News

Welcome New MCL Member Chaitra Suresh

We are so glad to welcome our new MCL member, Chaitra Suresh! Here is a short interview with Chaitra:
1. Could you briefly introduce yourself and your research interests?
 My name is Chaitra Suresh. I am a graduate student at USC, pursuing Master of Science in Electrical Engineering. I am from Bangalore, India. Prior to joining USC in Fall 2018, I worked at Bharti Airtel Limited for a year. I received my Bachelor’s degree in Electronics and Communication Engineering from R.V. College of Engineering, India in 2017. My current research interests include application of Machine learning in Computer Vision and Natural Language Processing.  
2. What is your impression about MCL and USC?
 USC has a very diversified culture with integrity. The institution has a lot of ongoing research activity with ample opportunities. Media Communications Lab led by Prof. C.-C. Jay Kuo facilitates working on emerging interdisciplinary areas. I have come across with lab members who work hard with determination and zeal. MCL has been a platform to acquire necessary skill to be a researcher. I am very glad to be onboard.
3. What is your future expectation and plan in MCL?
The lab environment with weekly meeting and seminar facilitates me to learn and adapt to recent developments. I am looking forward to the constant process of learning and understanding concepts under the guidance of Prof. C.-C. Jay Kuo. The ability to think differently drives me to gain experience in my research interest.
 

By |July 15th, 2019|News|Comments Off on Welcome New MCL Member Chaitra Suresh|

Welcome New MCL Member Vaishnavi Krishnamurthy

We are so glad to welcome our new MCL member, Vaishnavi Krishnamurthy! Here is a short interview with Vaishnavi:
1.    Could you briefly introduce yourself and your research interests?
My name is Vaishnavi Krishnamurthy and I am a graduate student at USC pursuing Masters in Electrical engineering with focus on image processing and machine learning. I hail from a city called Bengaluru which is located in the southern part of India. I completed my Bachelors degree in Electronics and Communication Engineering at Rashtreeya Vidyalay College of Engineering, Bengaluru. Post my undergrad studies and prior to joining USC, I worked as a Senior Executive at Bharti Airtel, Gurugram in Networks for a year. 
Broadly, my research interest lies in solving the current challenges in image processing using deep learning approach. I developed interest in this field when I was working on a biomedical imaging project that aimed at brain tissue segmentation for tumor detection. Currently, I am continuing my research on semantic image segmentation at the MCL lab in USC.
2.    What is your impression about MCL and USC?
In my initial days at USC, I felt that the coursework was challenging and it took a while for me to cope with the fast paced curriculum. The student life at USC has taught me that consistency is the key to achieve excellence in any given field. For a toddler in research like me, MCL lab has provided an extremely conducive environment to be in. Working under the guidance of Prof. Jay Kuo and his extremely motivated and helpful bunch of PhD students has been an amazing experience and I wish to utilize this opportunity to learn more and hone my research skills.
3.    What is [...]

By |July 8th, 2019|News|Comments Off on Welcome New MCL Member Vaishnavi Krishnamurthy|

Welcome New MCL Member Ranga Sai Shreyas Manchikanti

We are so glad to welcome our new MCL member, Ranga Sai Shreyas Manchikanti! Here is a short interview with Shreyas:
1. Could you briefly introduce yourself and your research interests?
My name is Ranga Sai Shreyas Manchikanti (long! I know). I am a graduate student studying for the Master’s degree in Electrical Engineering. I have spent almost my entire life in a city in southern India called Bangalore before coming to USC. I did my undergraduate degree from National Institute of Technology Karnataka, Surathkal in Electronics and Communication Engineering. I was working at Goldman Sachs as a Software Developer for the past 3 years before joining the graduate program. I have a strong passion towards computer vision and it’s application in everyday life. Specifically, I am very motivated to work in robotics where the images captured by the robot perform a huge role in understanding the environment and performing actions to navigate in the environment.
2. What is your impression about MCL and USC?
Since I joined USC, I have had the chance to meet amazing people all around me. The environment provided by the USC campus inspires me to work had and improve myself. Also, the various facilities available at USC are state of the art and I am very glad to have come to this place for my Master’s degree. MCL is a first research group that I have ever been a part of. I feel that there are a lot of highly skilled and motivated people here at MCL and I am very happy to have the opportunity to work with so many talented people. The weekly gathering of MCL members is also a great activity that helps me to [...]

By |July 1st, 2019|News|Comments Off on Welcome New MCL Member Ranga Sai Shreyas Manchikanti|

Welcome New MCL Member Pranav Kadam

We are so happy to welcome our new MCL member, Pranav Kadam! Here is a short interview with Pranav.

1. Could you briefly introduce yourself and your research interests?
My name is Pranav Kadam and am a graduate student at USC pursuing Master’s degree in Electrical Engineering. I grew up in a city called Pune which is in the western part of India. Prior to joining USC in Fall 2018, I completed my Bachelor’s degree in Electronics and Telecommunications Engineering from Savitribai Phule Pune University. In my undergraduate coursework, I found topics like image processing and neural networks quite interesting. I did some projects in these fields and read a lot a regarding recent developments then, such as CNNs. I am continuing my research and specialization in Computer Vision and Machine Learning at USC.

2. What is your impression about MCL and USC?
USC is a great urban campus with excellent educational and research facilities. A lot of focus is given on mastering the fundamental topics and concepts for a long-term career in the field of interest. In addition, Los Angeles is a large metropolis and there are plenty of options for entertainment, food and sightseeing, all very nearby campus, making it an ideal city to be in during graduate studies. MCL is a team of talented and passionate students headed by Prof. Kuo who is very experienced, insightful and supportive. Lab activities like research meetings and weekly seminars ensure that everyone is aware of each other’s work and there is a good bonding among members.

3. What is your future expectation and plan in MCL?
I would like to work under the guidance of Prof. Kuo and develop the necessary skills to be a successful researcher. [...]

By |June 23rd, 2019|News|Comments Off on Welcome New MCL Member Pranav Kadam|

Welcome New MCL Member Chengwei Wei

We are so glad to welcome our new MCL member, Chengwei Wei! Here is a short interview with Chengwei:

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

My name is Chengwei Wei, and I am a 18fall EE master student at USC. I come from Changsha, China and received my Bachelor’s degree majoring in automation from Central South University, China in Jun 2018. In my undergraduate study, I realize how to get a good signal input and process the signal are crucial parts in control system design, which is the reason I am very interested in signal processing. Currently I focus on image processing and machine learning.

2. What is your impression about MCL and USC?

The most impressive things about USC are the beautiful campus with convenient facilities and the perfect weather in LA. MCL is a large Lab in ECE department, and the leader Prof. Kuo is a respectable and energetic person. The members of MCL are very friendly, hardworking and are fun to be with.

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

My future expectation of this summer is to learn more about image processing and how to do a good research. Hope I can obtain some achievements in the field of image processing and machine learning in the coming future.

 

By |June 16th, 2019|News|Comments Off on Welcome New MCL Member Chengwei Wei|

Welcome New MCL Member Yifan Wang

We are so glad to welcome our new MCL member, Yifan Wang! Here is a short interview with Yifan:

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

My name is Yifan Wang, a graduate student in Department of Electrical and Engineering of USC. I received my bachelor’s degree in electrical engineering from Fudan University. When I was an undergraduate student, I learnt courses from multi-fields including digital and analog circuit, computer architecture etc. Among these, I found my interests lies in vision fields which is of vital importance to both human and machine.

2. What is your impression about MCL and USC?

I have been USC for two semesters. It is a really nice place for studying, since there are few entertainment sites outside school along with the super good sun shine prohibit me from going outside regularly. MCL is a large warn family where I met lots of talent people. It would be nice to make new friends and learn new things in MCL.

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

I would like to learn more theories and mathematics related to computer vision which would be the foundation of my future research. Besides, I would like to gain more practice in deep learning fields which are highly hardware relied.

 

By |June 9th, 2019|News|Comments Off on Welcome New MCL Member Yifan Wang|

MCL Research on Word Embedding

Word embeddings have been widely applied across several NLP tasks. The goal for word embedding is to transferring words into vector representations which embeds both syntactic and semantic information. General word embedding is usually generated by training on a large corpus like the whole wiki text data.

Our first work is mainly focus on improving the performance over trained word embedding models to make is more representative. The motivations are: (1) Even though current model are trained without considering the order of each dimension. But the obtain word embedding is usually carries a large mean and the variance is mostly lies on the first several principal components. This could lead hubness problem and we would like to analysis the statistics to make the whole space more iso-tropical. (2) The information of ordered input sequences is lost because of the context-based training scheme. From the above analysis, we proposed two ways to perform post-processing of word embedding call Post-processing via Variance Normalization (PVN) and Post-processing via Dynamic Embedding (PDE). The effectiveness of our model is verified over both intrinsic and extrinsic evaluation methods. For details, please refer to: [1].

During the past several years, word embedding is very popular, but the evaluation is mainly conducted over intrinsic evaluation methods because of their convenience. In Natural Language Processing society, we care about more the effective of word embedding on real NLP tasks like translation, sentiment analysis and question answering. Our second word focus on the word embedding quality and its relationship with evaluation methods. We have discussed criterions that a good word embedding should have and also for evaluation methods. Also, the properties of intrinsic evaluation methods are discussed because different intrinsic evaluator tests from different perspectives. Finally, [...]

By |June 2nd, 2019|News|Comments Off on MCL Research on Word Embedding|

MCL Research on Point Cloud Classification

With the rise of visualization, animation and autonomous driving applications, the demand for 3D point cloud analysis and understanding has rapidly increased. Point Cloud is a kind of data obtained from lidar scanning which contains abundant 3D information. ModelNet40 is a point cloud dataset contains 40 classes of objects. In this project, we use ModelNet40 dataset for the analysis and evaluation of point cloud classification. Many of the recent works focus on developing end to end algorithm like other convolutional neural networks for images. However, object and scene understanding with Convolutional Neural Networks (CNNs) on 3D volumetric data is still limited due to its high memory requirement and computational cost. For some simple tasks like classification, this method is too much.

An interpretable CNN design based on the feedforward (FF) methodology [1] without any backpropagation (BP) was recently proposed by the Media Communications Lab at USC. The classification baseline is composed by four Saab units, each unit contains KNN query, space grouping and Saab transform, and between units we use farthest sampling to improve efficiency. We are still working on it to improve as much as possible. Our goal is to catch up with the state-of-the-art results and show that FF design is powerful and useful. The advantages of the FF design methodology are multiple folds. It is completely interpretable. It demands much less training complexity and training data. Furthermore, it can be generalized to weakly supervised or unsupervised learning scenarios in a straightforward manner. The latter is extremely important in real world application scenarios since data labeling is very tedious and expensive.

The advantages of the FF design methodology are multiple folds. It is completely interpretable. It demands much less training complexity and training data. [...]

By |May 26th, 2019|News|Comments Off on MCL Research on Point Cloud Classification|

MCL Members Attended the PhD Hooding Ceremony

Nine MCL members attended the Viterbi PhD hooding ceremony on Thursday, May 9, 2019, from 8:30-11:00 a.m. in the Bovard Auditorium. They were Fenxiao Chen, Yueru Chen, Ronald Salloum, Yuhang Song, Yuanhang Su, Ye Wang, Chao Yang, Heming Zhang, and Junting Zhang. Congratulations to them for their accomplishments in completing their PhD program at USC!

Fenxiao (Jessica) Chen received the B.S. degree in General Engineering from Harvey Mudd College, Claremont, CA in 2014. She then continued with her PhD in Media Communications Lab at USC from 2017. Her research interests include natural language processing and deep learning.

Yueru Chen received her Bachelor’s degree in Physics from the University of Science and Technology of China in June 2014. Since 2015, she joined MCL for the PhD study. Her thesis topic is “Object Classification based on Neural-network-inspired Image Transforms”, where she focuses on solving the image classification problem based on the neural-network-inspired Saak transform and Saab transform.

Ronald Salloum received his B.S. degree in Electrical Engineering from California State Polytechnic University, Pomona, and his Ph.D. degree in Electrical Engineering from University of Southern California (USC). The title of his dissertation is “A Data-Driven Approach to Image Splicing Localization.” His research interests include multimedia forensics, machine learning, and biometrics.

Yuhang Song received his Bachelor’s degree in Electronic Engineering from Tsinghua University, Beijing in 2014. He then joined MCL to pursue Ph.D. degree in Electrical Engineering at USC from 2015. His research interests include deep generative models, image generation, visual relationship detection, and visual understanding.

Yuanhang Su received his Ph.D. at the University of Sothern California (USC) in computer vision, natural language processing and machine learning. He received M.S. degree from the USC in 2010 and the dual B.S. degree from the University [...]

By |May 19th, 2019|News|Comments Off on MCL Members Attended the PhD Hooding Ceremony|

Congratulations to Harry Yang for Passing His Defense!

Congratulations to Harry Yang for passing his defense on May 7, 2019! Let us hear what he would like to say about his defense and an abstract of his thesis.

“In the thesis, we tackle the problem of translating faces and bodies between different identities without paired training data: we cannot directly train a translation module using supervised signals in this case. Instead, we propose to train a conditional variational auto-encoder (CVAE) to disentangle different latent factors such as identity and expressions. In order to achieve effective disentanglement, we further use multi-view information such as keypoints and facial landmarks to train multiple CVAEs. By relying on these simplified representations of the data we are using a more easily disentangled representation to guide the disentanglement of image itself. Experiments demonstrate the effectiveness of our method in multiple face and body datasets. We also show that our model is a more robust image classifier and adversarial example detector comparing with traditional multi-class neural networks.

“To address the issue of scaling to new identities and also generate better-quality results, we further propose an alternative approach that uses self-supervised learning based on StyleGAN to factorize out different attributes of face images, such as hair color, facial expressions, skin color, and others. Using pre-trained StyleGAN combined with iterative style inference we can easily manipulate the facial expressions or combine the facial expressions of any two people, without the need of training a specific new model for each of the identity involved. This is one of the first scalable and high-quality approach for generating DeepFake data, which serves as a critical first step to learn a more robust and general classifier against adversarial examples.”

Harry also shared about his Ph.D. experience:

“Firstly, I would [...]

By |May 12th, 2019|News|Comments Off on Congratulations to Harry Yang for Passing His Defense!|