News

Welcome MCL New Member Ganning Zhao

Could you briefly introduce yourself and your research interests?

My name is Ganning Zhao. I was born in Weifang, China. This is my first semester here in USC, pursuing master’s degree on Electrical Engineering. I graduated from Guangdong University of Technology, majoring in automation. In my undergraduate, I did a project about audio signal processing using convolutional neural network with my friends and I became interested in signal processing and machine learning since then. My current research interest is image processing and computer vision.

What is your impression about MCL and USC?

I like the campus of USC, because the buildings are beautiful. Particularly, there are many libraries in USC and many of them are exquisite. People in MCL are intelligent and work very hard. I’m also impressed that they are very nice and always willing to help with each other. Professor Kuo is also very nice and caring about everyone in lab. I like the atmosphere here in MCL.

What is your future expectation and plan in MCL?

My research topic in this summer is texture synthesis. I hope I can do a good job in this topic. More importantly, because everyone in MCL are intelligent, I hope I can learn a lot from them during communication and improve my research ability. Also, I want to make more friends here in MCL.

By |June 28th, 2020|News|Comments Off on Welcome MCL New Member Ganning Zhao|

Welcome MCL New Member Jiamian Wang

Could you briefly introduce yourself and your research interests?

I’m Jiamian Wang, a graduate student of USC Ming Hsieh Department of Electrical and Computer Engineering. I got my bachelor’s degree at Tianjin University, China. My research interests are computer vision and image processing. I participated in the projects of doing image semantic segmentation, doing outlier-detection using CNNs and creating the image generating models. I’m interested in exploring the mathematical logits behind different algorithms.

What is your impression about MCL and USC?

USC provides many high-quality courses for us, from which I got a solid basis and rich experience.  Also, the community provides us with many chances and platforms, through which we share information and communicate with each other effectively. Because of this I know MCL, in which a new theory about computer vision has been proposed and explored. I’m honored to join the MCL and work with the excellent students and professors here.

What is your future expectation and plan in MCL?

Computer vision and image processing is my long-time interest and MCL is the excellent lab specialized for this. For this reason, I want to take this chance and devote as much time and effort onto my work as I can. Hopefully, summer intern is a good start for me and in the future, I want to be one of the formal members of MCL as a PhD student.

By |June 21st, 2020|News|Comments Off on Welcome MCL New Member Jiamian Wang|

Welcome MCL New Member Zheng Wen

Could you briefly introduce yourself and your research interests?

My name is Zheng Wen, I’m currently pursuing my Master’s degree at USC in Electrical Engineering. I received my Bachelor’s degree in Beihang University, Beijing, China. I’m very curious in math and programming. I found it interesting to do something related matrix and machine learning, so I’m very glad that I Professor Kuo could give me this opportunity to join MCL and dive deeper in image processing, computer vision and machine learning.

What is your impression about MCL and USC?

This is my first year in USC, I found the campus is very beautiful even though kind of small. Leavey Library is a good place to study when we are struggling for the final exams of a semester. I really enjoy the American Chinese cuisine offered by the canteen. MCL is a big family. I get to know the members in MCL by EE569, Professor Kuo is an expert in multimedia, and his understanding in deep learning impressed me a lot. TAs are very experience in image processing and willing to help us.

What is your future expectation and plan in MCL?

In MCL, I want to do some project in image forensics with the help of Yao, learn more about image processing and machine learning, also sharpen my programming skills and make some progress to the domain. I will try my best to get involved in MCL and make friends with everyone.

By |June 14th, 2020|News|Comments Off on Welcome MCL New Member Zheng Wen|

Welcome MCL New Member Zhiwei Deng

Could you briefly introduce yourself and your research interests?

My name is Zhiwei Deng, I am a first year MSEE student at USC. I came from Anhui, China. I received my bachelor’s degree from Shanghai University in 2019. I had some experience in computer vision and machine learning fields during my undergraduate years. In this summer, I will continue to work on these areas, specifically on the topic of 3D point cloud classification and segmentation.

What is your impression about MCL and USC?

USC has a beautiful campus and serious research environment. I really enjoy both the natural views of the campus and the historical buildings with red bricks. I think MCL is a lab with creativity and courage. Old things are challenged, and new things are created here. I think mathematics and logics are quite important for the members of MCL. Also, I feel very honored and motivated to work new things out with these excellent people.

What is your future expectation and plan in MCL?

The most important thing of this summer for me is to have a clearer view in this field and have a deeper understand in certain topics in image processing. Also, I hope I can contribute to some projects during the internship. For the future career plan, I want to dig deeper in these areas in the future and pursue a higher level of academic degree.

By |June 7th, 2020|News|Comments Off on Welcome MCL New Member Zhiwei Deng|

Welcome MCL New Member Chengyao Wang

1. Could you briefly introduce yourself and your research interests?

My name is Chengyao Wang and I’m currently pursuing a M.S. degree in Electrical Engineering here at USC. Prior to that, I received my B.S. in Automation from Zhejiang University in 2018. With my interest lying in machine learning and computer vision, I’m now working on a summer intern project regarding classification and segmentation of medical images under the guidance of Prof. Kuo. I believe it will be a good starting point of exploring this intriguing area.

 

2. What is your impression about MCL and USC?

USC is well known for its academic achievements and strong alumni network, and it sure is. Everyone I met here is full of passion about what they’re doing and seems to be always ready to help others. MCL is such a dynamic and cohesive group, where everyone here could get a chance & full support to dig into their own areas of interest. Prof. Kuo is a respected expert with profound domain knowledge as well as a supportive instructor who knows well how to guide students and group people.

 

3. What is your future expectation and plan in MCL?

At this point, I would hope my current project goes on well and treat it with full devotion. I also want to connect with more people at MCL as a newcomer and blend into this warm and big family. Frankly speaking, I don’t have a clear vision for the future yet, but I believe I’ll stick to what I feel is interesting and make some differences.

By |May 31st, 2020|News|Comments Off on Welcome MCL New Member Chengyao Wang|

Welcome MCL New Member Yaqi Shao

1. Could you briefly introduce yourself and your research interests?

My name is Yaqi Shao. I graduated from Zhejiang Gongshang University with a B.S. degree in Computer Science and Technology. Now, I am pursuing a master’s degree in Computer Science at University of Southern California. I joined Media Communications Lab as an intern in Spring 2020. In the past, my research experience concentrates on image processing like image defogging and image enhancement. In MCL, I think I will have an opportunity to broaden my experience including face recognition and deep learning.

2. What is your impression about MCL and USC?

USC is an internationally renowned research university and rank in top 5% of the country for EE program. The Viterbi school focus on technology and help students becoming the specialist in their field. I took EE569 as an elective course under the instruction of Prof. Kuo whose hard-working and persistent spirit impressed me deeply. All the members in MCL takes continuous effort, working in groups to help each other.

3. What is your future expectation and plan in MCL?

I will continue working on face recognition and deep learning this summer with the group. As a new intern, I think I will learn a lot from Prof. Kuo and the PhD students not only in research methods but also in work methodology. I am very interested with image processing and deep learning and hope to experience related research more.

By |May 24th, 2020|News|Comments Off on Welcome MCL New Member Yaqi Shao|

Welcome MCL New Member Vasileios Magoulianitis

1. Could you briefly introduce yourself and your research interests?

My name is Vasileios Magoulianitis and I was born in Athens, Greece. I joined Viterbi School of USC in Spring 2020, pursuing a Master’s degree on Machine Learning and Data Science. I graduated from the Electrical Engineering department at the University of Thessaly, receiving my bachelor’s degree with honors. At that time, my research interests were focused on video compression and its efficient implementations. The last year of my undergraduate studies, I interned at Irida Labs s.a., where I had my first experience with image processing and computer vision algorithms. Before joining USC, I had been working as a research assistant for the Centre of Research and Technology Hellas (CERTH), participating in EU-funded projects. My current research interests revolve around image processing and computer vision, as well as machine learning.

 

2. What is your impression about MCL and USC?

Since my first days in MCL, I have been impressed about the atmosphere exists in the lab. It maintains a multi-cultural environment that brings together highly talented students with different backgrounds. The knowledge sharing quality is at top level and there exists an underlying energy that pushes everyone to achieve at his top potentials. The learning curve of students in MCL grows really fast, since everyone is willing to help each other and to share his research ideas and suggestions. Professor Kuo collaborates and communicates firmly with his students, showing that he cares about the people in his lab. I would like to take this chance to express my gratitude to him for giving me the chance to work in such a reputable lab. USC and MCL is the right place to carry out research and explore also [...]

By |May 17th, 2020|News|Comments Off on Welcome MCL New Member Vasileios Magoulianitis|
  • Permalink Gallery

    Professor C.-C. Jay Kuo Received IEEE Signal Processing Society Claude Shannon-Harry Nyquist Technical Achievement Award

Professor C.-C. Jay Kuo Received IEEE Signal Processing Society Claude Shannon-Harry Nyquist Technical Achievement Award

Congratulations to MCL Director, Professor Kuo, for receiving the 2019 IEEE Signal Processing Society Claude Shannon-Harry Nyquist technical achievement award. Originally, the award would be presented in an Award Ceremony held in ICASSP 2020, Barcelona, Spain. However, due to the COVID-10 pandemic, the Award Ceremony became a virtual one. It took place on May 8 (Friday), 9:30-10:30am, in Los Angeles local time. Here is a short interview with Professor Kuo.

Question: It is a great honor to receive the prestigious IEEE Signal Processing Society Claude Shannon-Harry Nyquist Technical Achievement Award. Do you have any words about this honor?

Answer: I would like to thank my family and all my former and current students for their strong support. It is a teamwork. The credit should go to all people surrounding me.

Question: You have been conducting research for nearly 40 years since you were a graduate student. What keeps you work so hard for so long?

Answer: Passion and curiosity are the key driving factors. I enjoy research. It is not work but fun. Certainly, recognitions from peers and technical communities boost the morale, too.

Question: What was your impactful research?

Answer: I have been working on multimedia computing for 30 years. Many multimedia technologies have become mature and they are widely used today. To give an example, video streaming and conferencing play an important role nowadays. This is especially evident during the COVID-19 pandemic. I have been working on video coding technologies and contributed to standardization activities. Video coding plays a central role in video streaming and conferencing.

Question: What is your current and future research focus?

Answer: Data science and engineering is an emerging field. Sometimes, people give it another name – Artificial Intelligence (AI). There are many fascinating research problems [...]

By |May 10th, 2020|News|Comments Off on Professor C.-C. Jay Kuo Received IEEE Signal Processing Society Claude Shannon-Harry Nyquist Technical Achievement Award|

MCL Research on Small Neural Netwrok

Deep learning has shown great capabilities in many applications. Many works have proposed different architectures to improve the accuracy. However, such improvement may come at a cost of increased time and memory complexity. Time and memory complexity can be important to some applications such as mobile and embedded applications. For these applications, small neural network design can be helpful. Small neural networks aim to reduce the network size while maintaining good performance. Some examples of small neural networks include SqueezeNet [1], MobileNet [2], ShuffleNet [3].

Despite the success of small neural networks, the reason why such networks can achieve good performance while significantly reducing the size has not been studied. In our research, we aim to quantitatively justify the design of small neural networks. In particular, we currently focus on the design of SqueezeNet [1].  SqueezeNet significantly reduces the number of network parameters while maintaining comparable performance by

Replacing some of the 3×3 filters with 1×1 filters. Since each 3×3 filter has 9 weights while a 1×1 filter has only 1 weight, we can greatly reduce the number of parameters by using 1×1 filters in place of 3×3 filters.
Reduce the number of input channels to 3×3 filters. This significantly reduces the number of parameters for the 3×3 filters.
Activation maps are downsampled late in the network. This is motivated by the intuition that larger activation maps may improve accuracy.

A key module of SqueezeNet is the Fire module. A Fire module consists of a squeeze layer and a subsequent expand layer. The squeeze layer reduces the number of input channels to the 3×3 filters in the expand layer. In our work, we use some metrics and visualization techniques to analyze the role of [...]

By |May 3rd, 2020|Computer Vision and Scene Analysis, News, Research|Comments Off on MCL Research on Small Neural Netwrok|

MCL Research on Source-Distribution-Aimed Generative Model

There are typically two types of statistical models in mechine learning, discriminative models and generative models. Different from discriminative models that aim at drawing decision boundaries, generative models target at modeling the data distribution in the whole space. Generative models tackle a more difficult task than discriminative model because it needs to model complicated distributions. For example, generative models should capture correlations such as “Things look like boats are likely to appear near things that look like water” while discriminative model differentiates “boat” from “not boat”.

Image generative models have become popular in recent years since Generative Adversarial Network (GANs), can generate realistic natural images. They, however, have no clear relationship to probability distributions and suffer from difficult training process and mode dropping problem. Although difficult training process and mode dropping problems may be alleviated by using different loss functions [1], the underlying relationship to probability distributions remains vague in GANs. It encourages us to develop a SOurce-Distribution-Aimed (SODA) generative model that aims at providing clear probability distribution functions to describe data distribution.
There are two main modules in our SODA generative model. One is finding proper source data representations and the other is determining the source data distribution in each representation. One proper representation for source data is joint spatial-spectral representation proposed by Kuo, et.al. [2, 3]. By transforming between spectral domain and spatial domain, a rich set of spectral and spatial representations can be obtained. Spectral representations are vectors of Saab coefficients while spatial representations are pixels in an image or Saab coefficients that are arranged based on their pixel order in spatial domain. Spectral representation at the last stage give a global view of an image while the spatial representations describe details in [...]

By |April 27th, 2020|Computer Vision and Scene Analysis, News, Research|Comments Off on MCL Research on Source-Distribution-Aimed Generative Model|