ruiyuanlin

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 [...]

Professor C.-C. Jay Kuo visited the Biomedical Engineering Department in the James  H. Clark Center of the Stanford University on April 17 to attend a research project meeting. Professor Tsung Hsiai of UCLA, Professor Alison Marsden of Stanford and Professor Jay Kuo have a joint NIH project on “Sheer Stress and Light-Sheets to Study Cardiac Trabeculation”. In this project, the team developed a Super Resolution Light-Sheet Microscopy (SRLSM) technology to advance the field of mechanotransduction and cardiac development. The role of MCL in this project is to incorporate computational algorithm to synchronize the cardiac cycle with the SRLSM-captured images for reconstruction of 4-D (3D + time) simulation. Two MCL PhD students have contributed to this project. They are Hao Xu and Ruiyuan Lin. Hao already graduated in 2017 January and now is working at Google. The MCL team provides the expertise to capture the beating hearts by period determination, relative shift determination, absolute shift determination, and post-processing.

Professor Kuo was very impressed by Stanford’s beautiful campus. He visited the campus before about 30 years ago. He hopes to have more opportunities to visit the Silicon Valley to meet MCL alumni.

Congratulations to Hao Xu for passing his defense on January 23, 2017. His Ph.D. thesis is entitled “Understanding Deep Learning from Its System Architectures, Feature Representations to Applications”.

Abstract of thesis:

Deep learning plays key roles in various aspects of the modern computer vision research. Our research focused on analyzing, adopting, and developing better CNN architectures which outperform the previous methods. To begin with, a car detection method using deformable part models consisting of composite feature sets (DPM/CF) is proposed. It recognizes cars of various types and from multiple viewing angles. The DPM/CF system consists of two stages. In the first stage, an HOG template is used to detect the bounding box of the entire car of a certain type and viewed from a certain angle (called a t/a pair), which yields a region of interest (ROI). In the second stage, we detect each salient part in a given t/a-specific ROI using either the HOG or the CNN feature. An optimization procedure based on latent logistic regression is adopted to choose the most discriminative location/size and the most suitable feature set for each part automatically. It is observed that the DPM/CF detector can strike a balance between detection performance and training complexity, through selecting the capable and simple feature from the composite feature set. Extensive experimental results are given to demonstrate the superior performance of the proposed DPM/CF method.

The CNN features used in DPM/CF demonstrate strong performance in detecting objects from images. To analyze the strength and weakness of the CNN feature representation, two quantitative metrics are proposed for the automatic evaluation of trained features at different convolution layers. The Gaussian confusion measure (GCM) is used to identify the discriminative ability of an individual feature, while [...]