Welcome! You’re the conter12th vistor here.

Last Update: June, 10th, 2020.


Hello! My name is Xide Xia ( pronounced as 'Hseede Hsiah'). I was named after Xide Xie, who is a famous Chinese physicist as well as the first woman president of a major comprehensive university in China.

I am a Ph.D. student in the Computer Science Department at Boston University. I am advised by Professor Brian Kulis. I work as a research assistant in the Image and Video Computing (IVC) lab. My academic interests broadly include image/video style transfer learning, attribute-based models, segmentation, and metric learning for retrieval.

Before BU, I was a ME student in Computational Science and Engineering at Harvard. During 2013 and 2016, I've been fortunate to work with Dr. Mohammed AlQuraishi and Professor Peter Soger at the Sorger Lab and the Laboratory of Systems Pharmacology at Harvard Medical School. Before coming to Harvard, I received my M.S. degree in Electrical Engineering at Brown University. During my undergraduate at Beijing Institute of Technology, I studied in Information and Electrical Engineering.

For more information, welcome to my previous webpage.
Xide Xia

What's New

  • Our work on Image Photorealistic Style Transfer “Joint Bilateral Learning for Fast Universal Photorealistic Style Transfer.” is accepted by ECCV 2020!
  • During Fall 2019 and Spring 2020, I am a student researcher at Google AI Research.
  • Our new paper: "Moment Matching for Multi-Source Domain Adaptation" is accepted by ICCV 2019! It is posted here.
  • In Summer 2019, I worked as a Research Intern at Google AI Research.
  • Our new paper: "Deep Metric Learning to Rank" is accepted by CVPR 2019! It is posted here.
  • We release the M3SDA dataset. It is by far the largest unsupervised domain adaptation (UDA) dataset with six distinct domains and approximately 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. You can find it here.
  • In Fall 2018, I am the Teaching Assistant for course EC500/CS591-K1 Deep Learning. My office hours are on Mon and Wed during 4:30-6:30 pm at the CS Lab.
  • In Summer 2018, I work as a SWE-PhD intern at Google.
  • From Fall 2017 to Spring 2018, I work as a research intern at Legendary Applied Analytics.
  • Our new paper: "W-Net: A Deep Model for Fully Unsupervised Image Segmentation" posted here.
  • I am very honored and thankful to have received the Dean’s Fellow Scholarship 2017!
  • In Fall 2016, I am the Teaching Assistant for course CS131 Combinatoric Structures.
  • I am very honored and thankful to have received the Harvard IACS Student Scholarship 2016!
  • Our new paper "Cost-Sensitive Batch Mode Active learning: Designing Astronomical Observation by Optimizing Telescope Time and Telescope Choice." has just been accepted by In Proceedings of SIAM Data Mining Conference (SDM) 2016. pdf.

  • Publications

    2020

    [P.7] Xide Xia, Tianfan Xue, Wei-sheng Lai, Zheng Sun, Abby Chang, Brian Kulis, Jiawen Chen. “Real-time Localized Photorealistic Video Style Transfer.” Under reviewing. pdf

    vst_teaser.png

    [P.6] Xide Xia, Meng Zhang, Tianfan Xue, Zheng Sun, Hui Fang, Brian Kulis, Jiawen Chen. “Joint Bilateral Learning for Fast Universal Photorealistic Style Transfer.” The European Conference on Computer Vision (ECCV) 2020. pdf

    cvpr_2020

    2019

    [P.5] Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo Wang. “Moment Matching for Multi-Source Domain Adaptation.” In Proc. IEEE International Conference on Computer Vision (ICCV) 2019, Oral.pdf

    iccv_2019

    [P.4] Kun He, Fatih Cakir, Xide Xia, Brian Kulis, Stan Sclaroff. “Deep Metric Learning to Rank.” In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019. pdf

    cvpr_2019

    2017

    [P.3] Xide Xia, Brian Kulis. “W-Net: A Deep Model for Fully Unsupervised Image Segmentation.” ArXiv tech report 1711.08506, November 2017. pdf

    wnet

    2016

    [P.2] Xide Xia, Finale Doshi-Velez, Pavlos Protopapas. “Cost-Sensitive Batch Mode Active learning: Designing Astronomical Observation by Optimizing Telescope Time and Telescope Choice.” In In Proceedings of SIAM Data Mining Conference (SDM). 2016. pdf pdf w/notes github

    sdm

    2015

    [P.1] AlQuraishi, Mohammed, Shengdong Tang, and Xide Xia. “An affinity-structure database of helix-turn-helix: DNA complexes with a universal coordinate system.” BMC bioinformatics 16.1 (2015): 1. pdfgithub Data

    dna

    Contact

    Xide Xia
    Email: xidexia@bu.edu
    Department of Computer Science
    Boston University
    111 Cummington Mall
    Boston, MA 02215
    USA