News

Face attributes classification is an important topic in biometrics. The ancillary information of faces such as gender, age and ethnicity is referred to as soft biometrics in forensics. The face gender classification problem has been extensively studied for more than two decades. Before the resurgence of deep neural networks (DNNs) around 7-8 years ago, the problem was treated using the standard pattern recognition paradigm. It consists of two cascaded modules: 1) unsupervised feature extraction and 2) supervised classification via common machine learning tools such as support vector machine (SVM) and random forest (RF) classifiers.

We have seen a fast progress on this topic due to the application of deep learning (DL) technology in recent years. Cloud-based face verification, recognition and attributes classification technologies have become mature, and they have been used in many real world biometric systems. Convolution neural networks (CNNs) offer high performance accuracy. Yet, they rely on large learning models consisting of several hundreds of thousands or even millions of model parameters. The superior performance is contributed by factors such as higher input image resolutions, more and more training images and abundant computational/memory resources.

Edge/mobile computing in a resource-constrained environment cannot meet the above-mentioned conditions. The technology of our interest finds applications in rescue missions and/or field operational settings in remote locations. The accompanying face inference tasks are expected to execute inside a poor computing and communication infrastructure. It is essential to have a smaller learning model size, lower training and inference complexity, and lower input image resolution. The last requirement arises from the need to image individuals at farther standoff distances, which results in faces with fewer pixels.

In this research, MCL worked closely with ARL researchers in developing a new interpretable non-parametric machine [...]

MCL received a grant from the US Army Research Laboratory (ARL) recently for joint research on theory and applications of artificial intelligence (AI) and machine learning (ML) technologies. Through this support, MCL researchers will collaborate with ARL researchers to conduct fundamental and applied research in the next 4 years.

The fundamental research targets at explainable neural networks. Cybenko and Hornik et al. proved that the multi-layer perceptron (MLP) is a universal approximator in late 80s, which appears to be the most important theoretic result even up to now. However, for a given dataset, they do not provide a constructive procedure to build the MLP. We will investigate a systematic way to specify an MLP architecture and determine its model parameters. Resource-rich and resource-scarce networks refer to those have abundant and fewer model parameters, respectively. The objective of the stress test study is to understand the behavior of the transition of a network from a resource-rich one to a resource-scarce one. We would like to understand the behavior transition in several areas, including model sensitivity to different weight initializations, classification accuracy, overfitting, etc.

The applied research targets at spatial-temporal attention and semantic scene understanding via successive subspace learning (SSL). To extract key spatial-temporal information from visual data, facilitates video processing and understanding down-stream tasks. For example, an image contains one or several objects. Object detection and recognition is critical to image understanding. Also, motion provides cues for object tracking in video understanding. The sponsored research will also focus on two issues on multi-modality data, say, those obtained by RGB, depth and infrared sensors: 1) representation of multi-domain data and 2) understanding of multi-domain data.

—- by Dr. C.-C. Jay Kuo

Could you briefly introduce yourself and your research interests?

My name is Zhiyao Luo. I am a 1st year M.S. student in the program of EE general and join the MCL lab at USC for summer intern. I received my bachelor’s degree of engineering in Xi’an Jiaotong University of China. I have the background of machine learning and signal processing theory and I have some research background on classification and optimization problems. I have a passion for understanding models and algorithms in the field of computer vision by applying them to solve realistic problems.

What is your impression about MCL and USC?

I was deeply impressed by the school’s full consideration of students from different cultural backgrounds and I believe that USC can offer me plenty opportunities and  resource that I need. The first time I know about MCL is in EE569 course because most of TAs and graders in that course are members in MCL and the professionalism and rigor of MCL have been widely recognized in our class since then. It is my first week in MCL, I find that all the works are organized well and efficient, it makes me believe that I will gain a lot from MCL.

What is your future expectation and plan in MCL?

I hope I can help to finish some meaningful work in this summer and learn from other outstanding members in MCL. For my own career planning, I want to get familiar with the pace of academic research in MCL. If I think this kind of work is suitable for me and I believe that I will be able to achieve valuable result, I will try to get a chance to continue my academic career in [...]

Could you briefly introduce yourself and your research interests?

I am an EE master student in Viterbi. I just finished my first year of master’s. I get my bachelor’s degree from the electronic college in Nanjing University of Posts and Telecommunications. I like playing tennis, badminton, table tennis and jogging. I also joined the tennis club at USC. My area of interest is machine learning and signal processing. The topic I want to study is video tracking which I think is a very useful technique.

What is your impression about MCL and USC?

I think the members of MCL is very kind. They are always willing to help me when I have questions about the course. They spend lots of time explaining until I fully understand. Besides, I think Professor Kuo is a good manager. Professor Kuo personally guides everyone, and all members of MCL has clear goals and tasks.

What is your future expectation and plan in MCL?

I hope I can work hard and learn more about video tracking and machine learning. I want to have a deeper insight into them. I know I am too naïve now both in experience and knowledge, so I want to learn how to do research and academic report. If possible, I also want to make some contribution to MCL. In the future, I would like to become a PhD student.

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.