Databases and Information Systems Commons^™

Fusion Of Multimodal Embeddings For Ad-Hoc Video Search, Danny Francis, Phuong Anh Nguyen, Benoit Huet, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

The challenge of Ad-Hoc Video Search (AVS) originates from free-form (i.e., no pre-defined vocabulary) and freestyle (i.e., natural language) query description. Bridging the semantic gap between AVS queries and videos becomes highly difficult as evidenced from the low retrieval accuracy of AVS benchmarking in TRECVID. In this paper, we study a new method to fuse multimodal embeddings which have been derived based on completely disjoint datasets. This method is tested on two datasets for two distinct tasks: on MSR-VTT for unique video retrieval and on V3C1 for multiple videos retrieval.

Kgat: Knowledge Graph Attention Network For Recommendation, Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

To provide more accurate, diverse, and explainable recommendation, it is compulsory to go beyond modeling user-item interactions and take side information into account. Traditional methods like factorization machine (FM) cast it as a supervised learning problem, which assumes each interaction as an independent instance with side information encoded. Due to the overlook of the relations among instances or items (e.g., the director of a movie is also an actor of another movie), these methods are insufficient to distill the collaborative signal from the collective behaviors of users. In this work, we investigate the utility of knowledge graph (KG), which breaks …

Multimodal Transformer Networks For End-To-End Video-Grounded Dialogue Systems, Hung Le, Doyen Sahoo, Nancy F. Chen, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Developing Video-Grounded Dialogue Systems (VGDS), where a dialogue is conducted based on visual and audio aspects of a given video, is significantly more challenging than traditional image or text-grounded dialogue systems because (1) feature space of videos span across multiple picture frames, making it difficult to obtain semantic information; and (2) a dialogue agent must perceive and process information from different modalities (audio, video, caption, etc.) to obtain a comprehensive understanding. Most existing work is based on RNNs and sequence-to-sequence architectures, which are not very effective for capturing complex long-term dependencies (like in videos). To overcome this, we propose Multimodal …

Multi-Channel Graph Neural Network For Entity Alignment, Yixin Cao, Zhiyuan Liu, Chengjiang Li, Zhiyuan Liu, Juanzi Li, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make …

Personalized Fashion Recommendation With Visual Explanations Based On Multimodal Attention Network: Towards Visually Explainable Recommendation, Xu Chen, Hanxiong Chen, Hongteng Xu, Yongfeng Zhang, Yixin Cao, Zheng Qin, Hongyuan Zha

Research Collection School Of Computing and Information Systems

Fashion recommendation has attracted increasing attention from both industry and academic communities. This paper proposes a novel neural architecture for fashion recommendation based on both image region-level features and user review information. Our basic intuition is that: for a fashion image, not all the regions are equally important for the users, i.e., people usually care about a few parts of the fashion image. To model such human sense, we learn an attention model over many pre-segmented image regions, based on which we can understand where a user is really interested in on the image, and correspondingly, represent the image in …

Outcasts – In Search Of Identity, Syed Hasan Haider

MSJ Capstone Projects

The idea for this documentary came from a story published in the express tribune which talked about the people who are unable to vote in 2018 elections due to having Computerized National Identity Cards (CNICs) in the Ibrahim Hyderi locality in Karachi.

Not having a CNIC in Pakistan means that you are not able to participate in civic life and also not subscribe to basic facilitates like housing, water, gas and employment.

This documentary film looks at different cases and through the experience of some journalists what it is like to live as an undocumented citizen. The film also explores …

Radish: A Cross Platform Meal Prepping App For Beginner Weightlifters, Spoorthy S. Vemula, Tanay Gottigundala, Cory Baxes

Computer Science and Software Engineering

With the increasing ease of access and decreasing price of most food, obesity rates in the developing world have risen dramatically in recent years. As of March 23rd, 2019, obesity rates had reached 39.6%, a 6% increase in just 8 years. Research has shown that people with obesity have a significantly increased risk of heart disease, stroke, type 2 diabetes, and certain cancers, among other life-threatening diseases. In addition, 42% of people who begin weightlifting quit because it’s too difficult to follow a diet or workout regimen.

We created Radish in an attempt to tackle these problems. Radish makes it …

Sliced Wasserstein Generative Models, Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc Van Gool

Research Collection School Of Computing and Information Systems

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional distributions. In contrast, the sliced Wasserstein distance (SWD) factorizes high-dimensional distributions into their multiple one-dimensional marginal distributions and is thus easier to approximate. In this paper, we introduce novel approximations of the primal and dual SWD. Instead of using a large number of random projections, as it is done by conventional SWD approximation methods, we propose to approximate SWDs with a small number of parameterized orthogonal projections …

Mixed Dish Recognition Through Multi-Label Learning, Yunan Wang, Jing-Jing Chen, Chong-Wah Ngo, Tat-Seng Chua, Wanli Zuo, Zhaoyan Ming

Research Collection School Of Computing and Information Systems

Mix dish recognition, whose goal is to identify each of the dish type presented on one plate, is generally regarded as a difficult problem. The major challenge of this problem is that different dishes presented in one plate may overlap with each other and there may be no clear boundaries among them. Therefore, labeling the bounding box of each dish type is difficult and not necessarily leading to good results. This paper studies the problem from the perspective of multi-label learning. Specially, we propose to perform dish recognition on region level with multiple granularities. For experimental purpose, we collect two …

Dietlens-Eout: Large Scale Restaurant Food Photo Recognition, Zhipeng Wei, Jingjing Chen, Zhaoyan Ming, Chong-Wah Ngo, Tat-Seng Chua, Fengfeng Zhou

Research Collection School Of Computing and Information Systems

Restaurant dishes represent a significant portion of food that people consume in their daily life. While people are becoming healthconscious in their food intake, convenient restaurant food tracking becomes an essential task in wellness and fitness applications. Given the huge number of dishes (food categories) involved, it becomes extremely challenging for traditional food photo classification to be feasible in both algorithm design and training data availability. In this work, we present a demo that runs on restaurant dish images in a city of millions of residents and tens of thousand restaurants. We propose a rank-loss based convolutional neural network to …

Unifying Knowledge Graph Learning And Recommendation: Towards A Better Understanding Of User Preferences, Yixin Cao, Xiang Wang, Xiangnan He, Zikun Hu, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Incorporating knowledge graph (KG) into recommender system is promising in improving the recommendation accuracy and explainability. However, existing methods largely assume that a KG is complete and simply transfer the ”knowledge” in KG at the shallow level of entity raw data or embeddings. This may lead to suboptimal performance, since a practical KG can hardly be complete, and it is common that a KG has missing facts, relations, and entities. Thus, we argue that it is crucial to consider the incomplete nature of KG when incorporating it into recommender system. In this paper, we jointly learn the model of recommendation …

Building Consumer Trust In The Cloud: An Experimental Analysis Of The Cloud Trust Label Approach, Lisa Van Der Werff, Grace Fox, Ieva Masevic, Vincent C. Emeakaroha, John P. Morrison, Theo Lynn

Department of Computer Science Publications

The lack of transparency surrounding cloud service provision makes it difficult for consumers to make knowledge based purchasing decisions. As a result, consumer trust has become a major impediment to cloud computing adoption. Cloud Trust Labels represent a means of communicating relevant service and security information to potential customers on the cloud service provided, thereby facilitating informed decision making. This research investigates the potential of a Cloud Trust Label system to overcome the trust barrier. Specifically, it examines the impact of a Cloud Trust Label on consumer perceptions of a service and cloud service provider trustworthiness and trust in the …

Forensics Analysis For Bone Pair Matching Using Bipartite Graphs In Commingled Remains, Ryan Ernst

UNO Student Research and Creative Activity Fair

Identification of missing prisoners of war is a complex and time consuming task. There are many missing soldiers whose remains have yet to be returned to their families and loved ones. This nation has a solemn obligation to its soldiers and their families who have made the ultimate sacrifice for their country. There are currently over 82,000 unidentified prisoners of war which are identified at a rate of 100+ per year. At this rate it would take 300+ years to complete the identification process. Previously, anthropologists used excel spreadsheets to sort through skeletal data. This project aims to streamline the …

Explainable Reasoning Over Knowledge Graphs For Recommendation, Xiang Wang, Dingxian Wang, Canran Xu, Xiangnan He, Yixin Cao, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Incorporating knowledge graph into recommender systems has attracted increasing attention in recent years. By exploring the interlinks within a knowledge graph, the connectivity between users and items can be discovered as paths, which provide rich and complementary information to user-item interactions. Such connectivity not only reveals the semantics of entities and relations, but also helps to comprehend a user’s interest. However, existing efforts have not fully explored this connectivity to infer user preferences, especially in terms of modeling the sequential dependencies within and holistic semantics of a path. In this paper, we contribute a new model named Knowledgeaware Path Recurrent …

U.S. Census Explorer: A Gui And Visualization Tool For The U.S. Census Data Api, Timothy Snyder

Williams Honors College, Honors Research Projects

U.S. Census Explorer is a software application that is designed to provide tools for intuitive exploration and analysis of United States census data for non-technical users. The application serves as an interface into the U.S. Census Bureau’s data API that enables a complete workflow from data acquisition to data visualization without the need for technical intervention from the user. The suite of tools provided include a graphical user interface for dynamically querying U.S. census data, geographic visualizations, and the ability to download your work to common spreadsheet and image formats for inclusion in external works.

Open Source Foundations For Spatial Decision Support Systems, Jochen Albrecht

Publications and Research

Spatial Decision Support Systems (SDSS) were a hot topic in the 1990s, when researchers tried to imbue GIS with additional decision support features. Successful practical developments such as HAZUS or CommunityViz have since been built, based on commercial desktop software and without much heed for theory other than what underlies their process models. Others, like UrbanSim, have been completely overhauled twice but without much external scrutiny. Both the practical and the theoretical foundations of decision support systems have developed considerably over the past 20 years. This article presents an overview of these developments and then looks at what corresponding tools …

Eye Pressure Monitior, Andrea Nella Levy

Computer Engineering

The document describes a mobile application that takes information from an attached device which tests eye pressure. The device consists of an IOIO board connected to a custom device that measures the frequency of a given waveform. The device was designed by another student for their senior project, which I am taking over. This device is connected to an IOIO board which is a board designed by a Google employee which works with an android phone in order to create applications that work with embedded systems. The board comes with an API and connects to the phone via a micro-USB. …

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 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 …

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 …

Effective Visualization Approaches For Ultra-High Dimensional Datasets, Gurminder Kaur

LSU Doctoral Dissertations

Multivariate informational data, which are abstract as well as complex, are becoming increasingly common in many areas such as scientific, medical, social, business, and so on. Displaying and analyzing large amounts of multivariate data with more than three variables of different types is quite challenging. Visualization of such multivariate data suffers from a high degree of clutter when the numbers of dimensions/variables and data observations become too large. We propose multiple approaches to effectively visualize large datasets of ultrahigh number of dimensions by generalizing two standard multivariate visualization methods, namely star plot and parallel coordinates plot. We refine three variants …

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 …

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, …

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 …

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 …

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 …