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
Proceedings ArticleDOI
Attentionanatomy: A Unified Framework for Whole-Body Organs at Risk Segmentation Using Multiple Partially Annotated Datasets
TL;DR: This paper's proposed end-to-end convolutional neural network model, called AttentionAnatomy, can be jointly trained with three partially annotated datasets, segmenting OARs from whole body, and presented significant improvements in both Sørensen-Dice coefficient (DSC) and 95% Hausdorff distance compared to the baseline model.
Proceedings ArticleDOI
Axiomatically Regularized Pre-training for Ad hoc Search
Jia Chen,Yiqun Liu,Yan Fang,Jiaxin Mao,Hui Fang,Shenghao Yang,Xiaohui Xie,Jinghui Zhang,Shaoping Ma +8 more
TL;DR: This work provides insights into improving the interpretability of pre-trained models and the guidance of incorporating IR axioms or human heuristics into pre-training methods.
Proceedings ArticleDOI
Preference-based Evaluation Metrics for Web Image Search
TL;DR: A thorough comparison of variants of preference judgments for web image search finds that compared to strict preference judgments, weak preference judgments require less time and have better inter-assessor agreement.
Journal ArticleDOI
SAILER: scalable and accurate invariant representation learning for single-cell ATAC-seq processing and integration.
TL;DR: SAILER as mentioned in this paper adopts the conventional encoder-decoder framework to learn the latent representation but imposes additional constraints to ensure the independence of the learned representations from the confounding factors.
Posted ContentDOI
DNA writing at a single genomic site enables lineage tracing and analog recording in mammalian cells
Theresa B Loveless,Joseph H. Grotts,Mason W. Schechter,Elmira Forouzmand,Courtney K. Carlson,Bijan S. Agahi,Guohao Liang,Michelle Ficht,Bin Liu,Xiaohui Xie,Chang C. Liu +10 more
TL;DR: CHYRON represents a conceptual advance in DNA recording technologies where writing rather than erasing becomes the primary mode of information accumulation, and should lead to single-cell-resolution recording of lineage and other information through long periods of time in complex animals or tumors, advancing the pursuit of a full picture of mammalian development.