News

Welcome new MCL member Dr Xinfeng Zhang!

We are so happy to welcome a new Post Doctor, Dr Xinfeng Zhang, this Fall 2017. Let us hear what he has to say about his research and MCL.

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

My name is Xinfeng Zhang, and I received my B.S. degree in computer science from Hebei University of Technology, Tianjin, China, in 2007, and the Ph.D. degree in computer science from the Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, in 2014. From, Jul. 2014 to Oct. 2017, I was a research fellow in Rapid-Rich Object Search (ROSE) Lab in Nanyang Technological University, Singapore. My research interests include image/video compression, processing and quality assessment. I am also interested in image/video retrieval and analysis.

2. What is your impression about MCL and USC?

When I joined MCL, I was impressed with the professional group seminar, which is very formal and beneficial for both the speakers and audience. The active discussions among students also provide various views for us to think about questions. Moreover, I love the environment of USC, and it is real very beautiful.

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

I am very interested in the Saak transform, and I think it is a new powerful tool in image/video compression and understanding. Therefore, I hope to explore the characteristics of Saak transform, and investigate the higher compression performance using Saak transform. I also hope to become friends with all the other MCL members.

By |December 13th, 2017|News|Comments Off on Welcome new MCL member Dr Xinfeng Zhang!|

MCL celebrates Thanksgiving!

On November 23, MCL members and their respective families set out on a lavish Thanksgiving Luncheon organized by Professor Kuo at the China Great Buffet in El Monte. Thanksgiving has been an MCL tradition for over 20 years now, and this year was no exception. The spread was extremely satiating and diverse with an assortment of dishes including sushi, seafood, pizzas and dessert. All in all, it was a perfect start to a great holiday!

By |December 2nd, 2017|News|Comments Off on MCL celebrates Thanksgiving!|
  • Permalink Gallery

    MCL Student, Junting Zhang, Presented Paper at GlobalSIP 2017

MCL Student, Junting Zhang, Presented Paper at GlobalSIP 2017

MCL Student Junting Zhang presented a paper at the 5th IEEE Global Conference on Signal and Information Processing (GlobalSIP 2017) in Montreal Quebec, Canada on November 15, 2017. Here’s an abstract of the paper :
Scene text detection is a critical prerequisite for many fascinating applications for vision-based intelligent robots. Existing methods detect texts either using the local information only or casting it as a semantic segmentation problem. They tend to produce a large number of false alarms or cannot separate individual words accurately. In this work, we present an elegant segmentation-aided text detection solution that predicts the word-level bounding boxes using an end-to-end trainable deep convolutional neural network. It exploits the holistic view of a segmentation network in generating the text attention map (TAM) and uses the TAM to refine the convolutional features for the MultiBox detector through a multiplicative gating process. We conduct experiments on the large-scale and challenging COCO-Text dataset and demonstrate that the proposed method outperforms state-of-the-art methods significantly.

By |November 24th, 2017|News|Comments Off on MCL Student, Junting Zhang, Presented Paper at GlobalSIP 2017|
  • Permalink Gallery

    MCL Director, Professor Kuo, gave a Keynote Speech at ISPACS 2017

MCL Director, Professor Kuo, gave a Keynote Speech at ISPACS 2017

Professor C.-C. Jay Kuo gave a keynote speech in the IEEE Conference on Intelligent Signal Processing and Communication Systems held in Xiamen, China on November 7th. The title of his talk is “Why Deep Learning Networks Work So Well?” The abstract of his talk is given below.

“Deep learning networks, including convolution and recurrent neural networks (CNN and RNN), provide a powerful tool for image, video and speech processing and understanding nowadays. However, their superior performance has not been well understood. In this talk, I will unveil the myth of CNNs. To begin with, I will describe network architectural evolution in three generations: first, the McClulloch and Pitts (M-P) neuron model and simple networks (1940-1980); second, the artificial neural network (ANN) (1980-2000); and, third, the modern CNN (2000-Present). The differences between these three generations will be clearly explained. Next, theoretical foundations of CNNs have been studied from the approximation, the optimization and the signal representation viewpoints, and I will present main results from the signal processing viewpoint. A good theoretical understanding of deep learning networks provides valuable insights into the past, the present and the future of their research and applications.”

Understanding CNNs is one of the main activities of the MCL in last 3-4 years. Several PhD students and post-docs have made contributions to this topic, including Hao Xu and Yueru Chen.

By |November 19th, 2017|News|Comments Off on MCL Director, Professor Kuo, gave a Keynote Speech at ISPACS 2017|

Congratulations to Weihao Gan for passing his defense!

Let us hear what he has to say about his defense and an abstract of his thesis.

Online object tracking is one of the fundamental computer vision problems. It is commonly used in real world applications such as traffic control and safety in video surveillance, autonomous vehicle, robotic navigation, medical imaging, etc. It is a very challenging problem due to multiple time-varying attributes in video sequences.

In this research, we investigate two different kinds of tracking problems: single object tracking (SOT) and multiple object tracking (MOT). First, we attempt to achieve online single object tracking using both spatial and motion cues with two novel methods. One is a traditional framework called “temporal prediction and spatial refinement (TPSR)” tracker, consisting of three cascaded modules: pre-processing (PP), temporal prediction (TP) and spatial refinement (SR). Another one is based on convolutional neural network architecture that treats the tracking as a detection problem, called ”Motion-Guided Convolutional Neural Network (MGNet) Tracker”. It has two innovations: 1) adoption of a motion-guided candidate selection (MCS) scheme based on a dynamic prediction model, and 2) usage of a RGB- plus-motion 5-channel input to the convolutional neural network (CNN). From the two proposed methods, we have showed the advantages of combining spatial information and motion cue together to improve the tracking performance.

Second, from the proposed SOT technique, we build an online multiple object tracking system with advanced model update and matching. This method treats the MOT problem as an online tracking problem, rather than the global optimization framework. There are three major components in this tracking system: 1) a system platform built upon multiple CNN single object trackers in MOT environment; 2) the proposed advanced online update strategy including incremental and aggressive update mode; 3) [...]

By |November 14th, 2017|News|Comments Off on Congratulations to Weihao Gan for passing his defense!|

Welcome new MCL member Madhvi Kannan!

We are so happy to welcome a new master student, Madhvi Kannan, in Fall 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 Madhvi Kannan and I’m a Master’s Student in Electrical Engineering at USC. I joined MCL this Fall to work under Professor Kuo and his PhD student Ruiyuan Lin. My research interests include Image Processing and Deep Learning.

2. What is your impression about MCL and USC?

When I first joined MCL I was very excited to be exposed to the research being carried out by all the PhDs. I found that the research being conducted in MCL is up to date with the current trends in technology. The weekly seminars and study groups are extremely effective and novel.

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

​I hope to gain as much knowledge as possible in the fields of Image Processing, Computer Vision and Deep Learning during my term at MCL. I also look forward to learning from all the other lab members.

By |October 29th, 2017|News|Comments Off on Welcome new MCL member Madhvi Kannan!|

Welcome New MCL Member Fenxiao Chen

We are so happy to welcome a new Ph.D. student, Fenxiao Chen, in Fall 2017. Let us hear what she said about her research and MCL.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)
I worked on Cloud Computing and distributed systems before. I interned at Berkeley National Lab on DNA k-mer assembly and Artigen Corp on natural language processing.

2. What’s your first impression of USC and MCL?
First impression of USC is that it’s a school that welcomes a great range of diversity. MCL is the largest research group I have seen so far in the EE department. I like the researching environment that is not only encouraging but also inspiring.

3. What’s your future expectation for MCL?
I hope I can develop more expertise on natural language processing and deep learning. With the help of MCL I wish to bring my own contribution as well.

By |October 9th, 2017|News, Uncategorized|Comments Off on Welcome New MCL Member Fenxiao Chen|

Welcome New MCL Member Harry Yang

We are so happy to welcome a new Ph.D. student, Harry Yang, in Fall 2017. Let us hear what he said about his research and MCL.

1. Could you briefly introduce yourself and your research interests?
My name is Chao “Harry” Yang, and I am a 2nd year Ph.D. student at the MCL lab in the department of computer science at USC. Prior to joining MCL, I was a PhD student at the computer graphics lab of USC. I received my Bachelor’s degree of mathematics in University of Science and Technology of China. I am interested in computer vision and deep learning, and previously I worked on research projects related to image inpainting and domain adaptation.

2. What’s your first impression of USC and MCL?
USC has a beautiful campus and a vibrant research environment. I love to walk in the campus seeing a lot of students and professors full of passion and energy. The MCL lab is a wonderful place with a caring and supportive advisor and a large group of young talented students. I feel more motivated and enthusiastic about my everyday research after joining MCL and I super enjoy the interaction with the professor and group members.

3. What is your future expectation and plan in MCL?
I want to make friends in MCL, do good research and write high-quality papers. I am really excited to be able to learn from everyone in the group. With so much help and support, I am looking forward to a great career ahead of me after finishing my study in MCL.

By |October 1st, 2017|News, Uncategorized|Comments Off on Welcome New MCL Member Harry Yang|

MCL Students Presented Papers at BMVC 2017

We would like to share the good news that our group has two papers accepted by BMVC 2017 from Qin Huang and Siyang Li. This year BMVC is more competitive than before, according to the conference committee. We are happy that our group successfully has two papers, especially with one as oral presentation.

–Qin Huang, Chunyang Xia, Chihao Wu, Siyang Li, Ye Wang, Yuhang Song and C.-C. Jay Kuo, “Semantic Segmentation with Reverse Attention” (Oral)
–Siyang Li, Xiangxin Zhu, Qin Huang, Hao Xu and C.-C. Jay Kuo, “Multiple Instance Curriculum Learning for Weakly Supervised Object Detection” (Poster)

Here are the Obstructs for the two papers:

“Semantic Segmentation with Reverse Attention”:
Obstruct: Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation. Traditionally, the convolutional classifiers aretaught to learn the representative semantic features of labeled semantic objects. In thiswork, we propose a reverse attention network (RAN) architecture that trains the net-work to capture the opposite concept (i.e., what are not associated with a target class) aswell. The RAN is a three-branch network that performs the direct, reverse and reverse-attention learning processes simultaneously. Extensive experiments are conducted toshow the effectiveness of the RAN in semantic segmentation. Being built upon theDeepLabv2-LargeFOV, the RAN achieves the state-of-the-art mean IoU score (48.1%)for the challenging PASCAL-Context dataset. Significant performance improvementsare also observed for the PASCAL-VOC, Person-Part, NYUDv2 and ADE20K datasets.

“Multiple Instance Curriculum Learning for Weakly Supervised Object Detection”:
Obstruct: When supervising an object detector with weakly labeled data, most existing ap- proaches are prone to trapping in the discriminative object parts, e.g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects. To address this challenge, [...]

By |September 25th, 2017|News, Uncategorized|Comments Off on MCL Students Presented Papers at BMVC 2017|

Congratulations to Eddy Wu for Passing His Defense

Congratulations to Eddy Wu for passing his defense. His thesis title is “Deep Learning Techniques for Supervised Pedestrian Detection and Critically-Supervised Object Detection” with three major topics, as follow:

In the first topic, a boosted convolutional neural network (BCNN) system is proposed to enhance the pedestrian detection performance. Being inspired by the classic boosting idea, we develop a weighted loss function that emphasizes challenging samples in training a convolutional neural network (CNN). Two types of samples are considered challenging: 1) samples with detection scores falling in the decision boundary, and 2) temporally associated samples with inconsistent scores. Finally, we train a boosted fusion layer to benefit from the integration of these two weighting schemes. We test the corresponding BCNN on the Caltech pedestrian dataset in the experiment and observe a significant performance gain over the Fast-RCNN baseline.

In the second topic, a semi-supervised learning method is proposed for pedestrian detection in a domain adaptation setup. The proposed clustered deep representation adaptation (CDRA) method uses a small amount of labeled data to train an intial detector, extracts the deep representation and, then, clusters samples based on the space spanned by the deep representation. A purity measurement mechanism is applied to each cluster to provide a confident score to the estimated class of unlabeled data. Along with a weighted training approach, the CDRA method is shown to achieve the state-of-the-art performance against some large scale datasets.

In the third topic, we propose a new framework called critically-supervised learning that mimics children learing behaviors. Several novel components are proposed to fulfill the high level concept, including negative object proposal, critical example mining, and a machine-guided labeling process based on question answering. A labeling time model is proposed to [...]

By |September 18th, 2017|News|Comments Off on Congratulations to Eddy Wu for Passing His Defense|