Graphics and Human Computer Interfaces Commons^™

Task Relation Networks, Jianshu Li, Pan Zhou, Yunpeng Chen, Jian Zhao, Sujoy Roy, Shuicheng Yan, Jiashi Feng, Terence Sim

Research Collection School Of Computing and Information Systems

Multi-task learning is popular in machine learning and computer vision. In multitask learning, properly modeling task relations is important for boosting the performance of jointly learned tasks. Task covariance modeling has been successfully used to model the relations of tasks but is limited to homogeneous multi-task learning. In this paper, we propose a feature based task relation modeling approach, suitable for both homogeneous and heterogeneous multi-task learning. First, we propose a new metric to quantify the relations between tasks. Based on the quantitative metric, we then develop the task relation layer, which can be combined with any deep learning architecture …

The Living Wall Display: Physical Augmentation Of Interactive Content Using An Autonomous Mobile Display, Yuki Onishi, Yoshiki Kudo, Kazuki Takashima, Anthony Tang, Yoshifumi Kitamura

Research Collection School Of Computing and Information Systems

The Living Wall Display displays interactive content on a mobile wall screen that moves in concert with content animation. To augment the interaction experience, the display dynamically changes its position and orientation, responding to the content animation triggered by user interactions. We implement three proof of concept prototypes that represent pseudo force impact of the interactive content using physical screen movement. Pilot studies show that the Living Wall augments content expressiveness, and increases the sense of presence of the screen content.

Vr Safari Park: A Concept-Based World Building Interface Using Blocks And World Tree, Shotaro Ichikawa, Anthony Tang, Kazuki Takashima, Yoshifumi Kitamura

Research Collection School Of Computing and Information Systems

We present a concept-based world building approach, realized in a system called VR Safari Park, which allows users to rapidly create and manipulate a world simulation. Conventional world building tools focus on the manipulation and arrangement of entities to set up the simulation, which is time consuming as it requires frequent view and entity manipulations. Our approach focuses on a far simpler mechanic, where users add virtual blocks which represent world entities (e.g. animals, terrain, weather, etc.) to a World Tree, which represents the simulation. In so doing, the World Tree provides a quick overview of the simulation, and users …

Cross Euclidean-To-Riemannian Metric Learning With Application To Face Recognition From Video, Zhiwu Huang, R. Wang, S. Shan, Gool L Van

Research Collection School Of Computing and Information Systems

Riemannian manifolds have been widely employed for video representations in visual classification tasks including video-based face recognition. The success mainly derives from learning a discriminant Riemannian metric which encodes the non-linear geometry of the underlying Riemannian manifolds. In this paper, we propose a novel metric learning framework to learn a distance metric across a Euclidean space and a Riemannian manifold to fuse average appearance and pattern variation of faces within one video. The proposed metric learning framework can handle three typical tasks of video-based face recognition: Video-to-Still, Still-to-Video and Video-to-Video settings. To accomplish this new framework, by exploiting typical Riemannian …

Modeling Movement Decisions In Networks: A Discrete Choice Model Approach, Larry Lin Junjie

Dissertations and Theses Collection (Open Access)

In this dissertation, we address the subject of modeling and simulation of agents and their movement decision in a network environment. We emphasize the development of high quality agent-based simulation models as a prerequisite before utilization of the model as an evaluation tool for various recommender systems and policies. To achieve this, we propose a methodological framework for development of agent-based models, combining approaches such as discrete choice models and data-driven modeling.

The discrete choice model is widely used in the field of transportation, with a distinct utility function (e.g., demand or revenue-driven). Through discrete choice models, the movement decision …

Active Matting, Xin Yang, Ke Xu, Shaozhe Chen, Shengfeng He, Baocai Yin, Rynson Lau

Research Collection School Of Computing and Information Systems

Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce …

Cross-Modal Recipe Retrieval With Stacked Attention Model, Jing-Jing Chen, Lei Pang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Taking a picture of delicious food and sharing it in social media has been a popular trend. The ability to recommend recipes along will benefit users who want to cook a particular dish, and the feature is yet to be available. The challenge of recipe retrieval, nevertheless, comes from two aspects. First, the current technology in food recognition can only scale up to few hundreds of categories, which are yet to be practical for recognizing tens of thousands of food categories. Second, even one food category can have variants of recipes that differ in ingredient composition. Finding the best-match recipe …

Gesture Recognition With Transparent Solar Cells, Dong Ma, Guohao Lan, Mahbub Hassan, Wen Hu, B. Mushfika Upama, Ashraf Uddin, Youseef, Moustafa

Research Collection School Of Computing and Information Systems

Transparent solar cell is an emerging solar energy harvesting technology that allows us to see through these cells. This revolutionary discovery is creating unique opportunities to turn any mobile device screen into solar energy harvester. In this paper, we consider the possibility of using such energy harvesting screens as a sensor to detect hand gestures. As different gestures impact the incident light on the screen in a different way, they are expected to create unique energy generation patterns for the transparent solar cell. Our goal is to recognize gestures by detecting these solar energy patterns. A key uncertainty we face …

Designing A Tangible Interface For Manager Awareness In Wilderness Search And Rescue, Brennan Jones, Anthony Tang, Carman Neustaedter, Alissa N. Antle, Elgin-Skye Mclaren

Research Collection School Of Computing and Information Systems

We present a tangible interface for supporting wilderness search-and-rescue (SAR) managers in maintaining awareness of a large SAR incident, where there are numerous field teams searching for a lost person in a wilderness area. This interface consists of physical and digital representations of the search area and elements of the search activity (e.g., the locations of search teams, weather information, and clues from the field). It is intended to allow SAR managers to inspect information about the response and search area from different perspectives and aid them in planning by allowing them to physically manipulate the representations and explore the …

Joint Representation Learning Of Cross-Lingual Words And Entities Via Attentive Distant Supervision, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Chengjiang Li, Xu Chen, Tiansi Dong

Research Collection School Of Computing and Information Systems

Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings. In this paper, we propose a novel method for joint representation learning of cross-lingual words and entities. It captures mutually complementary knowledge, and enables cross-lingual inferences among knowledge bases and texts. Our method does not require parallel corpora, and automatically generates comparable data via distant supervision using multi-lingual knowledge bases. We utilize two types of regularizers to align cross-lingual words and entities, and design knowledge attention and crosslingual attention to further reduce noises. We conducted a series of experiments on …

Disruptive Technology: Can The Banking Industry Harness Disruption For Competitive Edge?, Edgar Low

MITB Thought Leadership Series

Disruptive innovation was identified as a phenomenon more than two decades ago by prominent Harvard scholar Clayton Christensen. So you may wonder why established industries are only now waking up to the prospect of digital transformation - the banking industry in particular.

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.

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 …

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.

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, …

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 …

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 …

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 …

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 …

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.

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.

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 …

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 …

Effect Of Temporality, Physical Activity, And Cognitive Load On Spatiotemporal Vibrotactile Pattern Recognition, Qin Chen, Simon T. Perrault, Quentin Xavier Louis Roy, Lonce Wyse

Research Collection School Of Computing and Information Systems

Previous research demonstrated the ability for users to accurately recognize Spatiotemporal Vibrotactile Patterns (SVP): sequences of vibrations on different motors occurring either sequentially or simultaneously. However, the experiments were only run in a lab setting and the ability for users to recognize SVP in a real-world environment remains unclear. In this paper, we investigate how several factors may affect recognition: (1) physical activity (running), (2) cognitive task (i.e. primary task, typing), (3) distribution of the vibration motors across body parts and (4) temporality of the patterns. Our results suggest that physical activity has very little impact, specifically compared to cognitive …

Movespace: On-Body Athletic Interaction For Running And Cycling, Velko Vechev, Alexandru Dancu, Simon T. Perrault, Quentin Xavier Louis Roy, Morten Fjeld, Shengdong Zhao

Research Collection School Of Computing and Information Systems

Wearables are increasingly used during training to quantify performance and provide valuable real-time information. However, interacting with these devices in motion may disrupt the movements of the activity. We propose a method of interaction involving tapping specific locations on the body, identify candidate locations for running and cycling, and compare them in a series of controlled experiments with athletes. A purpose-built prototype measures speed of interaction and gives feedback cues for athletes to report the physical effects on the activity itself. Our results suggest that specific locations are faster and have minimal disruption to movement, even under induced fatigue conditions. …

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 …

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 …

Neural Correlates Of States Of User Experience In Gaming Using Eeg And Predictive Analytics, Chandana Mallapragada, Fiona Fui-Hoon Nah, Keng Siau, Langtao Chen, Tejaswini Yelamanchili

Research Collection School Of Computing and Information Systems

In this research, we will analyze EEG signals to obtain neural correlate classifications of user experience by applying predictive analytics. Boredom, flow, and anxiety are three states experienced by users interacting with a computer-based system. A within-subjects experiment was used to collect EEG data for these three states and a baseline. We will apply predictive analytics including linear regression, support vector machine, and neural networks to analyze and classify the EEG data for these three states of user experience.

A Visual Interaction Cue Framework From Video Game Environments For Augmented Reality, Kody R. Dillman, Terrance Tin Hoi Mok, Anthony Tang, Lora Oehlberg, Alex Mitchell

Research Collection School Of Computing and Information Systems

Based on an analysis of 49 popular contemporary video games, we develop a descriptive framework of visual interaction cues in video games. These cues are used to inform players what can be interacted with, where to look, and where to go within the game world. These cues vary along three dimensions: the purpose of the cue, the visual design of the cue, and the circumstances under which the cue is shown. We demonstrate that this framework can also be used to describe interaction cues for augmented reality applications. Beyond this, we show how the framework can be used to generatively …