Xitong Yang
yangxitongbob AT gmail DOT com

I am currently a third year Ph.D. student in CS at University of Maryland, College Park, under the supervision of Prof. Larry S. Davis. My research focuses on deep learning based video understanding, including video action recognition, detection and retrieval. I also work closely with Dr. Xiaodong Yang during my internship with NVIDIA Research.

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

/ / /


What's New


Selected Projects

game

STEP: Spatio-Temporal Progressive Learning for Video Action Detection
Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao, Larry Davis, Jan Kautz
Computer Vision and Pattern Recognition (CVPR), 2019 (Oral)

paper / bibtex
@InProceedings{Yang_2019_CVPR,
author = {Yang, Xitong and Yang, Xiaodong and Liu, Ming-Yu and Xiao, Fanyi and Davis, Larry S. and Kautz, Jan},
title = {STEP: Spatio-Temporal Progressive Learning for Video Action Detection},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
} 
            

game

Towards Perceptual Image Dehazing by Physics-based Disentanglement and Adversarial Training
Xitong Yang, Zheng Xu and Jiebo Luo.
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018

paper / bibtex
@inproceedings{yang2018towards,
title={Towards perceptual image dehazing by physics-based disentanglement and adversarial training},
author={Yang, Xitong and Xu, Zheng and Luo, Jiebo},
booktitle={Thirty-second AAAI conference on artificial intelligence},
year={2018}
}
            

game

Deep Multimodal Representation Learning from Temporal Data
Xitong Yang, Palghat Ramesh, Radha Chitta, Sriganesh Madhvanath, Edgar A. Bernal, Jiebo Luo
Computer Vision and Pattern Recognition (CVPR), 2017

paper / bibtex
@inproceedings{yang2017deep,
title={Deep multimodal representation learning from temporal data},
author={Yang, Xitong and Ramesh, Palghat and Chitta, Radha and Madhvanath, Sriganesh and Bernal, Edgar A and Luo, Jiebo},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={5447--5455},
year={2017}
}
            


Publications

  1. Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao, Larry Davis and Jan Kautz. "STEP: Spatio-Temporal Progressive Learning for Video Action Detection." IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral) [PDF]
  2. 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) [PDF]
  3. Zheng Xu, Xitong Yang, Xue Li, Xiaoshuai Sun, PR Harbin. "Strong baseline for single image dehazing with deep features and instance normalization." The British Machine Vision Conference (BMVC), 2018 [PDF]
  4. Ahmed Taha, Moustafa Meshry, Xitong Yang, Yi-Ting Chen and Larry Davis. "Two Stream Self-Supervised Learning for Action Recognition." IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2018 [PDF]
  5. Wei Qian, Wending Li, Yasuhiro Sogawa, Ryohei Fujimaki, Xitong Yang and Ji Liu. "An Interactive Greedy Approach to Group Sparsity in High Dimensions." Techonometrics, 2018 [link]
  6. 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]
  7. 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]
  8. 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]
  9. Xitong Yang, Yuncheng Li, Jiebo Luo, "Pinterest Board Recommendation for Twitter Users." Proceedings of the ACM International Conference on Multimedia (MM), ACM, 2015 (short paper) [PDF]
  10. 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]

Nice website template from Georgia Gkioxari and Jon Barron!