Search Results for author:
Found 3 papers, 1 papers with code
YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss
All experiments and results reported in this paper are without any test time augmentation, unlike traditional approaches that use flip-test and multi-scale testing to boost performance.
Ranked #30 on
Pose Estimation
on COCO test-dev
(AP50 metric)
SS3D: Single Shot 3D Object Detector
Achieving the accuracy of two stage detectors using a single stage approach is important as single stage approaches are simpler to implement in embedded, real-time applications.
Efficient Semantic Segmentation using Gradual Grouping
We study the effectiveness of these techniques on a real-time semantic segmentation architecture like ERFNet for improving run time by over 5X.
