This inventor holds 1 USPTO granted patent and 2 published patent applications. Top assignee: Nvidia Corporation. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Innovations of Bingxin Hou in Object Detection Technology
Introduction
Bingxin Hou is an accomplished inventor based in Santa Clara, CA. He has made significant contributions to the field of object detection using deep learning techniques. His innovative work focuses on optimizing object detection models for real-time streaming applications.
Latest Patents
Bingxin Hou holds 1 patent for his invention titled "Object detection using deep learning for real-time streaming applications." This patent describes various techniques for optimizing object detection models. The systems and methods disclosed in the patent process sensor data using a backbone of machine learning models to generate feature maps at different resolutions. The machine learning models then generate a vector based on one or more of these feature maps. For instance, if the backbone generates four feature maps, the models may use two of them to create the vector. The processed vector is then utilized by a transformer within the machine learning models to produce data representing class labels for objects depicted in images and their locations within those images.
Career Highlights
Bingxin Hou is currently employed at Nvidia Corporation, a leading company in graphics processing and AI technology. His work at Nvidia has allowed him to push the boundaries of what is possible in real-time object detection.
Collaborations
Bingxin has collaborated with notable colleagues such as Parthasarathy Sriram and Dahjung Chung. Their combined expertise has contributed to advancements in the field of machine learning and object detection.
Conclusion
Bingxin Hou's innovative work in object detection technology exemplifies the potential of deep learning in real-time applications. His contributions continue to shape the future of this exciting field.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
