ruiyuanlin

MCL members, Yuzhuo Ren and Wenchao Zheng presented their papers at Asian Conference on Computer Vision (ACCV) 2016.

Yuzhuo’s presented paper is entitled “a coarse-to-fine indoor layout estimation (CFILE) method”. Here is an abstract of the paper:

Existing solutions to indoor layout estimation problem largely rely on hand-craft features and vanishing lines, and they often fail in highly cluttered indoor rooms. 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. The proposed FCN considers combines the layout contour property and the surface property so as to provide a robust estimate in the presence of cluttered objects. 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. Our proposed system offers the state-of-the-art performance on two commonly used benchmark datasets.

Wenchao’s paper is entitled “Object Boundary Guided Semantic Segmentation”. Here is a brief summary of the paper:

Recent development in fully-convolutional neural network (FCN) has enabled accurate pixel-level in semantic segmentation. However, segmentation details are lost since the object boundary information is not exploited. Our proposed object boundary guided FCN (OBG-FCN) is able to integrate the distinct properties of object shape and class features elegantly in a fully convolutional way with a designed masking architecture. We show that the end-to-end trainable OBG-FCN system offers great improvement in optimizing the target semantic segmentation quality.

Congratulations to Yuzhuo and Wenchao for their quality research work!

We are so happy to welcome a new undergraduate student, Beatriz Sousa, in Fall 2016. Let us hear what she said about research and MCL.

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

My name is Beatriz Sousa, and I am a freshman at USC pursuing a BS degree in Electrical Engineering. I am very interested in expanding my knowledge in the programming side of electrical engineering so that I can better apply my knowledge toward making electronic circuits in various gaming systems in the future. I am also interested in better understanding how programming and circuit systems work together to create such a dynamic environment for the gamer, and thus problem solving to better develop such an environment.

2. What is your impression about MCL and USC?

USC is a supportive community that is always looking for new ways to expand and improve current technologies. MCL provides me with the same impression as every member is interested and passionate about what they are doing and are very friendly and willing to help.

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

My future expectation is to learn a lot about programming, especially in games, and how different aspects of the program interact with the systems present in the console to create an effect on the user that I would have not expected otherwise. I hope to create strong connections that will not only help me in my work in MCL but outside of it as well.

We are so happy to welcome a new Ph.D. student, Yeji Shen, in fall 2016. Here is an interview with him.

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

Before becoming a Ph.D. student in USC, I got my bachelor degree in Computer Science from Peking University. My past research experience includes Image Quality Assessment (IQA), a little bit on Computational Neuroscience and a few on Computer Vision (CV) and Deep Learning. I have published one paper on IQA under the supervision of Prof. Tingting Jiang. She is also the advisor of my bachelor thesis. I was having a wonderful experience last summer in Carnegie Mellon University working with Prof. Tai Sing Lee on an EEG based project. My research interest is mainly about exploring the essentials of Machine Learning (ML) theory and applying ML techniques to multiple areas like CV, or ultimately speaking, the Artificial Intelligence. I was having strong programming skills 🙂 but relatively thin knowledge in mathematics and statistics where I am trying to improve through the training of Ph.D. program. Personally, I play baseball / softball and possess some skills in Slow Pitch. I like games and animations.

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

USC has a beautiful campus which stands head and shoulders above the environment nearby. Convenient facilities, gyms and fountains are everywhere. She is a university with history and culture. I am looking forward to becoming a proud Trojan nourished by USC.

MCL is an awesome and prospering research group having more than 20 friendly and hardworking members. Everything goes well under the supervision of Prof. Kuo. Prof. Kuo is profound in knowledge and research. He is a very nice advisor and also a senior worthy [...]

In summer 2016, four MCL members—Siyang Li, Chen Chen, Shangwen Li, and Jian Li—worked for Google, Facebook (Chen and Shangwen), and Apple respectively as summer interns. We are so glad to have them share their internship experience.

1. How was working in Apple/Facebook/Google?

Jian: The working environment and atmosphere in Apple are amazing but very unique when having Internship at Apple. You can work with smart people all around the world, who are friendly and helpful. Mentors and managers work closely with interns so that we can make contributions. I was working as a R&D role, which I enjoyed a lot. Moreover, you can also find good work and life balance here since there were several special events only for Apple summer interns.
Siyang Li: This was my second intern at Google, so everything went quite smoothly. My colleagues were friendly and helpful. Whenever I got stuck, my host answered my question quickly and pointed to helpful resources. Life there was easy, as almost everything (food, gym, laundry) was free. I guess this is Google’s trick to make you more concentrated on work.
Chen and Shangwen: It is firstly excited to get into Facebook—one of the top IT company in the work. On the first day of our training session, we met a lot of young genius from top Universities. We started to feel pressure from then. In the company, everyone is smart and diligent. That makes the moving pace extremely fast for the whole team. It is good to visualize, experience and push the high speed and learn from the genius around us. On the other side, there is still a lot of fun during the time we are in Facebook. There are many interesting [...]