Huijuan Xu

PhD Candidate
Computer Science, Boston University
Email: hxu@bu.edu

CV

About Me

I am a PhD student in computer science department at Boston University, advised by Professor Kate Saenko.

My research focuses on deep learning, computer vision and natural language processing, particularly in the area of visual question answering, video language description and activity detection.

Before coming to US, I received the Master’s degree from Graduate University of Chinese Academy of Sciences in 2012, advised by Professor Hua Yu, and a Bachelor’s degree of computer science from Hefei University of Technology in 2009. I conducted my PhD study at the CS Department of UMass Lowell for three years, before transferring to the CS Department of Boston University to continue my PhD study with Professor Kate Seanko.

News


Publications

Google Scholar

Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering.

Huijun Xu, Kate Saenko.
In European Conference on Computer Vision (ECCV), 2016.
arXiv Code

Translating Videos to Natural Language Using Deep Recurrent Neural Networks.

Subhashini Venugopalan, Huijun Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, Kate Saenko.
NAACL 2015.
arXiv Project page





Workshop Papers

Huijuan Xu and Kate Saenko. Dual Attention Network for Visual Question Answering. ECCV2016 2nd Workshop on Storytelling with Images and Videos (VisStory), 2016.
Huijuan Xu and Kate Saenko. Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering. VQA Challenge Workshop at CVPR 2016.
Huijuan Xu, Subhashini Venugopalan, Vasili Ramanishka, Marcus Rohrbach and Kate Saenko. A Multi-scale Multiple Instance Video Description Network. ICCV15 workshop on Closing the Loop Between Vision and Language (CLVL), 2015. (Abstract)

Teaching

Teaching Assistant, UMass Lowell(Spring 2015)
91.422/545: Machine Learning

Lab Instructor, UMass Lowell (Fall 2013, Spring 2014)
91.103: Computing I Lab