X
Xiaoqiong Li
Researcher at Beijing Institute of Technology
Publications - 23
Citations - 435
Xiaoqiong Li is an academic researcher from Beijing Institute of Technology. The author has contributed to research in topics: Medicine & Chemistry. The author has an hindex of 6, co-authored 11 publications receiving 235 citations.
Papers
More filters
Proceedings ArticleDOI
SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications
TL;DR: SlimYOLOv3 as discussed by the authors proposes to learn efficient deep object detectors through channel pruning of convolutional layers, which enforce channel-level sparsity of CNNs by imposing L1 regularization on channel scaling factors and prune less informative feature channels to obtain "slim" object detectors.
Journal ArticleDOI
An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy
Sharib Ali,Felix Zhou,Barbara Braden,Adam A. Bailey,Suhui Yang,Guanju Cheng,Pengyi Zhang,Xiaoqiong Li,Maxime Kayser,Roger D. Soberanis-Mukul,Shadi Albarqouni,Xiaokang Wang,Chunqing Wang,Seiryo Watanabe,Ilkay Oksuz,Ilkay Oksuz,Qingtian Ning,Shufan Yang,Mohammad Azam Khan,Xiaohong W. Gao,Stefano Realdon,Maxim Loshchenov,Julia A. Schnabel,James E. East,Georges Wagnières,Victor B. Loschenov,Enrico Grisan,Enrico Grisan,Christian Daul,Walter Blondel,Jens Rittscher +30 more
TL;DR: A comprehensive analysis of the submissions to the first edition of the Endoscopy Artefact Detection challenge is presented, revealing the shortcomings of current training strategies and highlighting the need for developing new optimal metrics to accurately quantify the clinical applicability of methods.
Proceedings ArticleDOI
SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications
TL;DR: SlimYOLOv3 as mentioned in this paper proposes to learn efficient deep object detectors through channel pruning of convolutional layers, which enforce channel-level sparsity of CNNs by imposing L1 regularization on channel scaling factors and prune less informative feature channels to obtain "slim" object detectors.
Journal ArticleDOI
A system on chip-based real-time tracking system for amphibious spherical robots:
TL;DR: A real-time detection and tracking system adopting Gaussian background model and compressive tracking algorithm was designed and implemented, which could meet future demands of the amphibious spherical robot in biological monitoring and multi-target tracking.
Journal ArticleDOI
CoSinGAN: Learning COVID-19 Infection Segmentation from a Single Radiological Image
TL;DR: A novel conditional generative model, called CoSinGAN, which can be learned from a single radiological image with a given condition, i.e., the annotation mask of the lungs and infected regions is proposed, which has the potential to learn COVID-19 infection segmentation from few radiological images in the early stage of CO VID-19 pandemic.