A keypoint‐based object detection method with wide dual‐path backbone network and attention modules
Abstract Keypoint‐based object detection is one of the most efficient and speedy methods at present, yet its performance is often worse than the anchor‐based method. Without prior settings in the keypoint‐based method, the huge search space of the keypoints results in the high recall but low precisi...
Main Authors: | Zhong Qu, Run Zhang, Kang‐hua Bao |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-06-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12152 |
Similar Items
-
No‐reference image quality assessment based on multiscale feature representation
by: Junhui Li, et al.
Published: (2021-11-01) -
Improve conditional adversarial domain adaptation using self‐training
by: Zi Wang, et al.
Published: (2021-08-01) -
Spatial attention model‐modulated bi‐directional long short‐term memory for unsupervised video summarisation
by: Rui Zhong, et al.
Published: (2021-03-01) -
Research on transformer fault diagnosis: Based on improved firefly algorithm optimized LPboost–classification and regression tree
by: Xiaoxing Zhang, et al.
Published: (2021-10-01) -
Stable feature selection based on brain storm optimisation for high‐dimensional data
by: Mengmeng Li, et al.
Published: (2022-01-01)