Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Joint visual-semantic embedding and grounding via multi-task training for image searching

Joint visual-semantic embedding and grounding via multi-task training for image searching

US Patent 11809822 · Granted Nov 7, 2023

Estimated economic value: $127,607,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Self-supervised visual-relationship probing2025
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
Systems and methods for predicting long-tail colors in images2025
Power connector with increased plugging force and improved heat dissipation perf2025
Personalized text-to-image generation2025
Scene graph modification based on natural language commands2025
Scene graph modification based on natural language commands2025
Recommending objects for image composition using geometry-and-lighting aware sea2025