X
Xiaohui Xie
Researcher at University of California, Irvine
Publications - 351
Citations - 34195
Xiaohui Xie is an academic researcher from University of California, Irvine. The author has contributed to research in topics: Medicine & Computer science. The author has an hindex of 58, co-authored 220 publications receiving 29844 citations. Previous affiliations of Xiaohui Xie include University of California, Berkeley & National Chiao Tung University.
Papers
More filters
Journal ArticleDOI
The Site-Frequency Spectrum of Linked Sites
TL;DR: The results presented here can be used to extend the Poisson random field to allow for estimating selection for correlated sites and the Green’s function construction should be able to aid in studying the genetic drift of multiple alleles in other cases.
Posted Content
Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering
TL;DR: This paper explores mechanisms of incorporating part-ofspeech tag guided attention, convolutional n-grams, triplet attention interactions between the image, question and candidate answer, and structured learning for triplets based on image-question pairs and achieves the state-of-the-art performance.
Journal ArticleDOI
Inference of the Xenopus tropicalis embryonic regulatory network and spatial gene expression patterns
TL;DR: A novel method to elucidate gene regulatory circuits from these aggregate measurements in embryos of the frog Xenopus tropicalis is proposed using gene network inference algorithms and the ability of the inferred networks to predict spatial gene expression patterns is tested.
Proceedings Article
TAGAN: Tonality-alignment generative adversarial networks for realistic hand pose synthesis
TL;DR: This work adopts an augmented reality simulator to synthesize hand poses with accurate 3D hand-keypoint annotations and develops tonality-alignment generative adversarial networks (TAGAN), which align the tonality and color distributions between synthetic hand poses and real backgrounds, and can generate high-quality hand poses.
Posted ContentDOI
Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
TL;DR: Experimental results on the INbreast dataset demonstrate the robustness of proposed deep networks compared to previous work using segmentation and detection annotations in the training.