siyangli

The increasing demand for rendering smooth and plausible 3D motion is fueling the development of motion capture (mocap) systems. This new format of high quality 3D motion data has paved its way into animation movies, high-end computer games, biomechanics and robotics (see the accompanying photo from [1]). Diverse applications and the rapid development of mocap systems have resulted in a large corpus of data in recent years. Automatic classification of the mocap data is essential for various database management tasks such as segmentation, indexing and retrieval.

Mr. Harshad Kadu, a MCL PhD student, and Professor C.-C. Jay Kuo recently proposed a new framework to tackle the human mocap data classification problem using novel spatial/temporal feature representations, machine learning and decision fusion concepts. The proposed solution methods are tested on a wide variety of sequences from the CMU mocap database, and a correct classification rate of 99.6% is achieved, which is the state-of-the-art technique in the field. This work has been accepted for publication in the IEEE Trans. on Multimedia.

[1] http://www.noldus.com/innovationworks/content/automated-behavior-recognition-in-humans

In 2014 Fall semester, Wei-Chih Hung will become a new Ph.D. student in MCLab. He received his B.S. and M.S. degree, both in electrical engineering, from the National Taiwan University, Taipei, Taiwan in 2011 and 2013, respectively. He arrived at USC one week ago, and now we have an interview with him, talking about his background and his thoughts on USC and MCLab.

What were your first impression of USC and MCLab?
USC definitely has a wonderful campus view. The buildings are beautiful and consistent in style. There are trees and grass yards everywhere, and of course I notice the famous fountains in the campus. After the first look on the USC campus, I am so excited that I can pursue my degree in this wonderful place.
As for MCLab, my first impression is that it is really like a big family. People in here are really friendly and willing to help as well as share their own experience, either in academy and living. I have received lots of help since I decided to join MCLab, especially from Professor Kuo, Brian and Joe.

Could you briefly describe your previous research experience?
In the last 2 years of my B.S. program, I was interested in various areas, such as wireless communication, machine learning, video coding, and computer graphics. Since my M.S. program, my research topic mainly focuses on wireless video transmission. I have worked on two projects on wireless video transmission. Both of them tried to adaptively improve video quality over wireless channel with different channel quality. But one tries to improve video quality with video codec parameter selection, and the other proposed a cross-layer video decoding algorithm, exploiting the natural information redundancy with video sequence.

What is [...]