CV

Education

Ph.D in Johns Hopkins University, Baltimore, MD. 2021
M.E. in Stevens Institute of Technology, Hoboken, NJ. 2015
B.E. in The University of Electronic Science and Technology of China, Chengdu, PRC. 2013

Work experience

Fall 2021 - Present: Research Scientist
- Protagolabs Inc.
- Duties included:
  - Leading research projects targeting at popular challenges and high-profile conferences.
  - Implementing Cutting-edge NLP models from research in practical and scalable algorithms.
  - Serving as key member for developing advanced analytic solutions for products.
  - Monitoring junior team members on implementing and fine-tuning machine learning models
- Supervised by: Yu Cheng
Fall 2015 - Fall 2021: Research Assistant
- Fall 2018 - Fall 2021: Johns Hopkins University (transferred)
- Fall 2015 - Fall 2018: Rutgers, the State University of New Jersey
- Duties included:
  - Advised by Prof. Vishal Patel, I was learning and conducting machine learning/deep learning algorithm for biometric applications.
  - The main research topics (but not limited) could be categorized as visual-attribute guided face synthesis and heterogeneous face recognition by the generative models (GANs, VAE).
- Supervised by: Vishal M. Patel

Publications

Deep tattoo recognition

Xing Di, Vishal Patel, "Deep tattoo recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2016.

Deep learning for tattoo recognition

Xing Di, Vishal Patel, "Deep learning for tattoo recognition." Deep Learning for Biometrics, 2017.

Face synthesis from visual attributes via sketch using conditional vaes and gans

Xing Di, Vishal Patel, "Face synthesis from visual attributes via sketch using conditional vaes and gans." arXiv preprint arXiv:1801.00077, 2017.

Large margin multi-modal triplet metric learning

Xing Di, Vishal Patel, "Large margin multi-modal triplet metric learning." Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, 2017.

Gp-gan: Gender preserving gan for synthesizing faces from landmarks

Xing Di, Vishwanath Sindagi, Vishal Patel, "Gp-gan: Gender preserving gan for synthesizing faces from landmarks." Proceedings of the International Conference on Pattern Recognition, 2018.

Polarimetric thermal to visible face verification via attribute preserved synthesis

Xing Di, He Zhang, Vishal Patel, "Polarimetric thermal to visible face verification via attribute preserved synthesis." Proceedings of the IEEE International Conference on Biometrics Theory, Applications and Systems, 2018.

Facial synthesis from visual attributes via sketch using multiscale generators

Xing Di, Vishal Patel, "Facial synthesis from visual attributes via sketch using multiscale generators." IEEE Transactions on Biometrics, Behavior, and Identity Science, 2019.

Polarimetric thermal to visible face verification via self-attention guided synthesis

Xing Di, Benjamin Riggan, Shuowen Hu, Nathaniel Short, Vishal Patel, "Polarimetric thermal to visible face verification via self-attention guided synthesis." Proceedings of the International Conference on Biometrics, 2019.

A large-scale, time-synchronized visible and thermal face dataset

Domenick Poster, Matthew Thielke, Robert Nguyen, Srinivasan Rajaraman, Xing Di, Cedric Fondje, Vishal Patel, Nathaniel Short, Benjamin Riggan, Nasser Nasrabadi, Hu Shuowen, "A large-scale, time-synchronized visible and thermal face dataset." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021.

DeepStationing: thoracic lymph node station parsing in CT scans using anatomical context encoding and key organ auto-search

Dazhou Guo, Xianghua Ye, Jia Ge, Xing Di, Le Lu, Lingyun Huang, Guotong Xie, Jing Xiao, Zhongjie Lu, Ling Peng, Senxiang Yan, Dakai Jin, "DeepStationing: thoracic lymph node station parsing in CT scans using anatomical context encoding and key organ auto-search." Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, 2021.

Heterogeneous face frontalization via domain agnostic learning

Xing Di, Shuowen Hu, Vishal Patel, "Heterogeneous face frontalization via domain agnostic learning." Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, 2021.

Multi-scale thermal to visible face verification via attribute guided synthesis

Xing Di, Benjamin Riggan, Shuowen Hu, Nathaniel Short, Vishal Patel, "Multi-scale thermal to visible face verification via attribute guided synthesis." IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021.

Multimodal face synthesis from visual attributes

Xing Di, Vishal Patel, "Multimodal face synthesis from visual attributes." IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021.

Thermal-to-Visible Face Synthesis and Recognition

Xing Di, He Zhang, Vishal Patel, "Thermal-to-Visible Face Synthesis and Recognition." Deep Learning-Based Face Analytics, 2021.

Backdoor attacks on crowd counting

Yuhua Sun, Tailai Zhang, Xingjun Ma, Pan Zhou, Jian Lou, Zichuan Xu, Xing Di, Yu Cheng, Lichao Sun, "Backdoor attacks on crowd counting." Proceedings of the 30th ACM International Conference on Multimedia, 2022.

Memory-guided semantic learning network for temporal sentence grounding

Daizong Liu, Xiaoye Qu, Xing Di, Yu Cheng, Zichuan Xu, Pan Zhou, "Memory-guided semantic learning network for temporal sentence grounding." Proceedings of the AAAI Conference on Artificial Intelligence, 2022.

Unsupervised temporal video grounding with deep semantic clustering

Daizong Liu, Xiaoye Qu, Yinzhen Wang, Xing Di, Kai Zou, Yu Cheng, Zichuan Xu, Pan Zhou, "Unsupervised temporal video grounding with deep semantic clustering." Proceedings of the AAAI Conference on Artificial Intelligence, 2022.

Community Service:

Reviewer: CVPR, ICCV, ECCV, AAAI, WACV, ICPR, ICB, BTAS, ICIP, CIBM, PR, TIP, TIFS, SPL, TBIOM, TVCJ
PC member: AAAI 23, CVPR 23

Xing Di

CV