Photo: Flying over the Chicago skyline on a Cessna 172.

Short Bio

I am a PhD Candidate in Computer Science at Purdue University fortunately under the supervision of Prof. Chris Clifton. My research interests lie in the intersection of computer vision, data privacy, and machine learning. Currently, I am working on formal (and practical) privacy definition for image and speech with the generous support from NSF. Outside of research, I enjoy flying and playing table tennis.

Contact

Email: contact@tao.li
Links: Google Scholar, GitHub, ResearchGate, DBLP, and PGP Key.
Follow @Tao_CS

Publications

Differentially Private Imaging via Latent Space Manipulation
Tao Li and Chris Clifton
In the 42nd IEEE Symposium on Security & Privacy (S&P), Poster, Virtual, May 2021.
[pdf] [abstract] [poster] [arxiv] [bib]

DeepBlur: A Simple and Effective Method for Natural Image Obfuscation
Tao Li and Min Soo Choi
arXiv preprint arXiv:2104.02655
[pdf] [arxiv] [bib]

Component Attention Guided Face Super-Resolution Network: CAGFace
Ratheesh Kalarot, Tao Li, and Fatih Porikli
In Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass village, Colorado, USA, March 2020.
[pdf] [poster] [slides] [arxiv] [bib]

Cooperative Adaptive Cruise Control for Connected Autonomous Vehicles by Factoring Communication-Related Constraints
Chaojie Wang, Siyuan Gong, Anye Zhou, Tao Li, and Srinivas Peeta
In Transportation Research Part C: Emerging Technologies, April 2020.
[pdf] [arxiv] [doi] [bib]

Music Sequence Prediction with Mixture Hidden Markov Models
Tao Li, Min Soo Choi, Kaiming Fu, and Lei Lin
In Proceedings of the 2019 IEEE International Conference on Big Data (BigData), Los Angeles, California, USA, December 2019.
[pdf] [arxiv] [doi] [bib]

Multiclass Information Flow Propagation Control under Vehicle-to-Vehicle Communication Environments
Jian Wang, Srinivas Peeta, Lili Lu, and Tao Li
In Transportation Research Part B: Methodological, November 2019.
[pdf] [arxiv] [doi] [bib]

AnonymousNet: Natural Face De-Identification with Measurable Privacy
Tao Li and Lei Lin
In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.
In CVPR-19 Workshop on Computer Vision: Challenges and Opportunities for Privacy and Security (CV-COPS 2019), Long Beach, California, USA, June 2019 (Oral Presentation).
[pdf] [poster] [slides] [arxiv] [bib]

Understanding Beauty via Deep Facial Features
Xudong Liu, Tao Li, Hao Peng, Iris Chuoying Ouyang, Taehwan Kim, and Ruizhe Wang
In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.
In CVPR-19 Workshop on Analysis and Modeling of Faces and Gestures (AMFG 2019), Long Beach, California, USA, June 2019 (Oral Presentation).
[pdf] [slides] [arxiv] [bib]

Beauty Learning and Counterfactual Inference
In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.
In CVPR-19 Workshop on Explainable AI, Long Beach, California, USA, June 2019.
[pdf] [arxiv] [bib]

Cooperative Adaptive Cruise Control for Connected Autonomous Vehicles by Factoring Communication-Related Constraints
Chaojie Wang, Siyuan Gong, Anye Zhou, Tao Li, and Srinivas Peeta
In Transportation Research Procedia, Volume 38, 2019
In the 23rd International Symposium on Transportation and Traffic Theory (ISTTT), Lausanne, Switzerland, July 2019 (Oral Presentation).
[pdf] [arxiv] [doi] [bib]

AutoMPC: Efficient Multi-Party Computation for Secure and Privacy-Preserving Cooperative Control of Connected Autonomous Vehicles
Tao Li, Lei Lin, and Siyuan Gong
In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI) Workshop on Artificial Intelligence Safety (SafeAI), Honolulu, Hawaii, USA, January 2019.
[pdf] [slides] [poster] [bib]

Mining Semantic Descriptions from Data for Beauty Understanding
Xudong Liu, Tao Li, Peng Hao, Iris Chuoying Ouyang, Taehwan Kim, and Ruizhe Wang
Accepted to the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, Hawaii, USA, January 2019.
[bib]

Semi-supervised Text Regression with Conditional Generative Adversarial Networks
Tao Li, Xudong Liu, and Shihan Su
In Proceedings of the 2018 IEEE International Conference on Big Data (BigData), Seattle, Washington, USA, December 2018.
[pdf] [arxiv] [doi] [bib]

IVAS: Facilitating Safe and Comfortable Driving with Intelligent Vehicle Audio Systems
Tao Li, Kantapon Kaewtip, Jianxiong Feng, and Lei Lin
In Proceedings of the 2018 IEEE International Conference on Big Data (BigData), Seattle, Washington, USA, December 2018.
[doi] [bib]

Opinion Mining at Scale: A Case Study of the First Self-driving Car Fatality
Tao Li, Min Soo Choi, Yuntao Guo, and Lei Lin
In Proceedings of the 2018 IEEE International Conference on Big Data (BigData), Seattle, Washington, USA, December 2018.
[pdf] [doi] [bib]

YouTube AV 50K: An Annotated Corpus for Comments in Autonomous Vehicles
Tao Li, Lei Lin, Min Soo Choi, Kaiming Fu, Siyuan Gong, and Jian Wang
In Proceedings of the 13th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), Pattaya, Thailand, November 2018.
[pdf] [arxiv] [doi] [bib]

Deep Learning-based Human-Driven Vehicle Trajectory Prediction and its Application for Platoon Control of Connected and Autonomous Vehicles
Lei Lin, Siyuan Gong, Tao Li, and Srinivas Peeta
In Autonomous Vehicles Symposium 2018 (AVS), San Francisco, California, USA, July 2018.
[pdf] [slides] [bib]

Cooperative Adaptive Cruise Control for a Platoon of Connected and Autonomous Vehicles Considering Dynamic Information Flow Topology
Siyuan Gong, Anye Zhou, Jian Wang, Tao Li, and Srinivas Peeta
arXiv preprint arXiv:1807.02224
[pdf] [arxiv] [bib]

Posters & Extended Abstracts

Causal Discovery from Electronic Medical Records
In CVPR-19 Workshop on Towards Causal, Explainable and Universal Medical Visual Diagnosis, Long Beach, California, USA, June 2019.

Poster: Natural Face De-Identification
In the 40th IEEE Symposium on Security and Privacy (S&P), San Francisco, California, USA, May 2019.
[pdf] [poster] [bib]

Byzantine-tolerant V2X Communication System
Tao Li and Lei Lin
Accepted to the 2018 INFORMS Annual Meeting Phoenix (INFORMS), Phoenix, Arizona, USA, November 2018.
[pdf] [bib]

Toward Robust and Efficient Training of Generative Adversarial Networks with Bayesian Approximation
Tao Li, Kaiming Fu, Min Soo Choi, Xudong Liu, and Ying Chen
In Approximation Theory and Machine Learning Conference (ATML), West Lafayette, Indiana, USA, September 2018.
[pdf] [bib]

Modeling Uncertainty in Vehicle Trajectory Prediction in a Mixed Connected and Autonomous Vehicle Environment using Deep Learning and Kernel Density Estimation
Accepted to the Fourth Annual Symposium on Transportation Informatics (TransInfo), Amherst, New York, USA, August 2018.
[pdf] [bib]

SoK: Single Image Super-Resolution
Technical Report, 2017.
[pdf] [bib]