Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Multi-task learning for real-time semantic and/or depth aware instance segmentation and/or three-dimensional object bounding

Multi-task learning for real-time semantic and/or depth aware instance segmentation and/or three-dimensional object bounding

US Patent 10984290 · Granted Apr 20, 2021

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Emergency vehicle detection and response2025
Trajectory prediction using efficient attention neural networks2025
Three-dimensional point clouds based on images and depth data2025
Adjusting vehicle models based on environmental conditions2025
Adjusting vehicle models based on environmental conditions2025
Vision based object representation2025
Tracking objects using sensor data segmentations and/or representations2025
Parallel vehicle model processing2025
Parallel vehicle model processing2025
Multi-frame temporal aggregation and dense motion estimation for autonomous vehi2025
In-path obstacle detection and avoidance system2025
Pedestrian attribute and gesture detection2025