap Inc.
Conclusion
Meng Song's contributions to icon identification technology demonstrate his expertise and commitment to innovation. His patents reflect a deep understanding of machine learning and image processing, paving the way for future advancements in this field.