X
Xiang Li
Researcher at Temple University
Publications - 2124
Citations - 58896
Xiang Li is an academic researcher from Temple University. The author has contributed to research in topics: Medicine & Computer science. The author has an hindex of 97, co-authored 1472 publications receiving 42301 citations. Previous affiliations of Xiang Li include Stony Brook University & Dalian University of Technology.
Papers
More filters
Proceedings ArticleDOI
Selective Kernel Networks
TL;DR: SKNet as discussed by the authors proposes a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information, which can capture target objects with different scales.
Journal ArticleDOI
On the origin and continuing evolution of SARS-CoV-2
Xiaolu Tang,Changcheng Wu,Xiang Li,Yuhe Song,Yuhe Song,Xinmin Yao,Xinkai Wu,Yuange Duan,Hong Zhang,Yirong Wang,Zhaohui Qian,Jie Cui,Jian Lu +12 more
TL;DR: The results suggest that the development of new variations in functional sites in the receptor-binding domain (RBD) of the spike seen in SARS-CoV-2 and viruses from pangolin SARSr-CoVs are likely caused by natural selection besides recombination.
Posted Content
On the Convergence of FedAvg on Non-IID Data
TL;DR: This paper analyzes the convergence of Federated Averaging on non-iid data and establishes a convergence rate of $\mathcal{O}(\frac{1}{T})$ for strongly convex and smooth problems, where $T$ is the number of SGDs.
Posted Content
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wenhai Wang,Enze Xie,Xiang Li,Deng-Ping Fan,Kaitao Song,Ding Liang,Tong Lu,Ping Luo,Ling Shao +8 more
TL;DR: Huang et al. as discussed by the authors proposed Pyramid Vision Transformer (PVT), which is a simple backbone network useful for many dense prediction tasks without convolutions, and achieved state-of-the-art performance on the COCO dataset.
Journal ArticleDOI
Human dopamine transporter gene (DAT1) maps to chromosome 5p15.3 and displays a VNTR
David J. Vandenbergh,Antonio M. Persico,Anita L. Hawkins,Constance A. Griffin,Xiang Li,Ethylin Wang Jabs,George R. Uhl +6 more
TL;DR: Analysis of a 40-bp repeat in the 3' untranslated region of the message revealed variable numbers of the repeat ranging from 3 to 11 copies, which will aid in the investigation of a role for this gene in genetic disorders of the dopaminergic system in humans.