Search Results for author:
Found 2 papers, 0 papers with code
OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection
By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results.
OSKDet: Towards Orientation-sensitive Keypoint Localization for Rotated Object Detection
Furthermore, we explore a new keypoint reorder algorithm and feature fusion module based on the angle distribution to eliminate the confusion of keypoint order.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
