Physical Sciences and Mathematics Commons^™

Head-Pose Tracking With A Time-Of-Flight Camera, Simon Meers, Koren Ward

Faculty of Informatics - Papers (Archive)

Intelligent interfaces that make use of the user's head pose or facial features in order to interpret the user's identity or point of attention, are finding increasing application in numerous fields. Although various techniques exist to passively track the user's gaze or head pose using monocular or stereo cameras, these systems generally cannot perceive in detail the characteristic three-dimensional (3D) profile of the user's head or face. Time-of-flight cameras, such as the Swiss Ranger SR-3000, are a recent innovation capable of providing three-dimensional image data from a single sensor. The advent of such sensors opens up new possibilities in the …

On Static And Dynamic Partitioning Behavior Of Large-Scale Networks, Zhongmei Yao, Derek Leonard, Xiaoming Wang, Dmitri Loguinov

Computer Science Faculty Publications

In this paper, we analyze the problem of network disconnection in the context of large-scale P2P networks and understand how both static and dynamic patterns of node failure affect the resilience of such graphs. We start by applying classical results from random graph theory to show that a large variety of deterministic and random P2P graphs almost surely (i.e., with probability 1 − o(1)) remain connected under random failure if and only if they have no isolated nodes. This simple, yet powerful, result subsequently allows us to derive in closed-form the probability that a P2P network develops isolated nodes, and …

Cognitive Agents Integrating Rules And Reinforcement Learning For Context-Aware Decision Support, Teck-Hou Teng, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

While context-awareness has been found to be effective for decision support in complex domains, most of such decision support systems are hard-coded, incurring significant development efforts. To ease the knowledge acquisition bottleneck, this paper presents a class of cognitive agents based on self-organizing neural model known as TD-FALCON that integrates rules and learning for supporting context-aware decision making. Besides the ability to incorporate a priori knowledge in the form of symbolic propositional rules, TD-FALCON performs reinforcement learning (RL), enabling knowledge refinement and expansion through the interaction with its environment. The efficacy of the developed Context-Aware Decision Support (CaDS) system is …

Beyond Semantic Search: What You Observe May Not Be What You Think, Chong-Wah Ngo, Yu-Gang Jiang, Xiaoyong Wei, Wanlei Zhao, Feng Wang, Xiao Wu, Hung-Khoon Tan

Research Collection School Of Computing and Information Systems

This paper presents our approaches and results of the four TRECVID 2008 tasks we participated in: high-level feature extraction, automatic video search, video copy detection, and rushes summarization

A Review Of Mobile-Based Initiatives Across College, Daniel Okunbor, Retta Guy

Math and Computer Science Faculty Working Papers

The information era in which we currently live is changing the culture of education. The use of information technologies has resulted in new opportunities that are rapidly evolving to include mobile learning. Keegan (2002) characterizes this evolution of distance learning as a shift from d-learning (distance) to e-learning (electronic) to m-learning (mobile) learning.

Mobile, wireless, and handheld technologies are being used to re-enact approaches and solutions to teaching and learning used in traditional and web-based formats. The goal of mobile learning is to provide opportunities for students to interact through computer-supported learning environments from mobile terminals with low speed wireless …

What A User Wants: Redesigning A Library's Web Site Based On A Card-Sort Analysis, Laura Pope Robbins, Lisa Esposito, Christ Kretz, Michael Aloi

Publications

Web site usability concerns anyone with a web site to maintain. Libraries, however, are often the biggest offenders in terms of usability. In our efforts to provide users with everything they need to do research, we often overwhelm them with sites that are confusing in structure, difficult to navigate, and weighed down with jargon. Dowling College Library recently completed a redesign of its web site based upon the concept of usability. For smaller libraries in particular, this can be a challenge. The web site is often maintained by one or two people and finding the time and resources to conduct …

Structuring Low-Quality Videotaped Lectures For Cross-Reference Browsing By Video Text Analysis, Feng Wang, Chong-Wah Ngo, Ting-Chuen Pong

Research Collection School Of Computing and Information Systems

This paper presents an unified approach in analyzing and Structuring the content of videotaped lectures for distance learning applications. By Structuring lecture videos, we can Support topic indexing and semantic querying of multimedia documents captured in the traditional classrooms. Our goal in this paper is to automatically construct the cross references of lecture videos and textual documents so as to facilitate the synchronized browsing and presentation of multimedia information. The major issues involved in our approach are topical event detection, video text analysis and the matching of slide shots and external documents. In topical event detection, a novel transition detector …

An Exploratory Overview Of Teaching Computer Game Development, Mario Guimaraes, Meg C. Murray

Faculty and Research Publications

The computer game industry has exploded reaching sales of several billion dollars a year and, consequently, a majority of college students are familiar with the gaming environment. In fact, videogame development has been cited as one way to motivate students to explore the world of Computer Science. However, most videogames are extremely complex computer programs created by a team of developers including programmers and graphic artists and represent thousands of hours of work. Fortunately there are software tools available that provide a way for simple computer games to be created fairly easily using a building block approach. This paper discusses …

Selection Of Concept Detectors For Video Search By Ontology-Enriched Semantic Spaces, Xiao-Yong Wei, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

This paper describes the construction and utilization of two novel semantic spaces, namely Ontology-enriched Semantic Space (OSS) and Ontology-enriched Orthogonal Semantic Space (OS2), to facilitate the selection of concept detectors for video search. These two semantic spaces are enriched with ontology knowledge, while emphasizing consistent and uniform comparison of ontological relatedness among concepts for query-to-concept mapping. OS2, in addition to being a linear space like OSS, also guarantees orthogonality of the semantic space. Compared with other ontology reasoning measures, both spaces are capable of providing platforms that offer a global view of concept inter-relatedness, by allowing evaluation of concept similarity …

Accelerating Near-Duplicate Video Matching By Combining Visual Similarity And Alignment Distortion, Hung-Khoon Tan, Xiao Wu, Chong-Wah Ngo, Wan-Lei Zhao

Research Collection School Of Computing and Information Systems

In this paper, we investigate a novel approach to accelerate the matching of two video clips by exploiting the temporal coherence property inherent in the keyframe sequence of a video. Motivated by the fact that keyframe correspondences between near-duplicate videos typically follow certain spatial arrangements, such property could be employed to guide the alignment of two keyframe sequences. We set the alignment problem as an integer quadratic programming problem, where the cost function takes into account both the visual similarity of the corresponding keyframes as well as the alignment distortion among the set of correspondences. The set of keyframe-pairs found …

Ontology-Based Visual Word Matching For Near-Duplicate Retrieval, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper proposes a novel approach to exploit the ontological relationship of visual words by linguistic reasoning. A visual word ontology is constructed to facilitate the rigorous evaluation of linguistic similarity across visual words. The linguistic similarity measurement enables cross-bin matching of visual words, compromising the effectiveness and speed of conventional keypoint matching and bag-of-word approaches. A constraint EMD is proposed and experimented to efficiently match visual words. Empirical findings indicate that the proposed approach offers satisfactory performance to near-duplicate retrieval, while still enjoying the merit of speed efficiency compared with other techniques.

Video Event Detection Using Motion Relativity And Visual Relatedness, Feng Wang, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Event detection plays an essential role in video content analysis. However, the existing features are still weak in event detection because: i) most features just capture what is involved in an event or how the event evolves separately, and thus cannot completely describe the event; ii) to capture event evolution information, only motion distribution over the whole frame is used which proves to be noisy in unconstrained videos; iii) the estimated object motion is usually distorted by camera movement. To cope with these problems, in this paper, we propose a new motion feature, namely Expanded Relative Motion Histogram of Bag-ofVisual-Words …

Simulating A Smartboard By Real-Time Gesture Detection In Lecture Videos, Feng Wang, Chong-Wah Ngo, Ting-Chuen Pong

Research Collection School Of Computing and Information Systems

Gesture plays an important role for recognizing lecture activities in video content analysis. In this paper, we propose a real-time gesture detection algorithm by integrating cues from visual, speech and electronic slides. In contrast to the conventional "complete gesture" recognition, we emphasize detection by the prediction from "incomplete gesture". Specifically, intentional gestures are predicted by the modified hidden Markov model (HMM) which can recognize incomplete gestures before the whole gesture paths are observed. The multimodal correspondence between speech and gesture is exploited to increase the accuracy and responsiveness of gesture detection. In lecture presentation, this algorithm enables the on-the-fly editing …

Matlab Report, Nancy Hale

Cornerstone 3 Reports : Interdisciplinary Informatics

The objective of this effort is to create a multidisciplinary approach to problem solving using technology. Through Thinkfinity, the Seidenberg School of Computer Science and Information Systems is collaborating with the science and quantitative faculty to create lessons that can be used by high school and first -year college students to work interactively with data to solve problems. MatLab is the tool of choice. It gives the user the ability to create visual models of large data sets and is used in the science and finance areas.

The key features of MatLab:

• Interactive tools for iterative exploration, design, and …

Bag-Of-Visual-Words Expansion Using Visual Relatedness For Video Indexing, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Bag-of-visual-words (BoW) has been popular for visual classification in recent years. In this paper, we propose a novel BoW expansion method to alleviate the effect of visual word correlation problem. We achieve this by diffusing the weights of visual words in BoW based on visual word relatedness, which is rigorously defined within a visual ontology. The proposed method is tested in video indexing experiment on TRECVID-2006 video retrieval benchmark, and an improvement of 7% over the traditional BoW is reported.

Measuring Novelty And Redundancy With Multiple Modalities In Cross-Lingual Broadcast News, Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

News videos from different channels, languages are broadcast everyday, which provide abundant information for users. To effectively search, retrieve, browse and track news stories, news story similarity plays a critical role in assessing the novelty and redundancy among news stories. In this paper, we explore different measures of novelty and redundancy detection for cross-lingual news stories. A news story is represented by multimodal features which include a sequence of keyframes in the visual track, and a set of words and named entities extracted from speech transcript in the audio track. Vector space models and language models on individual features (text, …

An Application Of High Fidelity Ftds For Ab Initio Pilot Training: The Way Ahead, Nickolas D. Macchiarella, Tim Brady, Brandon S. Lyon

Publications

"Decreases in simulation costs and increases in aircraft training costs led to the need for further investigation into the application of simulation-based training. Researchers conducted an eighteen-month study using ab initio student pilots as participants. This study applied a Federal Aviation Administration (FAA) approved, Part 142, flight-training curriculum that included 60% flight training device (FTD) use. Researchers identified five causal factors that warranted further investigation. The causal factors identified were visual fidelity, procedural similarity, dynamic flight environment, difficulty of task, and visual scanning and response. These causal factors have the potential to affect transfer of training (ToT) from simulated flight …

Multimodal News Story Clustering With Pairwise Visual Near-Duplicate Constraint, Xiao Wu, Chong-Wah Ngo, Alexander G. Hauptmann

Research Collection School Of Computing and Information Systems

Story clustering is a critical step for news retrieval, topic mining, and summarization. Nonetheless, the task remains highly challenging owing to the fact that news topics exhibit clusters of varying densities, shapes, and sizes. Traditional algorithms are found to be ineffective in mining these types of clusters. This paper offers a new perspective by exploring the pairwise visual cues deriving from near-duplicate keyframes (NDK) for constraint-based clustering. We propose a constraint-driven co-clustering algorithm (CCC), which utilizes the near-duplicate constraints built on top of text, to mine topic-related stories and the outliers. With CCC, the duality between stories and their underlying …

Anatomy Of An Arabetic Type Design, Saad D. Abulhab

Publications and Research

Arabetic type design, like type design in general, should not be limited by rigid rules, other than those advocating open choice and user options. But as with all design fields, highlighting certain principles and guidelines is crucial to realizing a successful project. In an Arabetic font design environment, such guidelines and principles should reveal deeper understanding of various scripts visual and behavioral defining characteristics rather than mere traditional calligraphic and handwriting norms. A main goal of this study is to emphasize that designing Arabetic fonts is much easier than it is portrayed, and designers of all backgrounds should be more …

Help-Based Tutorials, David G. Novick, Oscar D. Andrade, Nathaniel Bean, Edith Elizalde

Departmental Papers (CS)

The consensus of the documentation literature is that users rarely use help, usually preferring to muddle through. To increase use of help, tutorials for novice users could be changed from guided presentations toward using the system’s actual help system. To determine whether this approach would increase users’ use of help when they encountered problems with an application, we developed an alternative, help-based tutorial introduction to Microsoft Publisher. We compared the behaviors of users introduced to Publisher with the help-based tutorial with the behaviors of users who learned from a traditional tutorial. A balanced study of 22 novice users of Publisher …

Simple, Robust And Accurate Head-Pose Tracking Using A Single Camera, S. Meers, Koren Ward, I. Piper

Faculty of Informatics - Papers (Archive)

This paper describes an inexpensive, robust method for tracking the head position and orientation of the user by using a single low-cost USB camera and infrared light emitting diodes concealed within spectacle frames worn by the user. Unlike gaze and head-pose tracking systems which rely on high-resolution stereo cameras and complex image processing hardware and software to find and track facial features on the user, the proposed system is able to efficiently locate and track the head's orientation and distance relative to the camera with little processing. Due to the infrared light emitting diodes having fixed geometry, the system does …

Designing Search: Effective Search Interfaces For Academic Library Websites, Susan Teague Rector, Jimmy Ghaphery

VCU Libraries Faculty and Staff Publications

Academic libraries customize, support and provide access to myriad information systems, each with complex graphical user interfaces (GUIs). The number of possible information entry points on an academic library Web site is both daunting to the end user and consistently challenging to library Web site designers. Faced with the challenges inherent in designing online search interfaces and the ever-growing amount of resources available online, VCU Libraries sought to explore how to build effective search interfaces that, at the same time, support a wide variety of computer users and provide comprehensive access to assorted collections of electronic resources. Over a 9 …

Set Linear Algebra And Set Fuzzy Linear Algebra, Florentin Smarandache, W.B. Vasantha Kandasamy, K. Ilanthenral

Branch Mathematics and Statistics Faculty and Staff Publications

In this book, the authors define the new notion of set vector spaces which is the most generalized form of vector spaces. Set vector spaces make use of the least number of algebraic operations, therefore, even a non-mathematician is comfortable working with it. It is with the passage of time, that we can think of set linear algebras as a paradigm shift from linear algebras. Here, the authors have also given the fuzzy parallels of these new classes of set linear algebras. This book abounds with examples to enable the reader to understand these new concepts easily. Laborious theorems and …

Concept Detection: Convergence To Local Features And Opportunities Beyond, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky

Research Collection School Of Computing and Information Systems

No abstract provided.

Columbia University/Vireo-Cityu/Irit Trecvid2008 High-Level Feature Extraction And Interactive Video Search, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky

Research Collection School Of Computing and Information Systems

In this report, we present overview and comparative analysis of our HLF detection system, which achieves the top performance among all type-A submissions in 2008. We also describe preliminary evaluation of our video search system, CuZero, in the interactive search task.