Výsledky vyhledávání - "Zeng, Qinghua"

Report

Semi-Aerodynamic Model Aided Invariant Kalman Filtering for UAV Full-State Estimation

Autor: Ye, Xiaoyu, Song, Fujun, Zhang, Zongyu, Zhang, Rui, Zeng, Qinghua

Due to the state trajectory-independent features of invariant Kalman filtering (InEKF), it has attracted widespread attention in the research community for its significantly improved state estimation accuracy and convergence under disturbance. In thi

Externí odkaz: http://arxiv.org/abs/2310.01844

Zobrazit plný text záznamu

Report

Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning

Autor: Yuan, Xiang, Cheng, Gong, Yan, Kebing, Zeng, Qinghua, Han, Junwei

Publikováno v: Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 6317-6327

The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object regions leads

Externí odkaz: http://arxiv.org/abs/2308.09534

Zobrazit plný text záznamu

Report

Towards Large-Scale Small Object Detection: Survey and Benchmarks

Autor: Cheng, Gong, Yuan, Xiang, Yao, Xiwen, Yan, Kebing, Zeng, Qinghua, Xie, Xingxing, Han, Junwei

Publikováno v: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 11, pp. 13467-13488, 1 Nov. 2023

With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the unsatisfactory situation of Small Object Detection (SOD), one of the notoriously ch

Externí odkaz: http://arxiv.org/abs/2207.14096

Zobrazit plný text záznamu