Monthly Archives: December 2014

New Year Greetings

2014 is a fruitful year for MCLab and we are looking forward to a wonderful 2015.

Wish all members happy new year!


Image credit: Latin Times

By |December 28th, 2014|News|Comments Off on New Year Greetings|

Professor Kuo Completed His Service as APSIPA President

Professor C.-C. Jay Kuo attended 2015 APSIPA Annual Summit Conference (ASC) in Siem Reap, Cambodia, December 9-12. APSIPA represents “Asia Pacific Signal and Information Processing Association”, which was founded in 2009. Professor Sadaoki Furui was the first President (2009-2012) while Prof. Jay Kuo was the second (2012-2014). During his tenure, Professor Kuo launched a major membership campaign through recruiting APSIPA Friend Labs. Right now, APSIPA has around 3200 e-members in the LinkedIn Social Network and 260 APSIPA Friend Labs.

Professor Kosin Chamnongthai of King Mongkut’s University of Technology (Thailand), Professor Hitoshi Kiya of Tokyo Metropolitan University (Japan) and Professor Kuo were General Co-Chairs of APSIPA ASC 2014. The conference location, Siem Reap, is the home to the incredible Angkor ruins, a sprawling World Heritage-listed complex of ancient temples, including Angkor Wat, Angkor Thom, etc. Professor Kuo met a couple of MCL alumni from Korea and Taiwan.

Professor Kuo completed his two-year term of APSIPA President immediately after this conference, and Dr. Haizhou Li of Singapore has succeed Professor Kuo to become the new President of APSIPA. Dr. Li is a world renowned expert and technical leader in speech processing and recognition.

By |December 21st, 2014|News|Comments Off on Professor Kuo Completed His Service as APSIPA President|

MCLab at NIPS 2014

Neural Information Processing Systems (NIPS) conference, a premier machine learning conference, was held in the beautiful French city of Montreal, Canada from Dec. 8 to Dec. 13, 2014. This year’s conference was the 28th edition and it saw a record number of attendees (around 2400 registrations) from all over the world, with a good mixture of people from academia and industry. Applied machine learning practitioners from computer vision and neuroscience, and theorists from learning and information theory communities made the conference a great success.

Sanjay presented his paper titled `Studying User Influence in Personalized Group Recommenders in Location Based Social Networks’ at the NIPS Personalization Workshop. His work proposes a new class of Collaborative-filtering based Hierarchical Bayesian models to jointly learn group preferences and location-activities to perform personalization of group recommenders. Empirical experiments on a large location-based social network dataset showed that the models he proposed out-perform the state-of-the-art group recommendation systems. A photo of top machine learning researchers (photo credit: Prof. Andrew Ng) and a photo of Montreal City are shown.


By |December 15th, 2014|News|Comments Off on MCLab at NIPS 2014|

Congratulations to Hyunsuk Ko for Passing his Defense

Congratulations to Hyunsuk Ko, an MCL member, for passing his defense this afternoon. His thesis title is “Advanced Techniques for Stereoscopic image rectification and quality assessment”. His thesis guidance committee includes Jay Kuo (Chair), Sandy Sawchuk and Aiichiro Nakano (Outside Member). The committee gave a lot of praise to the quality of Hyunsuk’s thesis and his excellent presentation. The following is the abstract of Hyunsuk’s thesis.
“New frameworks for an objective quality evaluation and an image rectification of stereoscopic image pairs are presented in this work. First, quality assessment of stereoscopic image pairs is more complicated than that for 2D images since it is a multi-dimensional problem where the quality is affected by distortion types as well as the relation between the left and right views such as different types/levels of distortion in two views. In our work, we first introduce a novel formula-based metric that provide better results than several existing methods. However, the formula-based metric still has its limitation. For further improvement, we propose a parallel boosting system based quality index. That is, we classify distortion types into groups and design a set of scorer to handle them separately. At stage 1, each scorer generates its own score for a specific distortion type. At stage 2, all intermediate scores are fused to predict the final quality index with nonlinear regression. Experimental results demonstrate that the proposed quality index outperforms most of state-of-the art quality assessment methods by a significant margin over different databases. Secondly, a novel algorithm for uncalibrated stereo image-pair rectification under the constraint of geometric distortion, called USR-CGD, is presented in this work. Although it is straightforward to define a rectifying transformation (or homography) given the epipolar geometry, many existing [...]

By |December 6th, 2014|News|Comments Off on Congratulations to Hyunsuk Ko for Passing his Defense|

Thanksgiving Luncheon of MCLab

Last Thursday (Nov 27, 2014), Professor Kuo held a Thanksgiving luncheon for our MCL members at Ichiban Restaurant in El Monte. Around 35 people from our group including some family members and Professor Kuo’s family attended this great luncheon event at noon of Thanksgiving Day. There was a fusion of food such as Sushi, seafood, Chinese food, pizza and dessert, which was great for us since MCL has members from various regions. The most important thing was to have a social communication among our group. In this luncheon, everyone enjoyed talking to others and our topics were pretty diverse, ranging from research, course study, to sports, hobbies and Thanksgiving plans. Professor Kuo introduced his family to us and it was a great pleasure to receive warm Thanksgiving greetings from his family members. Besides, Professor Kuo went to each table to chat with group members, showing a touched concern about our life in the USA. Moreover, Professor Kuo’s sharing about his experience on research, PhD study, sociality, and life benefited us a lot on many aspects.

Two visiting scholars, Prof. Yang and Prof. Wang, mentioned this luncheon as “a valuable chance to understand the spirit of MCL group, to know the group members, and to learn more about Professor Kuo”. “My husband and I had no idea before about where to spend our Thanksgiving, but right now we find the answer is to have a good time with the big MCL family right here!”, as Dr. Nie told us. Yes! This is definitely correct. Most of our members are international students, whose families are quite far away. On this special moment, Thanksgiving Day, we just felt like we were a family right here, right now with [...]

By |December 1st, 2014|News|Comments Off on Thanksgiving Luncheon of MCLab|