About Me

I am currently a first year Ph.D. student at Department of Computer Science at University of Maryland, College Park. I am now working on interesting computer vision projects under the supervision of Prof. Larry S. Davis.

Before that, I received my Master's degree in Computer Science from Univeristy of Rochester. I worked on vision-based social media data mining projects with Prof. Jiebo Luo and spent two wonderful years there as a member of VIStA research group. I've also been lucky to work with Dr. Sriganesh Madhvanath and Dr. Raja Bala as a research intern at PARC East. I got my B.E degree from School of Information and Eletronics, Beijing Institute of Technology in China in 2014.

I'm interested in research topics related to computer vision, deep learning and machine learning, with the emphasis on following applications:

  • Computer Vision & Deep Learning: video understanding, multimodal data fusion, anomaly detection
  • Unsupervised Learning: temporal / disentangled representation learning, GANs
  • Data Mining: social media data mining
  • More information can be found in my CV.

    What's New

  • [Nov. 2017] Our paper "Towards Perceptual Image Dehazing by Physics-based Disentanglement and Adversarial Training" is accepted by AAAI 2018!
  • [Aug. 2017] A new blog about implementing GANs in Tensorflow / Pytorch is posted.
  • [Aug. 2017] One paper is accepted by IEEE Transactions on Multimedia!
  • [Aug. 2017] A new blog series is launched! I'll share some interesting papers I've read per week.
  • [Jun. 2017] Start my summer internship at Honda Research Institute! My mentors are Dr. Yi-Ting Chen and Dr. Teruhisa Misu.
  • [Apr. 2017] A new blog "Understanding Variational Lower Bound" was posted! A PDF version can be found HERE.
  • [Feb. 2017] Our paper "Deep Multimodal Representation Learning from Temporal Data" is accepted by CVPR 2017!
  • [Nov. 2016] Our paper "Tracking Illicit Drug Dealing and Abuse on Instagram using Multimodal Analysis" is accepted by ACM Transactions on Intelligent Systems and Technology (TIST) !
  • Publication

    1. Xitong Yang, Zheng Xu and Jiebo Luo. "Towards Perceptual Image Dehazing by Physics-based Disentanglement and Adversarial Training." The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)
    2. Bernal A. Edgar , Xitong Yang, Qun Li, Jayant Kumar, Sriganesh Madhvanath, Palghat Ramesh, and Raja Bala. "Deep Temporal Multimodal Fusion for Medical Procedure Monitoring using Wearable Sensors." IEEE Transactions on Multimedia (2017). [Link]
    3. Xitong Yang, Palghat Ramesh, Radha Chitta, Sriganesh Madhvanath, Edgar A. Bernal, Jiebo Luo, "Deep Multimodal Representation Learning from Temporal Data." IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [PDF]
    4. Xitong Yang, Jiebo Luo, "Tracking Illicit Drug Dealing and Abuse on Instagram using Multimodal Analysis." ACM Transactions on Intelligent Systems and Technology (TIST), Volume 8 Issue 4, February 2017. [Link]
    5. Xitong Yang, Yuncheng Li, Jiebo Luo, "Pinterest Board Recommendation for Twitter Users." Proceedings of the ACM International Conference on Multimedia (MM), ACM, 2015. [PDF]
    6. Yuncheng Li, Xitong Yang, and Jiebo Luo. "Semantic Video Entity Linking based on Visual Content and Metadata." International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015. [PDF]