US Patent Issued to QUALCOMM Technologies on Jan. 13 for "Object detection using visual language models via latent feature adaptation with synthetic data" (Dutch Inventors)

ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,525,008, issued on Jan. 13, was assigned to QUALCOMM Technologies Inc. (San Diego).

"Object detection using visual language models via latent feature adaptation with synthetic data" was invented by Michael Dorkenwald (Amsterdam) and Yuki Asano (Amsterdam).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and techniques are described herein for adapting a pretrained machine learning model. For instance, a process can include encoding a training image into a first feature vector, the training image including a first object located at a first location; generating a second feature vector based on a set of sinusoidal functions using a set of weights; com...