Welcome to Kang Wang's Homepage

About me

I graduated from the Department of Electrical, Computer, and System Engineering (ECSE), Rensselaer Polytechnic Institute (RPI) on April 2019.

Previously, I worked at Intelligent System Lab (ISL) as a research assistant with Professor Qiang Ji. My research focus is mainly on computer vision and machine learning, especially on human attention modeling, developing robust, accurate and low-cost eye gaze tracking systems (see demos from ISL), and applying vision algorithms for natural human-computer interactions and human-robot interactions.

I received my Bachelor's degree from the Department of Electronic Engineering and Information Science, University of Science and Technology of China (USTC) in 2013.

Publications

	Kang Wang, Hui Su and Qiang Ji. Neural-inspired Eye Tracking with Eye Movement Dynamics IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [pdf]
	Kang Wang, Rui Zhao, Hui Su and Qiang Ji. Generalizing Eye Tracking with Bayesian Adversarial Learning IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [pdf]
	Kang Wang, Rui Zhao and Qiang Ji. A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [pdf]
	Kang Wang , Yue Wu and Qiang Ji. Head Pose Estimation on Low-Quality Images. IEEE International Conference on Automatic Face & Gesture Recognition (FG), 2018. [pdf]
	Rui Zhao, Kang Wang , Rahul Divekar, Robert Rouhani, Hui Su and Qiang Ji. An Immersive System with Multi-modal Human-computer Interaction. IEEE International Conference on Automatic Face & Gesture Recognition (FG), 2018. [pdf]
	Kang Wang and Qiang Ji. 3D Gaze Estimation without Explicit Personal Calibration. Pattern Recognition, 2018. [pdf]
	Kang Wang and Qiang Ji. Real Time Eye Gaze Tracking with 3D Deformable Eye-Face Model. IEEE International Conference on Computer Vision (ICCV), 2017. [pdf]
	Chao Gou, Yue Wu, Kang Wang, Kunfeng Wang, Fei-Yue Wang and Qiang Ji. A Joint Cascaded Framework for Simultaneous Eye Detection and Eye State Estimation. Pattern Recognition, 2017. [pdf]
	Kang Wang, Shen Wang, and Qiang Ji. Deep Eye Fixation Map Learning for Calibration-Free Eye Gaze Tracking (Oral). Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications (ETRA), 2016. [pdf]
	Kang Wang and Qiang Ji. Hybrid Model and Appearance based Eye Tracking with Kinect. Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications (ETRA), 2016. [pdf]
	Kang Wang and Qiang Ji. Real Time Eye Gaze Tracking with Kinect. International Conference on Pattern Recognition (ICPR), 2016. [pdf]
	Chao Gou, Yue Wu, Kang Wang, Feiyue Wang and Qiang Ji. Learning-By-Synthesis for Accurate Eye Detection. International Conference on Pattern Recognition (ICPR), 2016. [pdf]
	Kang Wang, Tam V Nguyen, Jiashi Feng, Jose Sepulveda. Sense Beyond Expressions: Cuteness. Proceedings of the 23rd ACM international conference on Multimedia (ACM-MM), 2015. [pdf]
	Annan Li, Luoqi Liu, Kang Wang, Si Liu and Shuicheng Yan. Clothing Attributes Assisted Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2014. [pdf]

Projects

Real time eye gaze tracking with a simple web camera. With the proposed deformable eye-face model, 3D gaze direction can be estimated effectively by detecting rigid facial landmarks and the pupil center. The system runs at 25 fps and can handle large head movement.

User controls the cursor through both head movement and eye movement. Head movement determines the rough position of cursor, while eye movement controls the fine-grained cursor movement. Best suitable for long-range or large-display related applications.

Facial behavior mirroring of Zeno R25, an expressive humanoid robot from Robokind. Zeno can understand the facial motion/expression of the user through a camera and tries to mimic the same movement. The system is part of the Robot exhibition event at London Science Museum.

Contact me

kangwang.kw@gmail.com