Xide Xia - Facebook AI

Welcome! You’re the conter12th vistor here.

Last Update: December, 4th, 2020.

Hello! My name is Xide Xia ( pronounced as 'Hsi-teh 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 research scientist at Facebook AI. My research interests broadly include multi-modal multi-task learning, retrieval task, style transfer learning, and attribute-based models.

I earned my Ph.D. degree from the Computer Science Department at Boston University, advised by Professor Brian Kulis. During my PhD, I have spent two summers full-time interning at Google. I was also a part-time student researcher at Google Research and Legendary Research.

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.

Xide Xia

What's New

  • I have graduated with my Ph.D. degree from BU. I will join Facebook AI in December 2020.
  • Our new paper “Real-time Localized Photorealistic Video Style Transfer.” is accepted to WACV 2021!
  • Our new paper “Learning to Approximate a Bregman Divergence.” is accepted to NeurIPS 2020!
  • Our new paper “Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer.” is accepted to ECCV 2020!
  • During Fall 2019 and Spring 2020, I am a student researcher at Google Research.
  • Our new paper: "Moment Matching for Multi-Source Domain Adaptation" is accepted to ICCV 2019! It is posted here.
  • In Summer 2019, I worked as a Research Intern at Google Research.
  • Our new paper: "Deep Metric Learning to Rank" is accepted to CVPR 2019! It is posted here.

    • Publications

    2021

    [P.8] Xide Xia, Tianfan Xue, Wei-sheng Lai, Zheng Sun, Abby Chang, Brian Kulis, Jiawen Chen. “Real-time Localized Photorealistic Video Style Transfer.” Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021. pdf

    vst_teaser.png

    2020

    [P.7] Ali Siahkamari, Xide Xia, Venkatesh Saligrama, David Castañón, Brian Kulis. “Learning to Approximate a Bregman Divergence.” Advances in Neural Information Processing Systems (NeurIPS), 2020.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 [AT] gmail [dot] com