Databases and Information Systems Commons^™

Dictionary Pair Learning On Grassmann Manifolds For Image Denoising, Xianhua Zeng, Wei Bian, Wei Liu, Jialie Shen, Dacheng Tao

Research Collection School Of Computing and Information Systems

Image denoising is a fundamental problem in computer vision and image processing that holds considerable practical importance for real-world applications. The traditional patch-based and sparse coding-driven image denoising methods convert 2D image patches into 1D vectors for further processing. Thus, these methods inevitably break down the inherent 2D geometric structure of natural images. To overcome this limitation pertaining to the previous image denoising methods, we propose a 2D image denoising model, namely, the dictionary pair learning (DPL) model, and we design a corresponding algorithm called the DPL on the Grassmann-manifold (DPLG) algorithm. The DPLG algorithm first learns an initial dictionary …

E-Classroom For An Underserved Institution, Bhanuprakash Madupati, Kaleem Danish Mohammed, Dilipkumar Pampana

All Capstone Projects

The E-Class Room system is a web based project. An educational institution in India is understaffed and has limited interaction among faculty, student and industry experts. The project is to provide an online platform for the students and faculty of the institution to enhance their educational needs and to share their learning with their fellow students, faculty or industrial experts. It aims to provide a platform for mutual cooperation between different kinds of learning. The new system will provide directional way for online learning between faculty, student and industrial experts.

Face Recognition On Large-Scale Video In The Wild With Hybrid Euclidean-And-Riemannian Metric Learning, Zhiwu Huang, R. Wang, S. Shan, X Chen

Research Collection School Of Computing and Information Systems

Face recognition on large-scale video in the wild is becoming increasingly important due to the ubiquity of video data captured by surveillance cameras, handheld devices, Internet uploads, and other sources. By treating each video as one image set, set-based methods recently have made great success in the field of video-based face recognition. In the wild world, videos often contain extremely complex data variations and thus pose a big challenge of set modeling for set-based methods. In this paper, we propose a novel Hybrid Euclidean-and-Riemannian Metric Learning (HERML) method to fuse multiple statistics of image set. Specifically, we represent each image …

Semi-Supervised Hashing With Semantic Confidence For Large Scale Visual Search, Yingwei Pan, Ting Yao, Houqiang Li, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Similarity search is one of the fundamental problems for large scale multimedia applications. Hashing techniques, as one popular strategy, have been intensively investigated owing to the speed and memory efficiency. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, most existing supervised methods learn hashing function by treating each training example equally while ignoring the different semantic degree related to the label, i.e. semantic confidence, of different examples. In this paper, we propose a novel semi-supervised hashing framework by leveraging semantic confidence. Specifically, a confidence factor is first assigned to each example by neighbor …

State Preserving Extreme Learning Machine For Face Recognition, Md. Zahangir Alom, Paheding Sidike, Vijayan K. Asari, Tarek M. Taha

Electrical and Computer Engineering Faculty Publications

Extreme Learning Machine (ELM) has been introduced as a new algorithm for training single hidden layer feed-forward neural networks (SLFNs) instead of the classical gradient-based algorithms. Based on the consistency property of data, which enforce similar samples to share similar properties, ELM is a biologically inspired learning algorithm with SLFNs that learns much faster with good generalization and performs well in classification applications. However, the random generation of the weight matrix in current ELM based techniques leads to the possibility of unstable outputs in the learning and testing phases. Therefore, we present a novel approach for computing the weight matrix …

Automatic Video Self Modeling For Voice Disorder, Ju Shen, Changpeng Ti, Anusha Raghunathan, Sen-Ching S. Cheung, Rita Patel

Computer Science Faculty Publications

Video self modeling (VSM) is a behavioral intervention technique in which a learner models a target behavior by watching a video of him- or herself. In the field of speech language pathology, the approach of VSM has been successfully used for treatment of language in children with Autism and in individuals with fluency disorder of stuttering. Technical challenges remain in creating VSM contents that depict previously unseen behaviors. In this paper, we propose a novel system that synthesizes new video sequences for VSM treatment of patients with voice disorders. Starting with a video recording of a voice-disorder patient, the proposed …

Log-Euclidean Metric Learning On Symmetric Positive Definite Manifold With Application To Image Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Li, X. Chen

Research Collection School Of Computing and Information Systems

The manifold of Symmetric Positive Definite (SPD) matrices has been successfully used for data representation in image set classification. By endowing the SPD manifold with Log-Euclidean Metric, existing methods typically work on vector-forms of SPD matrix logarithms. This however not only inevitably distorts the geometrical structure of the space of SPD matrix logarithms but also brings low efficiency especially when the dimensionality of SPD matrix is high. To overcome this limitation, we propose a novel metric learning approach to work directly on logarithms of SPD matrices. Specifically, our method aims to learn a tangent map that can directly transform the …

Semi-Supervised Domain Adaptation With Subspace Learning For Visual Recognition, Ting Yao, Yingwei Pan, Chong-Wah Ngo, Houqiang Li, Tao Mei

Research Collection School Of Computing and Information Systems

In many real-world applications, we are often facing the problem of cross domain learning, i.e., to borrow the labeled data or transfer the already learnt knowledge from a source domain to a target domain. However, simply applying existing source data or knowledge may even hurt the performance, especially when the data distribution in the source and target domain is quite different, or there are very few labeled data available in the target domain. This paper proposes a novel domain adaptation framework, named Semi-supervised Domain Adaptation with Subspace Learning (SDASL), which jointly explores invariant lowdimensional structures across domains to correct data …

Face Video Retrieval With Image Query Via Hashing Across Euclidean Space And Riemannian Manifold, Y. Li, R. Wang, Zhiwu Huang, S. Shan, X. Chen

Research Collection School Of Computing and Information Systems

Retrieving videos of a specific person given his/her face image as query becomes more and more appealing for applications like smart movie fast-forwards and suspect searching. It also forms an interesting but challenging computer vision task, as the visual data to match, i.e., still image and video clip are usually represented quite differently. Typically, face image is represented as point (i.e., vector) in Euclidean space, while video clip is seemingly modeled as a point (e.g., covariance matrix) on some particular Riemannian manifold in the light of its recent promising success. It thus incurs a new hashing-based retrieval problem of matching …

Online Multimodal Co-Indexing And Retrieval Of Weakly Labeled Web Image Collections, Lei Meng, Ah-Hwee Tan, Cyril Leung, Liqiang Nie, Tan-Seng Chua, Chunyan Miao

Research Collection School Of Computing and Information Systems

Weak supervisory information of web images, such as captions, tags, and descriptions, make it possible to better understand images at the semantic level. In this paper, we propose a novel online multimodal co-indexing algorithm based on Adaptive Resonance Theory, named OMC-ART, for the automatic co-indexing and retrieval of images using their multimodal information. Compared with existing studies, OMC-ART has several distinct characteristics. First, OMCART is able to perform online learning of sequential data. Second, OMC-ART builds a two-layer indexing structure, in which the first layer co-indexes the images by the key visual and textual features based on the generalized distributions …

Projection Metric Learning On Grassmann Manifold With Application To Video Based Face Recognition, Zhiwu Huang, R. Wang, S. Shan, X. Chen

Research Collection School Of Computing and Information Systems

In video based face recognition, great success has been made by representing videos as linear subspaces, which typically lie in a special type of non-Euclidean space known as Grassmann manifold. To leverage the kernel-based methods developed for Euclidean space, several recent methods have been proposed to embed the Grassmann manifold into a high dimensional Hilbert space by exploiting the well established Project Metric, which can approximate the Riemannian geometry of Grassmann manifold. Nevertheless, they inevitably introduce the drawbacks from traditional kernel-based methods such as implicit map and high computational cost to the Grassmann manifold. To overcome such limitations, we propose …

Multimodal Learning With Deep Boltzmann Machine For Emotion Prediction In User Generated Videos, Lei Pang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Detecting emotions from user-generated videos, such as“anger” and “sadness”, has attracted widespread interest recently. The problem is challenging as effectively representing video data with multi-view information (e.g., audio, video or text) is not trivial. In contrast to the existing works that extract features from each modality (view) separately followed by early or late fusion, we propose to learn a joint density model over the space of multi-modal inputs (including visual, auditory and textual modalities) with Deep Boltzmann Machine (DBM). The model is trained directly on the user-generated Web videos without any labeling effort. More importantly, the deep architecture enlightens the …

Compression Of Video Tracking And Bandwidth Balancing Routing In Wireless Multimedia Sensor Networks, Yin Wang, Jianjun Yang, Ju Shen, Bryson Payne, Juan Guo, Kun Hua

Computer Science Faculty Publications

There has been a tremendous growth in multimedia applications over wireless networks. Wireless Multimedia Sensor Networks(WMSNs) have become the premier choice in many research communities and industry. Many state-of-art applications, such as surveillance, traffic monitoring, and remote heath care are essentially video tracking and transmission in WMSNs. The transmission speed is constrained by the big file size of video data and fixed bandwidth allocation in constant routing paths. In this paper, we present a CamShift based algorithm to compress the tracking of videos. Then we propose a bandwidth balancing strategy in which each sensor node is able to dynamically select …

Design, Programming, And User-Experience, Kaila G. Manca

Honors Scholar Theses

This thesis is a culmination of my individualized major in Human-Computer Interaction. As such, it showcases my knowledge of design, computer engineering, user-experience research, and puts into practice my background in psychology, com- munications, and neuroscience.

I provided full-service design and development for a web application to be used by the Digital Media and Design Department and their students.This process involved several iterations of user-experience research, testing, concepting, branding and strategy, ideation, and design. It lead to two products.

The first product is full-scale development and optimization of the web appli- cation.The web application adheres to best practices. It was …

Recipe Suggestion Tool, Tejaswi Patha, Deepika Sandhadi

All Capstone Projects

There is currently a great need for a tool to search cooking recipes based on ingredients, country and recipe type. Current search engines do not provide this feature. Most of the recipe search results in current websites are not efficiently clustered based on relevance or categories resulting in a user getting lost in the huge search results presented. They also do not provide links to view images of the ingredients of a recipe.

My project aims to combine the features like search based on ingredients, suggestions for similar recipes, and images for the ingredients under one search engine and provide …

Leading Undergraduate Students To Big Data Generation, Jianjun Yang, Ju Shen

Computer Science Faculty Publications

People are facing a flood of data today. Data are being collected at unprecedented scale in many areas, such as networking, image processing, virtualization, scientific computation, and algorithms. The huge data nowadays are called Big Data. Big data is an all encompassing term for any collection of data sets so large and complex that it becomes difficult to process them using traditional data processing applications. In this article, the authors present a unique way which uses network simulator and tools of image processing to train students abilities to learn, analyze, manipulate, and apply Big Data. Thus they develop students hands-on …

Hole Detection And Shape-Free Representation And Double Landmarks Based Geographic Routing In Wireless Sensor Networks, Jianjun Yang, Zongming Fei, Ju Shen

Computer Science Faculty Publications

In wireless sensor networks, an important issue of geographic routing is “local minimum” problem, which is caused by a “hole” that blocks the greedy forwarding process. Existing geographic routing algorithms use perimeter routing strategies to find a long detour path when such a situation occurs. To avoid the long detour path, recent research focuses on detecting the hole in advance, then the nodes located on the boundary of the hole advertise the hole information to the nodes near the hole. Hence the long detour path can be avoided in future routing. We propose a heuristic hole detecting algorithm which identifies …

Metalogic Notes, Saverio Perugini

Computer Science Working Papers

A collection of notes, formulas, theorems, postulates and terminology in symbolic logic, syntactic notions, semantic notions, linkages between syntax and semantics, soundness and completeness, quantified logic, first-order theories, Goedel's First Incompleteness Theorem and more.

Statistics Notes, Saverio Perugini

Computer Science Working Papers

A collection of terms, definitions, formulas and explanations about statistics.

Interpretative Phenomenological Analysis Of Accessibility Awareness Among Faculty In Online Learning Environments, Rachael Sessler Trinkowsky

CCAC Theses and Dissertations

Although all organizations and institutions should consider accessibility when developing online content, inaccessibility is a recurring issue in recent literature pertaining to online learning environments (OLEs) and faculty accessibility awareness. The goal was to describe how online faculty gain knowledge regarding accessibility, to explore the lived experiences of online faculty who have worked with students who have disabilities, and to gain a better understanding of how faculty experience the process of accessibility implementation. The following research questions guided this study: How do faculty in OLEs experience encounters regarding accessibility for students who have print related disabilities? How do faculty in …

A Content-Sensitive Wiki Help System, Eswara Satya Pavan Rajesh Pinapala

Master's Projects

Context-sensitive help is a software application component that enables users to open help pertaining to their state, location, or the action they are performing within the software. Context-sensitive “wiki” help, on the other hand, is help powered by a wiki system with all the features of context-sensitive help. A context-sensitive wiki help system aims to make the context-sensitive help collaborative; in addition to seeking help, users can directly contribute to the help system. I have implemented a context-sensitive wiki help system into Yioop, an open source search engine and software portal created by Dr. Chris Pollett, in order to measure …

Combining Multiple Kernel Methods On Riemannian Manifold For Emotion Recognition In The Wild, M. Liu, R. Wang, S. Li, S. Shan, Zhiwu Huang, X. Chen

Research Collection School Of Computing and Information Systems

In this paper, we present the method for our submission to the Emotion Recognition in the Wild Challenge (EmotiW 2014). The challenge is to automatically classify the emotions acted by human subjects in video clips under realworld environment. In our method, each video clip can be represented by three types of image set models (i.e. linear subspace, covariance matrix, and Gaussian distribution) respectively, which can all be viewed as points residing on some Riemannian manifolds. Then different Riemannian kernels are employed on these set models correspondingly for similarity/distance measurement. For classification, three types of classifiers, i.e. kernel SVM, logistic regression, …

Hybrid Euclidean-And-Riemannian Metric Learning For Image Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Chen

Research Collection School Of Computing and Information Systems

We propose a novel hybrid metric learning approach to combine multiple heterogenous statistics for robust image set classification. Specifically, we represent each set with multiple statistics – mean, covariance matrix and Gaussian distribution, which generally complement each other for set modeling. However, it is not trivial to fuse them since the mean vector with dd-dimension often lies in Euclidean space RdRd, whereas the covariance matrix typically resides on Riemannian manifold Sym+dSymd+. Besides, according to information geometry, the space of Gaussian distribution can be embedded into another Riemannian manifold Sym+d+1Symd+1+. To fuse these statistics from heterogeneous spaces, we propose a Hybrid …

Celelabel: An Interactive System For Annotating Celebrities In Web Videos, Zhineng Chen, Jinfeng Bai, Chong-Wah Ngo, Bailan Feng, Bo Xu

Research Collection School Of Computing and Information Systems

Manual annotation of celebrities in Web videos is an essential task in many people-related Web services. The task, however, poses a significant challenge even to skillful annotators, mainly due to the large quantity of unfamiliar and greatly varied celebrities, and the lack of a customized system for it. This work develops CeleLabel, an interactive system for manually annotating celebrities in the Web video domain. The peculiarity of CeleLabel is to exploit and display multiple types of information that could assist the annotation, including video content, context surrounding and within a video, celebrity images on the Web, and human factors. Using …

Scalable Visual Instance Mining With Threads Of Features, Wei Zhang, Hongzhi Li, Chong-Wah Ngo, Shih-Fu Chang

Research Collection School Of Computing and Information Systems

We address the problem of visual instance mining, which is to extract frequently appearing visual instances automatically from a multimedia collection. We propose a scalable mining method by exploiting Thread of Features (ToF). Specifically, ToF, a compact representation that links consistent features across images, is extracted to reduce noises, discover patterns, and speed up processing. Various instances, especially small ones, can be discovered by exploiting correlated ToFs. Our approach is significantly more effective than other methods in mining small instances. At the same time, it is also more efficient by requiring much fewer hash tables. We compared with several state-of-the-art …

Click-Through-Based Subspace Learning For Image Search, Yingwei Pan, Ting Yao, Xinmei Tian, Houqiang Li, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

One of the fundamental problems in image search is to rank image documents according to a given textual query. We address two limitations of the existing image search engines in this paper. First, there is no straightforward way of comparing textual keywords with visual image content. Image search engines therefore highly depend on the surrounding texts, which are often noisy or too few to accurately describe the image content. Second, ranking functions are trained on query-image pairs labeled by human labelers, making the annotation intellectually expensive and thus cannot be scaled up. We demonstrate that the above two fundamental challenges …

Structure Preserving Large Imagery Reconstruction, Ju Shen, Jianjun Yang, Sami Taha Abu Sneineh, Bryson Payne, Markus Hitz

Computer Science Faculty Publications

With the explosive growth of web-based cameras and mobile devices, billions of photographs are uploaded to the internet. We can trivially collect a huge number of photo streams for various goals, such as image clustering, 3D scene reconstruction, and other big data applications. However, such tasks are not easy due to the fact the retrieved photos can have large variations in their view perspectives, resolutions, lighting, noises, and distortions. Furthermore, with the occlusion of unexpected objects like people, vehicles, it is even more challenging to find feature correspondences and reconstruct realistic scenes. In this paper, we propose a structure-based image …

Gamification Of Education: A Review Of Literature, Fiona Fui-Hoon Nah, Qing Zeng, Venkata R. Telaprolu, Abhishek Padmanabhuni Ayyappa, Brenda Eschenbrenner

Research Collection School Of Computing and Information Systems

We synthesized the literature on gamification of education by conducting a review of the literature on gamification in the educational and learning context. Based on our review, we identified several game design elements that are used in education. These game design elements include points, levels/stages, badges, leaderboards, prizes, progress bars, storyline, and feedback. We provided examples from the literature to illustrate the application of gamification in the educational context.

Learning Euclidean-To-Riemannian Metric For Point-To-Set Classification, Zhiwu Huang, R. Wang, S. Shan, X. Chen

Research Collection School Of Computing and Information Systems

In this paper, we focus on the problem of point-to-set classification, where single points are matched against sets of correlated points. Since the points commonly lie in Euclidean space while the sets are typically modeled as elements on Riemannian manifold, they can be treated as Euclidean points and Riemannian points respectively. To learn a metric between the heterogeneous points, we propose a novel Euclidean-to-Riemannian metric learning framework. Specifically, by exploiting typical Riemannian metrics, the Riemannian manifold is first embedded into a high dimensional Hilbert space to reduce the gaps between the heterogeneous spaces and meanwhile respect the Riemannian geometry of …

Institutional Boundaries And Trust Of Virtual Teams In Collaborative Design: An Experimental Study In A Virtual World Environment, Shu Z. Schiller, Brian Mennecke, Fiona Fui-Hoon Nah, Andy Luse

Research Collection School Of Computing and Information Systems

Members of virtual teams often collaborate within and across institutional boundaries. This research investigates the effects of boundary spanning conditions on the development of team trust and team satisfaction. Two hundred and eighty-two participants carried out a collaborative design task over several weeks in a virtual world, Second Life. Multigroup structural equation modeling was used to examine our research model, which compares individual level measurement between two boundary spanning team conditions. The results indicate that trusting beliefs have a positive impact on team trust, which in turn, influences team satisfaction. Further, we found that, compared to cross-boundary teams, within-boundary teams …