Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Self-supervised hierarchical motion learning for video action recognition

Self-supervised hierarchical motion learning for video action recognition

US Patent 11594006 · Granted Feb 28, 2023

Estimated economic value: $528,489,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

System and method for content and motion controlled action video generation2025
Visual property determinations using one or more neural networks2025
Context-aware synthesis and placement of object instances2025
Distance determinations using one or more neural networks2025
Weakly-supervised object detection using one or more neural networks2025
Segmentation using an unsupervised neural network training technique2025
Hallucinating details for over-exposed pixels in videos using learned reference 2025
Synthetic bracketing for exposure correction2025
Learning robotic tasks using one or more neural networks2025
Differentiable object insertion using hybrid lighting volumes for synthetic data2025
Measurement control method, terminal, and network-side device2025
Method and apparatus for obtaining key, user equipment, and network side device2025