Ching Lik Teo
I am a PhD student at Department of Computer Science at University of Maryland, College Park . I am also affliated to the Computer Vision Lab at UMIACS. My advisors are Yiannis Aloimonos and Cornelia Fermüller.
I am interested in Computer Vision, Computational Linguistics and how these two emerging fields combine to solve difficult problems that models human understanding, attention and recognition. I am also interested in robotic perception, especially on how we can model Vision and Linguistics on mobile active agents.
I am a recipient of the Qualcomm Innovation Fellowship 2011, the UMD CS Department Fellowship award and DSO National Laboratories Post-graduate Scholarship.
Here's my updated CV.
Latest News
- We are one of the 8 teams nationwide to have received the Qualcomm Innovation Fellowship 2011, mentored by Qualcomm's Ashwin Sampath and Snehesh Shrestha. Our proposal Robots Need Language: A computational model for the integration of vision, language and action is supported by Prof. Yiannis Aloimonos and Prof. Hal Daumé III.
- Our group will be involved in the 2011 Telluride Neuromorphic Cognition Engineering Workshop.
- Our group will be taking part in the Robotic Perception Challenge at ICRA 2011.
- Participated at the 2010 CLSP-JHU Summer Workshop.
Current Research
We are developing a novel framework under the EU sponsored project POETICON++ that uses a Language to recognize common everyday actions and implementing it on the iCub, a humanoid robot. Key to this framework is the idea of a "Cognitive Dialog" between visual and linguistic processes. I am currently developing novel techniques that formalizes this process, integrating language at various levels of abstraction in the visual processing.
Software and data
Several datasets that we have used in our work are listed and made available here.- POETICON video dataset consisting of 6 complex activities involving 2 persons. Fully annotated, and hand segmented.
- UMD-Telluride Kinect Dataset consisting of RGB-Depth Kinect data of 10 kitchen actions using different tools.
- UMD Sushi-Making dataset consisting of synced RGB + MOCAP data of 4 actors performing various actions connected with making sushi.
We are actively using the Robot Operating System (ROS) to develop codes for the Videre Erratic robot platform. See our ROS hints to get acquainted. It contains useful README, links and sample ROS codes as well.
Refereed Publications
Ching L. Teo, Yezhou Yang, Hal Daumé III, Cornelia Fermüller, Yiannis Aloimonos. Towards a Watson That Sees: Language-Guided Action Recognition for Robots. IEEE International Conference on Robotics and Automation, ICRA. 2012. pdf slides dataset supplementary results
Ching L. Teo, Yezhou Yang, Cornelia Fermüller, Yiannis Aloimonos. Synergistic Methods for using Language in Robotics. Performance Metrics for Intelligent Systems Workshop, PerMIS. 2012. pdf slides dataset
Xiaodong Yu, Cornelia Fermüller, Ching L. Teo, Yezhou Yang, Yiannis Aloimonos. Active Scene Recognition with Vision and Language. International Conference on Computer Vision, ICCV. 2011. pdf
Ching L. Teo, Yezhou Yang, Hal Daumé III and Yiannis Aloimonos. Corpus-Guided Sentence Generation of Natural Images. Conference on Empirical Methods in Natural Language Processing, EMNLP. 2011. pdf slides results
Ching L. Teo, Yezhou Yang, Hal Daumé III, Cornelia Fermüller and Yiannis Aloimonos . A Corpus-Guided Framework for Robotic Visual Perception. AAAI Workshop on Language-Action Tools for Cognitive Artificial Agents. 2011. pdf slides dataset
Ching L. Teo, S. Li, L-F. Cheong and J. Sun. 3D ordinal constraints in Spatial Configuration for Robust Scene Recognition. 19th International Conference on Pattern Recognition. 2008. IEEE Xplore
Current Courses and Teaching
Spring 2012
- CMSC 828L: Link Mining by Lise Getoor
- BMGT 833: Operations Reasearch -- Integer Programming by Michael Ball
Last Updated: Apr 7, 2012