News

The 9th Asia Pacific Signal and Information Processing Association (APSIPA) Annual Summit and Conference (ASC), or APSIPA ASC 2017 in short, was held in Kuala Lumpur, Malaysia, from Dec. 11-14, 2017. Research conducted at MCL has received a lot of attention at this conference.
First, MCL Director, Professor C.-C. Jay Kuo was the keynote speaker on December 14. The title of his talk is “Why Deep Learning Networks Work So Well?” His talk was very well attended. He received enthusiastic feedback from the audience. Although deep learning is very hot these days, there is little theoretical justification. Professor Kuo’s keynote provided insights into the working principle behind CNNs and also pointed out ways to improve its shortcomings by introducing the Saak transform.
Second, two MCL papers received honors at the conference. The paper entitled with “Understanding CNN via Deep Feature Analysis” by Hao Xu, Yueru Chen, Ruiyuan Lin and C.-C. Jay Kuo received the best paper award. The poster presentation on “Age/Gender Classification with Whole-Component Convolutional Neural Networks” (by Chun-Ting Huang, Yueru Chen, Ruiyuan Lin and C.-C. Jay Kuo) won the Springer best poster book prize. Both Hao Xu and Chun-Ting Huang were MCL alumni. Hao Xu is currently working at Google while Chun-Ting is a research engineer at Qualcomm.

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.

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.

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) [...]