News

We are so happy to welcome a new summer intern student, Sreedhar Radhakrishnan, in Summer 2017. Let us hear what he said about his research and MCL.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

Hi, I am Sreedhar, I am currently an undergrad senior in Computer Science and Engineering at PES University,Bangalore,India and Data Science excites me. After my freshman year I interned at a research centre at my university where I was introduced to methodologies of research and I worked in the area of Computer Vision. The following year I had coursework in Design and Analysis of Algorithms and Linear Algebra which I fell in love with as I was able to get a perspective of how they are used in real world problems based on my research after my freshman year. The summer after sophomore year I worked on data analysis applied in the sport of Cricket and developed a player evaluation metric through the same. This really got me interested in leveraging the power of data in numerous applications. I then had course work in Data Analytics, Natural Language Processing, Digital Image Processing and Big Data which are some of my favorite courses. I am currently interested in Machine Learning and Deep Learning and their applications in various fields such as Computer Vision and NLP. I am currently working on Deep Learning for Computer Vision and learning a lot under the guidance of Dr. Kuo and fellow MCL members.

2. What’s your first impression of USC and MCL?

I just completed my first week of the summer internship here and I love the environment. Members of MCL are truly very hard working and dedicated in their [...]

We are so happy to welcome a new master student, Shilpashree Rao, in Summer 2017. Let us hear what she said about her research and MCL.

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

My name is Shilpashree Rao, pursuing Master’s degree in Electrical Engineering at University of Southern California. My research interests include Image Processing, Computer Vision, Machine learning and Robotics. The collaboration of innovation and knowledge describes my life wherein my interest towards these areas was sown by my ardor for art and creativity. I have previously advanced research studies on imaging techniques for facial expression detection and face recognition mechanisms for bio-metric applications. The research results have been published in National and IEEE publications. I have always enjoyed developing robots for social cause and I look forward to progress this with amalgamation of Machine learning, Computer Vision and Artificial Intelligence technologies.

2. What is your impression about MCL and USC?

I like the liveliness and the dynamic environment at USC. The people I have met here are focused, intelligent and of course fun-loving! USC and the location itself is great to build professional network. The opportunities to learn and explore recent technologies are unlimited here. MCL is one such lab at USC which nurtures such motivated students, providing resources and learning for advanced practical applications.

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

My future expectation at the MCL lab is to develop my skills and learning in deep learning techniques and image processing. To innovate and utilize these skills for practical purposes.

We are so happy to welcome a new master student, Zhuwei Xu, in Summer 2017. Let us hear what she said about her research and MCL.

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

My name is Zhuwei Xu, a master student in Electronic Engineering Department. I pursued my undergraduate degree in Electronic Science and Technology in Sichuan University. I have an interest of research in new fields. I like to know the latest techniques and apply them to different problems. I learnt a lot about signal processing and probability. I would like to be a researcher and explore the unknown knowledge. Nowadays, my research interests are machine learning and image processing.

2. What is your impression about MCL and USC?

I consider MCL is a great laboratory for me, since I would like to make some contribution in multimedia. Also, I think machine learning is a great idea for many new fields, so I am eager to apply some machine learning ideas on multimedia things.

USC is an outstanding university, it has many excellent faculties and peers in EE department. I want to learn from them and improve my abilities.

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

My research direction will focus on ‘object localization and classification’ this summer. I hope I can know more things about multimedia, machine learning and how to do research. I would like to do some exciting works, and build connections with people in this laboratory.

Four MCL members attended the Viterbi PhD hooding ceremony on Thursday, May 11, 2017, from 8:00-11:00 a.m. in the Bovard Auditorium. They were Yuzhuo Ren, Chi-Hao Wu, Qin Huang and Weihao Gan. Congratulations to them and their families for their accomplishments in completing their PhD program at USC.

Yuzhuo Ren received her B.S. degree in Hebei University of Technology, China, in 2011 and the M.S. degree from University of Southern California (USC) in 2013. Her research interest is the field of computer vision. Her thesis title is “Machine Learning Techniques for Outdoor and Indoor Layout Estimation”.

Qin Huang received the B.E. in Southeast University, Nanjing, China in 2012 and received the M.S. in Electrical Engineering at USC. He has been in Prof. Kuo’s Media Communications Lab since Nov 2013. His research interests include image and video processing, digital compression and computer vision.

Chi-Hao Wu received his B.S. and M.S. degrees in computer science from National Taiwan University in 2004 and 2006, respectively. He has rich experiences as a software engineer responsible for algorithm design in multimedia fields in Mediatek and IMEC Taiwan Innovation Center. Since 2013, he began his PhD study with Media Communications Lab at USC. His research interests include multimedia signal processing, multi-view image processing and computer vision.

Weihao Gan received his B.S. degree in automation from Huazhong University of Science and Technology in July, 2012. Then he finished his M.S. degree in Electrical Engineering at USC in May 2014. Since June 2013, he has been with Media Communications Lab. Now he is a PhD student in MCL, whose research interests include computer vision, machine learning and visual perception.

Congratulations to Yuzhuo Ren for passing her defense on April 26, 2017. Her Ph.D. thesis is entitled “Machine Learning Techniques for Outdoor and Indoor Layout Estimation”.

Abstract of thesis:

In my dissertation, I study three research problems: 1) Outdoor geometric labeling, and 2) Indoor layout estimation and 3) 3D object detection.

A novel method that extracts global attributes from outdoor images to facilitate geometric layout labeling is proposed. The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes. The performance of the proposed GAL system is demonstrated and benchmarked with several state-of-the-art algorithms against a popular outdoor scene layout dataset.

Existing solutions to indoor layout estimation largely rely on hand-craft features and vanishing lines. They often fail in highly cluttered indoor scenes. The proposed coarse-to-fine indoor layout estimation (CFILE) method consists of two stages: 1) coarse layout estimation; and 2) fine layout localization. In the first stage, we adopt a fully convolutional neural network (FCN) to obtain a coarse-scale room layout estimate that is close to the ground truth globally. In the second stage, we formulate an optimization framework that enforces several constraints such as layout contour straightness, surface smoothness and geometric constraints for layout detail refinement. The proposed CFILE system offers the state-of-the-art performance on two common benchmark datasets.

Given a RGB-D image, we examine the 3D object detection problem with an objective to produce a bounding box around the object and classify its category. This is a challenging problem due to high intra-class variance, illumination change, background clutter and occlusion. Here, we propose a novel solution that integrates the context information together to provide a robust 3D object detection solution. Extensive experiments are conducted to demonstrate that the proposed Context-3D method achieves the [...]