Li Ding | 丁立


I'm currently at MIT, working on deep learning for perception and control of autonomous vehicles. Our focus lies on Human-Centered Artificial Intelligence (HCAI) that leverages human knowledge to enhance machine intelligence.

I will be TAing MIT 6.S094: Deep Learning for Self-driving Cars and MIT 6.S099: Artificial General Intelligence in Jan. & Feb. 2018. If you have questions regarding the course, please email us through deepcars [at] mit.edu for 6.S094 or agi [at] mit.edu for 6.S099.

Prior to joining MIT, I worked on deep learning for human action recognition at University of Rochester (Department of Computer Science).

I'm from Shanghai, China. On a side of fun, I'm a casual Kaggler interested in playing with various kinds of data. I like photography, electro-funk, all kinds of cuisine, and at the moment, walking and traveling around with Pokémon Go.

Github | LinkedIn | Kaggle
liding [at] mit.edu


Research
Ongoing

Neural Synthesis

Driving Scene Perception

Motion Estimation and Optical Flow

Edge Cases in Image Recognition


Past

Weakly Supervised Action Localization

Fine-grained Image Classification


Publications

MIT Autonomous Vehicle Technology Study: Large-Scale Deep Learning Based Analysis of Driver Behavior and Interaction with Automation
Lex Fridman, Daniel E. Brown, Michael Glazer, William Angell, Spencer Dodd, Benedikt Jenik, Jack Terwilliger, Julia Kindelsberger, Li Ding, Sean Seaman, Hillary Abraham, Alea Mehler, Andrew Sipperley, Anthony Pettinato, Bobbie Seppelt, Linda Angell, Bruce Mehler, Bryan Reimer
[arXiv preprint] [arXiv:1711.06976]

TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation
Li Ding, Chenliang Xu
[arXiv preprint] [arXiv:1705.07818]


Kaggle

Competitions Expert | Current Rank 1242/75701 (Top 2%)

Satellite Iceberg Detection ( Top 6%)

Lung Cancer Detection ( Top 6%)