Graphics and Human Computer Interfaces Commons^™

Geometry-Aware Similarity Learning On Spd Manifolds For Visual Recognition, Zhiwu Huang, R. Wang, X. Li, W. Liu, S. Shan, Gool L. Van, X Chen

Research Collection School Of Computing and Information Systems

Symmetric positive definite (SPD) matrices have been employed for data representation in many visual recognition tasks. The success is mainly attributed to learning discriminative SPD matrices encoding the Riemannian geometry of the underlying SPD manifolds. In this paper, we propose a geometry-aware SPD similarity learning (SPDSL) framework to learn discriminative SPD features by directly pursuing a manifold-manifold transformation matrix of full column rank. Specifically, by exploiting the Riemannian geometry of the manifolds of fixed-rank positive semidefinite (PSD) matrices, we present a new solution to reduce optimization over the space of column full-rank transformation matrices to optimization on the PSD manifold, …

Mixed-Reality For Object-Focused Remote Collaboration, Martin Feick, Anthony Tang, Scott Bateman

Research Collection School Of Computing and Information Systems

In this paper we outline the design of a mixed-reality system to support object-focused remote collaboration. Here, being able to adjust collaborators' perspectives on the object as well as understand one another's perspective is essential to support effective collaboration over distance. We propose a low-cost mixed-reality system that allows users to: (1) quickly align and understand each other's perspective; (2) explore objects independently from one another, and (3) render gestures in the remote's workspace. In this work, we focus on the expert's role and we introduce an interaction technique allowing users to quickly manipulation 3D virtual objects in space.

Deep Understanding Of Cooking Procedure For Cross-Modal Recipe Retrieval, Jingjing Chen, Chong-Wah Ngo, Fu-Li Feng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Finding a right recipe that describes the cooking procedure for a dish from just one picture is inherently a difficult problem. Food preparation undergoes a complex process involving raw ingredients, utensils, cutting and cooking operations. This process gives clues to the multimedia presentation of a dish (e.g., taste, colour, shape). However, the description of the process is implicit, implying only the cause of dish presentation rather than the visual effect that can be vividly observed on a picture. Therefore, different from other cross-modal retrieval problems in the literature, recipe search requires the understanding of textually described procedure to predict its …

Knowledge-Aware Multimodal Fashion Chatbot, Lizi Liao, You Zhou, Yunshan Ma, Richang Hong, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Multimodal fashion chatbot provides a natural and informative way to fulfill customers’ fashion needs. However, making it ‘smart’ in generating substantive responses remains a challenging problem. In this paper, we present a multimodal domain knowledge enriched fashion chatbot. It forms a taxonomy-based learning module to capture the fine-grained semantics in images and leverages an endto-end neural conversational model to generate responses based on the conversation history, visual semantics, and domain knowledge. To avoid inconsistent dialogues, deep reinforcement learning method is used to further optimize the model.

Predicting Visual Context For Unsupervised Event Segmentation In Continuous Photo-Streams, Ana García Del Molino, Joo-Hwee Lim, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Segmenting video content into events provides semantic structures for indexing, retrieval, and summarization. Since motion cues are not available in continuous photo-streams, and annotations in lifelogging are scarce and costly, the frames are usually clustered into events by comparing the visual features between them in an unsupervised way. However, such methodologies are ineffective to deal with heterogeneous events, e.g. taking a walk, and temporary changes in the sight direction, e.g. at a meeting. To address these limitations, we propose Contextual Event Segmentation (CES), a novel segmentation paradigm that uses an LSTM-based generative network to model the photo-stream sequences, predict their …

Human Hexokinase I - Allosteric Regulation: Model File Name: 1dgk-Editb22-Allostery_Sc06.Stl, Michelle Howell, Rebecca Roston

3-D Printed Model Structural Files

This is a teaching model of human Hexokinase I in a surface representation with small molecules ADP and G6P included (PDB: 1DGK). It is designed to be hollow with a lever to mimic allosteric regulation. The printable model is already uploaded to Shapeways.com in the MacroMolecules shop under the name “Human Hexokinase I - Allosteric regulation model”. This model has been printed successfully using these parameters on Shapeways’ laser sintering printer in the following material: Processed Versatile Plastic (Strong & Flexible Plastic).

A Vector Field Design Approach To Animated Transitions, Yong Wang, Daniel Archambault, Carlos E. Scheidegger, Huamin Qu

Research Collection School Of Computing and Information Systems

Animated transitions can be effective in explaining and exploring a small number of visualizations where there are drastic changes in the scene over a short interval of time. This is especially true if data elements cannot be visually distinguished by other means. Current research in animated transitions has mainly focused on linear transitions (all elements follow straight line paths) or enhancing coordinated motion through bundling of linear trajectories. In this paper, we introduce animated transition design, a technique to build smooth, non-linear transitions for clustered data with either minimal or no user involvement. The technique is flexible and simple to …

Wasserstein Divergence For Gans, J. Wu, Zhiwu Huang, J. Thoma, D. Acharya, Gool L. Van

Research Collection School Of Computing and Information Systems

In many domains of computer vision, generative adversarial networks (GANs) have achieved great success, among which the family of Wasserstein GANs (WGANs) is considered to be state-of-the-art due to the theoretical contributions and competitive qualitative performance. However, it is very challenging to approximate the k-Lipschitz constraint required by the Wasserstein-1 metric (W-met). In this paper, we propose a novel Wasserstein divergence (W-div), which is a relaxed version of W-met and does not require the k-Lipschitz constraint. As a concrete application, we introduce a Wasserstein divergence objective for GANs (WGAN-div), which can faithfully approximate W-div through optimization. Under various settings, including …

Discrete Information Object Analysis Of Primary Flight Display Clutter, Kenneth Ward

National Training Aircraft Symposium (NTAS)

Modern aircraft utilize digital display screens to provide critical flight and system status information to pilots. As computing power has increased, the number of data sources and information presented has also increased, with the goal of increasing situational awareness. However, the display can become cluttered with extraneous or irrelevant information, to the detriment of pilot cognitive workload. Pilot perceptions of clutter vary with flight experience, introducing unique considerations in the flight training environment, given the experience difference between instructors and students. Researchers have studied the problem, identifying both the number of visual objects and information density as predictors of perception …

Visualization Of Geospatial Data As An Analytical And Educational Tool, Richard A. Vu

STAR Program Research Presentations

World Wind is an open-source API developed for Java, Android, and browsers that is designed to visualize and interact with geospatial data. The Web World Wind client is composed of four major components: the HTML template, the globe, geospatial features, and application features. The template was implemented using Bootstrap and hosts the globe provided by World Wind. This globe draws its data from multiple imagery sources, including the Open Geospatial Consortium (OGC) Web Map Service and Web Map Tile Service. This enables the application to perform and visualize complex calculations with multiple types of data such as weather and terrain. …

Neural Collective Entity Linking, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu

Research Collection School Of Computing and Information Systems

Entity Linking aims to link entity mentions in texts to knowledge bases, and neural models have achieved recent success in this task. However, most existing methods rely on local contexts to resolve entities independently, which may usually fail due to the data sparsity of local information. To address this issue, we propose a novel neural model for collective entity linking, named as NCEL. NCEL applies Graph Convolutional Network to integrate both local contextual features and global coherence information for entity linking. To improve the computation efficiency, we approximately perform graph convolution on a subgraph of adjacent entity mentions instead of …

Theatrical Genre Prediction Using Social Network Metrics, Manisha Shukla

Graduate Theses and Dissertations

With the emergence of digitization, large text corpora are now available online that provide humanities scholars an opportunity to perform literary analysis leveraging the use of computational techniques. This work is focused on applying network theory concepts in the field of literature to explore correlations between the mathematical properties of the social networks of plays and the plays’ dramatic genre, specifically how well social network metrics can identify genre without taking vocabulary into consideration. Almost no work has been done to study the ability of mathematical properties of network graphs to predict literary features. We generated character interaction networks of …

Leveraging Tiled Display For Big Data Visualization Using D3.Js, Ujjwal Acharya

Boise State University Theses and Dissertations

Data visualization has proven effective at detecting patterns and drawing inferences from raw data by transforming it into visual representations. As data grows large, visualizing it faces two major challenges: 1) limited resolution i.e. a screen is limited to a few million pixels but the data can have a billion data points, and 2) computational load i.e. processing of this data becomes computationally challenging for a single node system. This work addresses both of these issues for efficient big data visualization. In the developed system, a High Pixel Density and Large Format display was used enabling the display of fine …

Teaching Landscape Construction Using Augmented Reality, Arshdeep Singh

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

This thesis describes the design, development, and evaluation of an interactive Microsoft HoloLens application that projects landscape models in Augmented Reality. The application was developed using the Unity framework and 3D models created in Sketchup. Using the application, students can not only visualize the models in real space but can also interact with the models using gestures. The students can interact with the models using gaze and air-tap gestures.

Application testing was conducted with 21 students from the Landscape Architecture and Environmental Planning department at Utah State University. To evaluate the application, students completed a usability survey after using the …

Formalizing Schoenberg’S Fundamentals Of Musical Composition Through Petri Nets, A. Baratè, G. Haus, L. A. Ludovico, Davide Andrea Mauro

Computer Sciences and Electrical Engineering Faculty Research

The formalization of musical composition rules is a topic that has been studied for a long time. It can lead to a better understanding of the underlying processes, and provide a useful tool for musicologist to aid and speed up the analysis process. In our attempt we introduce Schoenberg’s rules from Fundamentals of Musical Composition using a specialized version of Petri nets, called Music Petri nets. Petri nets are a formal tool for studying systems that are concurrent, asynchronous, distributed, parallel, nondeterministic, and/or stochastic. We present some examples highlighting how multiple approaches to the analysis task can find counterparts in …

Effect Of Gamification On Intrinsic Motivation, Edna Chan, Fiona Fui-Hoon Nah, Qizhang Liu, Zhiwei Lu

Research Collection School Of Computing and Information Systems

Gamification has been increasing in popularity in a variety of online context, including online learning. However, its impact on intrinsic motivation is still unclear. In this research, we carried out an experiment to assess the impact of providing two gamification features in an online learning system – point and leaderboard – on intrinsic motivation.

An Assessment Of Users’ Cyber Security Risk Tolerance In Reward-Based Exchange, Xinhui Zhan, Fiona Fui-Hoon Nah, Maggie X. Cheng

Research Collection School Of Computing and Information Systems

This study examines users’ risk-taking behavior in software downloads. We are interested in quantifying the degree of risks that users are willing to take in the cyber security context. We propose conducting an experiment using Amazon’s Mechanical Turk to assess the degree of risks that people are willing to take for monetary gains when they download software from uncertified sources.

Role Of Social Media In Public Accounting Firms, Brenda Eschenbrenner, Fiona Fui-Hoon Nah, Zhiwei Lu

Research Collection School Of Computing and Information Systems

Social media has been widely used for both professional and personal communications. Businesses recognize the importance of social media and are using them to fulfill various business objectives. In this paper, we focus on analyzing the business objectives of public accounting firms that have both a firm-wide main page and a career page on Facebook. More specifically, we compare the business objectives they are achieving with their firm-wide main pages versus career pages. We not only find differences in the objectives that are being achieved, but also identify other objectives that are not actively being pursued on either page but …

Using Eeg-Validated Music Emotion Recognition Techniques To Classify Multi-Genre Popular Music For Therapeutic Purposes, Dejoy Shastikk Kumaran

The International Student Science Fair 2018

Music is observed to possess significant beneficial effects to human mental health, especially for patients undergoing therapy and older adults. Prior research focusing on machine recognition of the emotion music induces by classifying low-level music features has utilized subjective annotation to label data for classification. We validate this approach by using an electroencephalography-based approach to cross-check the predictions of music emotion made with the predictions from low-level music feature data as well as collected subjective annotation data. Collecting 8-channel EEG data from 10 participants listening to segments of 40 songs from 5 different genres, we obtain a subject-independent classification accuracy …

Using Eeg-Validated Music Emotion Recognition Techniques To Classify Multi-Genre Popular Music For Therapeutic Purposes, Dejoy Shastikk Kumaran

The International Student Science Fair 2018

Music is observed to possess significant beneficial effects to human mental health, especially for patients undergoing therapy and older adults. Prior research focusing on machine recognition of the emotion music induces by classifying low-level music features has utilized subjective annotation to label data for classification. We validate this approach by using an electroencephalography-based approach to cross-check the predictions of music emotion made with the predictions from low-level music feature data as well as collected subjective annotation data. Collecting 8-channel EEG data from 10 participants listening to segments of 40 songs from 5 different genres, we obtain a subject-independent classification accuracy …

Effects Of Dynamic Goals On Agent Performance, Nathan R. Ball

Theses and Dissertations

Autonomous systems are increasingly being used for complex tasks in dynamic environments. Robust automation needs to be able to establish its current goal and determine when the goal has changed. In human-machine teams autonomous goal detection is an important component of maintaining shared situational awareness between both parties. This research investigates how different categories of goals affect autonomous change detection in a dynamic environment. In order to accomplish this goal, a set of autonomous agents were developed to perform within an environment with multiple possible goals. The agents perform the environmental task while monitoring for goal changes. The experiment tests …

Raymarching The Mandelbulb Fractal In Vr, Timotheus Alexander Letz

Computer Engineering

Elaborate 3D fractals, such as the mandelbulb, offer fascinating depths and structures that bear self-similarity as one zooms in closer and closer. Traditional rendering techniques focus on pre-rendering the fractal, to bypass the need for real-time display. To display and explore the mandelbulb in VR, this real-time display is needed, and can be provided through the use of “Raymarching”, a technique that allows for the rendering of scenes within the GPU. This paper explores various techniques and systems used to provide, augment, and accelerate this process.

Topographic Maps: Image Processing And Path-Finding, Calin Washington

Master's Theses

Topographic maps are an invaluable tool for planning routes through unfamiliar terrain. However, accurately planning routes on topographic maps is a time- consuming and error-prone task. One factor is the difficulty of interpreting the map itself, which requires prior knowledge and practice. Another factor is the difficulty of making choices between possible routes that have different trade-offs between length and the terrain they traverse.

To alleviate these difficulties, this thesis presents a system to automate the process of finding routes on scanned images of topographic maps. The system allows users to select any two points on a topographic map and …

Jupyterlab_Voyager: A Data Visualization Enhancement In Jupyterlab, Ji Zhang

Master's Theses

With the emergence of big data, scientific data analysis and visualization (DAV) tools are critical components of the data science software ecosystem; the usability of these tools is becoming extremely important to facilitate next-generation scientific discoveries. JupyterLab has been considered as one of the best polyglot, web-based, open-source data science tools. As the next phase of extensible interface for the classic iPython Notebooks, this tool supports interactive data science and scientific computing across multiple programming languages with great performances. Despite these advantages, previous heuristics evaluation studies have shown that JupyterLab has some significant flaws in the data visualization side. The …

Real-Time Object Removal In Augmented Reality, Tyler Dahl

Master's Theses

Diminished reality, as a sub-topic of augmented reality where digital information is overlaid on an environment, is the perceived removal of an object from an environment. Previous approaches to diminished reality used digital replacement techniques, inpainting, and multi-view homographies. However, few used a virtual representation of the real environment, limiting their domains to planar environments.

This thesis provides a framework to achieve real-time diminished reality on an augmented reality headset. Using state-of-the-art hardware, we combine a virtual representation of the real environment with inpainting to remove existing objects from complex environments.

Our work is found to be competitive with previous …

Covariance Pooling For Facial Expression Recognition, D. Acharya, Zhiwu Huang, D. Paudel, Gool L. Van

Research Collection School Of Computing and Information Systems

Classifying facial expressions into different categories requires capturing regional distortions of facial landmarks. We believe that second-order statistics such as covariance is better able to capture such distortions in regional facial features. In this work, we explore the benefits of using a manifold network structure for covariance pooling to improve facial expression recognition. In particular, we first employ such kind of manifold networks in conjunction with traditional convolutional networks for spatial pooling within individual image feature maps in an end-to-end deep learning manner. By doing so, we are able to achieve a recognition accuracy of 58.14% on the validation set …

Deep Adversarial Subspace Clustering, Pan Zhou, Yunqing Hou, Jiashi Feng

Research Collection School Of Computing and Information Systems

Most existing subspace clustering methods hinge on self-expression of handcrafted representations and are unaware of potential clustering errors. Thus they perform unsatisfactorily on real data with complex underlying subspaces. To solve this issue, we propose a novel deep adversarial subspace clustering (DASC) model, which learns more favorable sample representations by deep learning for subspace clustering, and more importantly introduces adversarial learning to supervise sample representation learning and subspace clustering. Specifically, DASC consists of a subspace clustering generator and a quality-verifying discriminator, which learn against each other. The generator produces subspace estimation and sample clustering. The discriminator evaluates current clustering performance …

Tessellated Voxelization For Global Illumination Using Voxel Cone Tracing, Sam Thomas Freed

Master's Theses

Modeling believable lighting is a crucial component of computer graphics applications, including games and modeling programs. Physically accurate lighting is complex and is not currently feasible to compute in real-time situations. Therefore, much research is focused on investigating efficient ways to approximate light behavior within these real-time constraints.

In this thesis, we implement a general purpose algorithm for real-time applications to approximate indirect lighting. Based on voxel cone tracing, we use a filtered representation of a scene to efficiently sample ambient light at each point in the scene. We present an approach to scene voxelization using hardware tessellation and compare …

Scale Impacts Elicited Gestures For Manipulating Holograms: Implications For Ar Gesture Design, Tran Pham, Jo Vermeulen, Anthony Tang, Lindsay Macdonald

Research Collection School Of Computing and Information Systems

Because gesture design for augmented reality (AR) remains idiosyncratic, people cannot necessarily use gestures learned in one AR application in another. To design discoverable gestures, we need to understand what gestures people expect to use. We explore how the scale of AR affects the gestures people expect to use to interact with 3D holograms. Using an elicitation study, we asked participants to generate gestures in response to holographic task referents, where we varied the scale of holograms from desktop-scale to room-scale objects. We found that the scale of objects and scenes in the AR experience moderates the generated gestures. Most …

Dimensionality's Blessing: Clustering Images By Underlying Distribution, Wen-Yan Lin, Jian-Huang Lai, Siying Liu, Yasuyuki Matsushita

Research Collection School Of Computing and Information Systems

Many high dimensional vector distances tend to a constant. This is typically considered a negative “contrastloss” phenomenon that hinders clustering and other machine learning techniques. We reinterpret “contrast-loss” as a blessing. Re-deriving “contrast-loss” using the law of large numbers, we show it results in a distribution’s instances concentrating on a thin “hyper-shell”. The hollow center means apparently chaotically overlapping distributions are actually intrinsically separable. We use this to develop distribution-clustering, an elegant algorithm for grouping of data points by their (unknown) underlying distribution. Distribution-clustering, creates notably clean clusters from raw unlabeled data, estimates the number of clusters for itself and …