Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Training a deep neural network model to generate rich object-centric embeddings of robotic vision data

Training a deep neural network model to generate rich object-centric embeddings of robotic vision data

US Patent 11887363 · Granted Jan 30, 2024

Estimated economic value: $69,147,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Mitigating reality gap through training a simulation-to-real model using a visio2025
Class agnostic repetition counting in video(s) utilizing a temporal self-similar2025
Training instance segmentation neural networks through contrastive learning2025
Method and system of providing metaverse digital asset based on retailer desired2025
Microfluidic pixel driving circuit, microfluidic substrate, and microfluidic chi2025
Unsupervised depth prediction neural networks2025
Optimizing policy controllers for robotic agents using image embeddings2025
Optimizing policy controllers for robotic agents using image embeddings2025
Driving circuit, driving method and microfluidic substrate2025
System(s) and method(s) of using imitation learning in training and refining rob2025
System(s) and method(s) of using imitation learning in training and refining rob2025
Gene sequencing structure, gene sequencing device and gene sequencing method2025