chuntinghuang

MCL Students Attended Google LA PhD Summit

The Google LA PhD Summit 2014 was held on February 14th at Google LA site. Jian Li, Hao Xu, Jia He and Xin Zhang from MCL attended the event. They were invited to several events from Google including a keynote talk “Music Understanding”, presentations about “Large-Scale Machine Learning”, “Language Understanding”, “Chrome Security” and “Vision + Quantum”. Besides, they had a good chance to talk with leading Google PhDs, and got the opportunities to meet with Google engineers and project managers.

 

During the information session, engineers from Google mainly introduced researching differences between academia and Google. Two key differences are about available resources and the motivation of the research. Firstly, Google has the most powerful computer center, which offers almost infinite computation resources. They can train very complicated models, adopt more training samples, and obtain results almost instantly with the help from Google. This is crucial for current computer vision research. Secondly, as of motivation, researchers have no pressure on the quantity of publication. Instead, the quality of the publication plays more important role when they publish papers. Additionally, Google has no limit on sharing the work to research community, but they prefer to share the practical work instead of theories only. Several research scientists pointed out that they fundamentally traded the community work to coding when they move from academia to Google.

 

Besides, they have learned more about the ongoing research work in Google. Hartwig Adam, who is the technical lead manager of the Visual Search team in LA office, shared his work there. His team is focusing on developing computer vision algorithms and a scalable computer vision application such as image and video searching, data mining. He also works for Google Goggles and Glass. They [...]

By |March 9th, 2014|News|Comments Off on MCL Students Attended Google LA PhD Summit|

Interview with Visiting Scholar Prof. Wen-Jiin Tsai

Prof. Wen-Jiin Tsai began her term as Visiting Scholar in Media Communications Lab since August 2013. She received Ph.D and B.S. degrees in Computer Science from National Chiao Tung University (NCTU). Since 2011, Prof. Wen-Jiin Tsai has been an Associate Professor in NCTU. She took the time to answer some questions about her research.

Could you share your research experience and interest with us?

Before joining NCTU, I have eight years working experience in the industry. I was a senior manager of software department in Zinwell Corporation, and I was in charge of software development for digital TV receivers, which include receiving satellite, cable and terrestrial signals. However, because of family issue, I decided to move to NCTU as an Assistant Professor in 2005, and I became an Associate Professor later in 2011. My research interests include video codec, video streaming, digital TV, and video analysis. In addition, I also teach Digital TV system design and some undergraduate courses in Computer Science department.

During your time as a visiting scholar in MCL, what has been the focus of your work?

Continued from my research field, my research topic here is “perceptual lossless HD/UHD video coding”, which is the same one with another visiting scholar, Dr. Kim. The objective of this project is to amplify the coding efficiency and perceptual quality during compression, so that viewers can receive best visual quality under fixed constraint.

Besides, a graduate student, Qin Huang, in MCL that worked with me in this project has caught my attention; he is responsible and hard-working; I am impressed by his attitude and dedication toward the task assigned to him. It is a great experience to work with such a high-quality student, and I am also amazed by [...]

By |March 3rd, 2014|News|Comments Off on Interview with Visiting Scholar Prof. Wen-Jiin Tsai|

Interview with Visiting Scholar Dr. Hui Yong Kim

Dr. Hui Yong Kim, a senior researcher of Broadcasting and Telecommunications Media Research Laboratory of Electronics and Telecommunications Research Institute (ETRI) and also a former adjunct professor at University of Science and Technology (UST) in Korea, visited Media Communication Lab since September 2013. He generously spent some of his short time with us to share his research.

Could you give us a brief introduction about your research experience?

I would like to start from my PhD research experience. I worked on visual surveillance project during my PhD years, and the project required object detection and segmentation from videos. By separating background and foreground, I compressed detected objects and background differently to increase quality of objects area. After graduation, I joined a start-up company because I wanted to get a whole picture of how the real devices are developed. There, I mainly developed H.264 real-time codec software for several video communication systems, such as IP video phone and other consumer products. Because I was a manager in multimedia team, I also needed to care other issues like middle-wares, communication protocols, audio codecs, graphical user interfaces, and even mechanical designs. After few years, I decided to move to ETRI to continue my research path. In ETRI, I participated and contributed to developments of several international standards, including MPEG Multimedia Application Formats and High Efficiency Video Coding (HEVC). During the process, I developed more than 70 patent algorithms.

Could you also talk about your research interest?

My research interests include video/image signal processing and compression for realistic video services, such as UHDTV and 3DTV. They are called as “realistic media”, which implies making things real to human. My research goal is how to maximize visual reality to the user efficiently under [...]

By |February 22nd, 2014|News|Comments Off on Interview with Visiting Scholar Dr. Hui Yong Kim|

Prof. Kuo visited TCL Research America

Prof. Kuo and Summer He visited the Multimedia Lab of TCL Research America in San Jose (http://www.tcl-america.com/Multimedia_Lab.html) on Feb. 10th, 2014. The manager of TCL Research America Dr. Haohong Wang hosted the visiting. He introduced to Prof. Kuo the lab, and the research projects and products what there researchers are working on. The current foci of the lab include:

• Video capturing and pre-processing
• Audio and video coding
• Intelligent media analysis
• Video post-processing
• Networked media processing
• QoE based multimedia communications
• 3D graphics rendering
• Stereo and multi-view 3D content creation and processing
• 3DTV technology
• Multimedia applications and services
• Mobile multimedia
• Telepresence and IPTV services
• Universal media access

After that, Prof. Kuo gave a talk on “Recent developments in Visual Saliency Detection and Salient object Segmentation”. The researchers in TCL Research showed their great interests on this topic. They were impressed by the research technology and its high performance. They discussed with Prof. Kuo for details, and further potential applications.

By |February 11th, 2014|News|Comments Off on Prof. Kuo visited TCL Research America|
  • Permalink Gallery

    Congratulatons!! The Golden Eyes Contest Result Has Come Out

Congratulatons!! The Golden Eyes Contest Result Has Come Out

The result of Golden Eye Test has come out shortly after the subjective tests for MCL-3D and MCL-V database finished, and six students won their awards according to their accurate observations on 3D images and video clips, respectively.
MCL-3D database has 9 image sets, each set has 77 images. In addition, there are 12 video sets in MCL-V database, and each set contains 9 video clips. Since we have collected 30 opinions scores for each set, there are 20790 opinion scores for MCL-3D database and 3600 for MCL-V database in total. Both databases will be released to public in short term.
For our future research, we will develop a stereoscopic image quality assessment algorithm on MCL-3D database for Samsung and an effective video quality assessment metric on MCL-V database for Netflix.

By |December 24th, 2013|News|Comments Off on Congratulatons!! The Golden Eyes Contest Result Has Come Out|

Facial Recognition in Heterogeneous Environment

Author: Chun-Ting Huang and C.-C. Jay Kuo

“Facial Recognition” has become an important technique to handle the tremendous growing need for identification and verification since last century. The replacement of traditional transaction by electronic transaction successfully gathered attention for facial recognition from research and business communities, because facial recognition requires no physical interaction on behalf of users. The research on facial recognition can be traced back to early 1990s, from the Eigenface proposed by Turk and Pentland in 1991 [1], which has over 11409 citations on Google Scholar. The follow-up development can be concluded into general directions discussed in Face Recognition Vendor Test – FRVT 2002 [2], and different face databases are developed in order to solve various conditions, such as poses, expressions, and environment. A new database called Long Distance Heterogeneous Face Database (LDHF-DB) [3] is focused on face images under various distances and near-infrared camera, which provides an new challenge within this field.

Since under the long distance, the near-infrared camera can only capture blurred and vague face images, as shown in Fig. 1, causing the template feature’s low performance on LDHF-DB. Therefore, our research only adopts geometric and shape-based features, locally and globally, to determine the input of structured-fusion method. Based on the different characteristics of features we collected from database, we aim to develop an robust classification algorithm with machine learning to distinguish faces under various quality.

The major difference between our work and other research is the feature selection and structured fusion model. I have explained the reason why template method only has a fair performance under the influence of heterogeneous environment. Our proposed model can boost up the recognition rate by adopting different feature’s strength and discarding the outliers for particular [...]

By |November 21st, 2013|Biometrics|Comments Off on Facial Recognition in Heterogeneous Environment|