Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Utilizing a deep neural network-based model to identify visually similar digital images based on user-selected visual attributes

Utilizing a deep neural network-based model to identify visually similar digital images based on user-selected visual attributes

US Patent 10628708 · Granted Apr 21, 2020

Estimated economic value: $66,026,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Semantic image synthesis2025
Open vocabulary instance segmentation2025
Self-supervised visual-relationship probing2025
Performing multiple segmentation tasks2025
Object class inpainting in digital images utilizing class-specific inpainting ne2025
Object class inpainting in digital images utilizing class-specific inpainting ne2025
Image and object inpainting with diffusion models2025
Image and object inpainting with diffusion models2025
Multi-modal image editing2025
Power connector with increased plugging force and improved heat dissipation perf2025
Personalized text-to-image generation2025
Scene graph modification based on natural language commands2025