ruiyuanlin

  • Permalink Gallery

    Congratulations to Qin Huang for Passing His Qualifying Exam

Congratulations to Qin Huang for Passing His Qualifying Exam

Congratulations to Qin Huang for passing his Qualifying Exam on January 18, 2016. The title of his Ph.D. thesis proposal is “Machine Learning Techniques for Perceptual Quality Enhancement and Semantic Image Segmentation”. His qualifying exam committee consisted of Jay Kuo (Chair), Antonio Ortega, Justin Haldar, Sandy Sawchuk and Cyrus Shahabi (Outside Member).

Abstract of thesis proposal:

Researches on image processing and computer vision problems can be generally divided into two major steps: extracting powerful feature representations and designing efficient decision system. Traditional methods rely on hand-craft features, as well as pre-defined thresholds to generate a necessary condition required for the desired target. A more robust system could be designed taking advantage of machine learning techniques if enough training samples are provided. Thanks to the development of big data, millions of image and video contents are now available for training. To better utilize the information in the training, convolutional neural network based deep learning systems become popular in recent years. Specifically, the CNN based methods demonstrate better ability to acquire powerful feature representations in a simultaneous way. However, CNN based training has a high requirement of hardware and subtle process design. And therefore it should be carefully explored in order to obtain desired results.

In this proposal, we contribute to three works that gradually develop from the traditional method to deep learning based method. Based on the applications, the works can be divided into two major categories: perceptual quality enhancement and semantic image segmentation. In the first part, we focus on enhancing the quality of images and videos by considering related perceptual properties of human visual system. To begin with, we deal with a type of compression artifacts referred to as “false contour”. We then focus on the visual experience [...]

By |January 22nd, 2017|News|Comments Off on Congratulations to Qin Huang for Passing His Qualifying Exam|
  • Permalink Gallery

    Congratulations to Chun-Ting Huang for Passing His PhD Defense

Congratulations to Chun-Ting Huang for Passing His PhD Defense

Congratulations to Chun-Ting Huang for passing his defense on January 18, 2016. His Ph.D. thesis is entitled “Facial Identity Recognition and Attribute Classification Using Machine Learning Techniques”.

Abstract of thesis:

Robust face recognition plays a central role in biometric and surveillance applications.  Although the subject has been studied for about four decades, there still exist quite a few technical challenges and system design issues in deploying it in a real-world video surveillance environment.  Nowadays, the raw face images and their associated meta data are stored in a remote cloud storage system in a distributed face recognition platform.  One key challenge in the overall system design is to ensure the security of stored data. In this research, we first conduct a survey on this technology and then, study the problems of cross-distance/environment face recognition and facial attribute classification with machine learning techniques.

The problem of long distance face recognition and attribute classification arising from surveillance applications impose major challenges. The captured face from the surveillance system can be low resolution and quality, which is further degraded by an uncontrolled outdoor environment such as long distance during daytime or nighttime. In addition, human age/gender inferred by face images are fundamental attributes in our social interactions. This research has many applications such as demographics analysis, commercial user management, visual surveillance, and even aging progression. Despite the rapid development in automatic face recognition, there is far less work on automatic age/gender classification in an unconstrained environment.

Research in this dissertation provides effective solutions to three topics: 1) cross-distance/environment face recognition, 2) cross-distance/spectral face recognition and 3) age/gender classification.  For Topic 1, a two-stage alignment/enhancement filtering (TAEF) method is proposed to achieve the state-of-the-art performance.  For Topic 2, a locally linear embedding (LLE) [...]

By |January 19th, 2017|News|Comments Off on Congratulations to Chun-Ting Huang for Passing His PhD Defense|

Congratulations to Eddy Wu for Passing His Qualifying Exam

Congratulations to Eddy Wu for passing his Qualifying Exam on January 13, 2016. The title of his Ph.D. thesis proposal is “Deep Learning Techniques for Supervised and Semi-Supervised Pedestrian Detection”. His qualifying exam committee consisted of Jay Kuo (Chair), Sandy Sawchuk, Richard Leahy, Justin Haldar and Aiichiro Nakano (Outside Member).

Abstract of thesis proposal:

With the emergence of autonomous driving and the advanced driver assistance system (ADAS), the importance of pedestrian detection has increased significantly. A lot of research work has been conducted to tackle this problem with the availability of large-scale datasets. Methods based on the convolutional neural network (CNN) technology have achieved great success in pedestrian detection in recent years, which offers a giant step to the solution of this problem.  Although the performance of CNN-based solutions reaches a significantly higher level than traditional methods, it is still far from perfection. Further advancement in this field is still demanded. In this proposal, we conducted two research topics along this direction.

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. A weighting scheme is designed for each of them. Finally, we train a boosted fusion layer to benefit from the integration of these two weighting schemes. We use the Fast-RCNN as the baseline and test the corresponding BCNN on the Caltech pedestrian dataset in the experiment and observe a significant performance gain of the BCNN over its baseline.

Data-driven pedestrian detection methods demand [...]

By |January 15th, 2017|News|Comments Off on Congratulations to Eddy Wu for Passing His Qualifying Exam|
  • Permalink Gallery

    Congratulations to Weihao Gan for Passing His Qualifying Exam

Congratulations to Weihao Gan for Passing His Qualifying Exam

Congratulations to Weihao Gan for passing his qualifying exam on January 11, 2016. The title of his Ph.D. thesis proposal is “Advanced Online Object Tracking Techniques by Exploiting Spatial and Temporal Information”. His qualifying exam committee consisted of Jay Kuo, Antonio Ortega, Keith Chugg, Panayiotis Georgiou and Ulrich Neumann.

Abstract of thesis proposal:

Online object tracking is one of the fundamental computer vision problems. It is commonly used in real world applications such as traffic control 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 attempt to achieve online object tracking using both spatial and temporal cues with two novel methods.

First, we develop a new method, called the “temporal prediction and spatial refinement (TPSR)” tracker, to integrate spatial and temporal cues effectively. The TPSR tracking system consists of three cascaded modules: pre-processing (PP), temporal prediction (TP) and spatial refinement (SR). Illumination variation and shaking camera movement are two challenging factors in a tracking problem. They are compensated in the PP module. Then, a joint region-based template matching (TM) and pixel-wised optical flow (OF) scheme is adopted in the TP module, where the switch between TM and OF is conducted automatically. These two modes work in a complementary manner to handle different foreground and background situations. Finally, to overcome the drifting error arising from the TP module, the bounding box location and size are finetuned using the local spatial information of the new frame in the SR module.

Next, we apply the deep neural network architecture to the online object tracking problem. We have made several major improvements on the state-of-the-art multi- domain network (MDNet) tracker. The enhanced MDNet (EMDNet) tracker not [...]

By |January 12th, 2017|News|Comments Off on Congratulations to Weihao Gan for Passing His Qualifying Exam|

MCL Releases VideoSet in IEEE DataPort

The MCL joined a collaborative project to build a large-scale subjective video quality database. The database was proposed to boost a major breakthrough in video coding and processing. It consists of 220 5-second sequences in four resolutions (i.e., 1920×1080, 1280×720, 960×540 and 640×360). For each of the 880 video clips, we encoded it using the H.264 codec and conducted a large-scale subjective test on the perceptual quality. The dataset is called the “VideoSet”, which is an acronym for “Video Subject Evaluation Test (SET)”. The database are available to the public in the IEEE DataPort.

IEEE DataPort is a valuable and universally accessible repository of datasets serving the growing data needs in both research and industry. The repository is designed to accept all types of datasets, including Big Data datasets up to 2TB, and it provides both downloading capabilities and access to Cloud services to enable data analysis in the Cloud.

We appreciate the help from Dr. K. J. Ray Liu and Melissa Handa in hosting the VidoeSet database.

By |January 8th, 2017|News|Comments Off on MCL Releases VideoSet in IEEE DataPort|

Happy New Year – 2017

2016 has been a fruitful year for MCL. Some members graduated with impressive research work and began a new chapter of life. Some new students joined the MCL family and explored the joy of research. MCL members have made great efforts on their research and published quality research papers on top journals and conferences.

Wish all MCL members a happy new year.

Image credits: Photo 1: “Happy New Year” by maf04, used under CC BY-SA 2.0 / Resized with white padding on the borders; Photo 2: “New Years 2017” by maf04, used under CC BY-SA 2.0 / Resized with black padding on the borders.

By |January 1st, 2017|News|Comments Off on Happy New Year – 2017|

Congratulations to MCL Members for Passing Screening Exams

MCL members, Heming Zhang, Junting Zhang and Yueru Chen passed the screening exam in Fall 2016. The screening exam is an important examination during PhD study, which aims to estimate the research potential of the student. In the area of Signal and Image Processing, the screening exam includes four topics: applied linear algebra, digital signal processing, probability and random processes.

Congratulations to Heming, Junting and Yueru. We wish them all the best in their future research and PhD study.

By |December 25th, 2016|News|Comments Off on Congratulations to MCL Members for Passing Screening Exams|

Congratulations to Shangwen Li for Passing PhD Defense

Congratulations to Shangwen Li for passing his defense on December 1, 2016. His Ph.D. thesis is entitled “Multimodal Image Retrieval and Object Classification Using Deep Learning Features”.

Abstract of thesis:

Computer vision has achieved a major breakthrough in recent years with the advancement of deep learning based methods. However, its performance is still yet to be claimed as robust for practical applications, and more advanced methods on top of deep learning architecture are needed. This work targets at using deep learning features to tackle two major computer vision problems: Multimodal Image Retrieval and Object Classification.

Multimodal Image Retrieval (MIR) aims at building the alignment between the visual and textual modalities, thus reduce the well-known “semantic gap” in image retrieval problem. As the most widely existing textual information of images, tag plays an important semantic role in MIR framework. However, treating all tags in an image as equally important may result in misalignment between visual and textual domains, leading to bad retrieval performance. To address this problem and build a robust retrieval system, we propose an MIR framework that embeds tag importance as the textual feature. In the first part, we propose an MIR system, called Multimodal Image Retrieval with Tag Importance Prediction (MIR/TIP), to embed the automatically predicted object tag importance in image retrieval. To achieve this goal, a discounted probability metric is first presented to measure the object tag importance from human sentence descriptions. Using this as ground truth, a structured object tag importance prediction model is proposed. The proposed model integrates visual, semantic, and context cues to achieve robust object tag importance prediction performance. Our experimental results demonstrate that, by embedding the predicted object tag importance, significant performance gain can be obtained in terms of [...]

By |December 18th, 2016|News|Comments Off on Congratulations to Shangwen Li for Passing PhD Defense|

Congratulations to Chen Chen for Passing PhD Defense

Congratulations to Chen Chen for passing his defense on November 30, 2016. His Ph.D. thesis is entitled “Large-Scale Scene Classification Using Machine Learning Techniques”.

Abstract of thesis:

This thesis focuses on solving a general “scene image classification” problem using advanced machine learning techniques. Indoor/outdoor classification, outdoor background semantic segmentation for image classification, and exploration of scene class/image confusion are studied in the thesis. Unlike traditional solutions to the long-standing problems, the research works proposed several innovative machine learning-based approach to resolve the challenges from different angles. Most of the proposed approaches provide the state-of-the-art performance which are highly appreciated in corresponding field of research.

We are so glad to have him share his Ph.D. experience with us. Here is his sharing.

Ph.D. experience:

Having a Ph.D. is definitely not an easy process. I was lucky to have Prof. Kuo as my advisor/leader/team member in this process. He cared me as child of his own and provided huge amount patience and love in this process. So the PhD study was not as hard as I had heard from other friends of mine. Besides, I learned to be humble, diligent, caring and taking responsibility in this process. I acknowledge my lab mates, my wife and my cats for the lasting support in my life to gain such a huge transformation in my life.

Congratulations again to Chen and we wish him all the best in his career in Facebook.

By |December 11th, 2016|News|Comments Off on Congratulations to Chen Chen for Passing PhD Defense|

MCL Celebrated Thanksgiving Holiday

Thanksgiving luncheon, which has always been a tradition of MCL, was held on December 3, 2016. More than 30 MCL members and their families attended the luncheon. The atmosphere was joyful and we enjoyed the food and conversation with each other. “It has been a long time that I haven’t tasted good Chinese food since I arrived in LA. I would like to thank Professor Kuo for treating us to such a good luncheon,” said Professor Xin Zhou. “The atmosphere is so joyful. I enjoyed the casual chats with others,” said Anubhuti.

Though most of the MCL members are international students and did not get to spend Thanksgiving with their families. We were so happy to celebrate Thanksgiving with other MCL members as a big family.

By |December 7th, 2016|News|Comments Off on MCL Celebrated Thanksgiving Holiday|