This inventor holds 2 USPTO granted patents and 1 published patent application. Top assignee: Adobe, Inc.. Active years: 2023.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2023
Title: Xihui Liu: Innovator in Visual-Semantic Technologies
Introduction
Xihui Liu is a prominent inventor based in Hong Kong, CN. He has made significant contributions to the field of visual-semantic technologies, holding 2 patents that showcase his innovative approach to image searching and manipulation.
Latest Patents
One of Xihui Liu's latest patents is titled "Joint visual-semantic embedding and grounding via multi-task training for image searching." This invention involves a method for generating search results by processing devices that perform operations such as receiving a query with text input through a joint embedding model. The model is trained to generate image results by accessing a set of images and textual information, encoding them into feature vectors, and generating image-text pairs based on matches. The training also includes generating a visual grounding dataset and visual-semantic joint embeddings to produce an image result for display.
Another notable patent is "Semantic image manipulation using visual-semantic joint embeddings." This technology is directed towards a reinforcement learning-based framework that trains a natural media agent to learn a rendering policy without human supervision. The agent explores a canvas and minimizes a loss function to generate a series of graphic actions that reproduce or transform a reference image.
Career Highlights
Xihui Liu is currently employed at Adobe, Inc., where he continues to develop innovative solutions in the realm of visual-semantic technologies. His work at Adobe has positioned him as a key player in advancing the capabilities of image processing and manipulation.
Collaborations
Xihui Liu collaborates with talented individuals such as Quan Anh Tran and Handong Zhao, contributing to a dynamic team focused on pushing the boundaries of technology in their field.
Conclusion
Xihui Liu's contributions to visual-semantic technologies through his patents and work at Adobe, Inc. highlight his role as an influential inventor in the industry. His innovative approaches continue to shape the future of image searching and manipulation.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile