News

Congratulations to Xiaqing Pan for passing his defense on January 23, 2016. His Ph.D. thesis is entitled “Machine Learning Methods for 2D/3D Shape Retrieval and Classification”.

Abstract of thesis:

Shape classification and retrieval are two important problems in both computer vision and computer graphics. A robust shape analysis contributes to many applications such as manufacture components recognition and retrieval, sketch-based shape retrieval, medical image anaysis, 3D model repository management, etc. In this dissertation, we propose three methods to address three significant problems such as 2D shape retrieval, 3D shape retrieval and 3D shape classification, respectively.

First, in the 2D shape retrieval problem, most state-of-the-art shape retrieval methods are based on local features matching and ranking. Their retrieval performance is not robust since they may retrieve globally dissimilar shapes in high ranks. To overcome this challenge, we decompose the decision process into two stages. In the first irrelevant cluster filtering (ICF) stage, we consider both global and local features and use them to predict the relevance of gallery shapes with respect to the query. Irrelevant shapes are removed from the candidate shape set. After that, a local-features-based matching and ranking (LMR) method follows in the second stage.  We apply the proposed TSR system to three shape datasets: MPEG-7, Kimia99 and Tari1000. We show that TSR outperforms all other existing methods. The robustness of TSR is demonstrated by the retrieval performance.

Second, a novel solution for the content-based 3D shape retrieval problem using an unsupervised clustering approach, which does not need any label information of 3D shapes, is presented.  The proposed shape retrieval system consists of two modules in cascade: the irrelevance filtering (IF) module and the similarity ranking (SR) module. The IF module attempts to cluster gallery shapes that [...]

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) [...]

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 [...]

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.

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 [...]