Computer Sciences Commons^™

Contrastive Video Question Answering Via Video Graph Transformer, Junbin Xiao Xiao, Pan Zhou, Angela Yao, Yicong Li, Richang Hong, Shuicheng Yan, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT’s uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional cross-modal interaction modules. 3) It is optimized by the joint fully- and self-supervised contrastive objectives between the …

A Review On The Effects Of Chanting And Solfeggio Frequencies On Well-Being, Xuyu Yang, Fiona Fui-Hoon Nah, Fen Lin

Research Collection School Of Computing and Information Systems

This paper presents our literature review on how chanting and solfeggio frequencies affect brain activity, enhance well-being, and inform the design of sound therapy. We call for more scientific research to investigate and better understand the effects of chanting and solfeggio frequencies on well-being.

Robust And Parallel Segmentation Model (Rpsm) For Early Detection Of Skin Cancer Disease Using Heterogeneous Distributions, Nancy Zreika, Ali El-Zaart, Abdallah El Chakik

BAU Journal - Science and Technology

Melanoma is the most common dangerous type of skin cancer; however, it is preventable if it is diagnosed early. Diagnosis of Melanoma would be improved if an accurate skin image segmentation model is available. Many computer vision methods have been investigated, yet the problem of finding a consistent and robust model that extracts the best threshold value, persists. This paper suggests a novel image segmentation approach using a multilevel cross entropy thresholding algorithm based on heterogeneous distributions. The proposed strategy searches the problem space by segmenting the image into several levels, and applying for each level one of the three …

Deep-Learning Realtime Upsampling Techniques In Video Games, Biruk Mengistu

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

This paper addresses the challenge of keeping up with the ever-increasing graphical complexity of video games and introduces a deep-learning approach to mitigating it. As games get more and more demanding in terms of their graphics, it becomes increasingly difficult to maintain high-quality images while also ensuring good performance. This is where deep learning super sampling (DLSS) comes in. The paper explains how DLSS works, including the use of convolutional autoencoder neural networks and various other techniques and technologies. It also covers how the network is trained and optimized, as well as how it incorporates temporal antialiasing and frame generation …

How Photorealistic Images Are Generated, Nahom Ketema

University Honors Theses

The field of computer graphics looks into how computers can be used to generate images. From using some trigonometry to plot 3D objects to using rays to calculate the lighting of an object, there are a variety of ways that we can use to draw objects onto a screen. For this thesis, we will be looking at a few of those methods to determine how photorealistic images are generated.

Interstice, Shravan Rao

Masters Theses

When I was about three years old, I distinctly remember being too small to see what was on top of the table. A couple of years later, when I could see those objects, I thought the world around me had grown smaller. In a way, it did, as I experienced, lived, captured, remembered, and shared the space repeatedly. This sense of the world shrinking was exaggerated during the Covid-19 pandemic, allowing new behaviours and modes of interaction to emerge. Continually shaping our modern lives, virtual technologies redefine how we access and share information and stories or even explore new places. …

An Investigation Into Machine Learning Techniques For Designing Dynamic Difficulty Agents In Real-Time Games, Ryan Adare Dunagan

Electronic Theses and Dissertations

Video games are an incredibly popular pastime enjoyed by people of all ages world wide. Many different kinds of games exist, but most games feature some elements of the player overcoming some challenge, usually through gameplay. These challenges are insurmountable for some people and may turn them off to video games as a pastime. Games can be made more accessible to players of little skill and/or experience through the use of Dynamic Difficulty Adjustment (DDA) systems that adjust the difficulty of the game in response to the player’s performance. This research seeks to establish the effectiveness of machine learning techniques …

Generalizing Graph Neural Networks Across Graphs, Time, And Tasks, Zhihao Wen

Dissertations and Theses Collection (Open Access)

Graph-structured data are ubiquitous across numerous real-world contexts, encompassing social networks, commercial graphs, bibliographic networks, and biological systems. Delving into the analysis of these graphs can yield significant understanding pertaining to their corresponding application fields.Graph representation learning offers a potent solution to graph analytics challenges by transforming a graph into a low-dimensional space while preserving its information to the greatest extent possible. This conversion into low-dimensional vectors enables the efficient computation of subsequent graph algorithms. The majority of prior research has concentrated on deriving node representations from a single, static graph. However, numerous real-world situations demand rapid generation of representations …

Scanet: Self-Paced Semi-Curricular Attention Network For Non-Homogeneous Image Dehazing, Yu Guo, Yuan Gao, Ryan Wen Liu, Yuxu Lu, Jingxiang Qu, Shengfeng He, Ren Wenqi

Research Collection School Of Computing and Information Systems

The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details. Existing homogeneous dehazing methods struggle to handle the non-uniform distribution of haze in a robust manner. The crucial challenge of non-homogeneous dehazing is to effectively extract the non-uniform distribution features and reconstruct the details of hazy areas with high quality. In this paper, we propose a novel self-paced semi-curricular attention network, called SCANet, for non-homogeneous image dehazing that focuses on enhancing haze-occluded regions. Our approach consists of an attention generator network and a scene re-construction network. We use the luminance …

Curricular Contrastive Regularization For Physics-Aware Single Image Dehazing, Yu Zheng, Jiahui Zhan, Shengfeng He, Yong Du

Research Collection School Of Computing and Information Systems

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are non-consensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy …

Position-Guided Text Prompt For Vision-Language Pre-Training, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Yan Shuicheng

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into N x N blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates …

Ifundit: Visual Profiling Of Fund Investment Styles, Rong Zhang, Bon Kyung Ku, Yong Wang, Xuanwu Yue, Siyuan Liu, Ke Li, Huamin Qu

Research Collection School Of Computing and Information Systems

Mutual funds are becoming increasingly popular with the emergence of Internet finance. Clear profiling of a fund's investment style is crucial for fund managers to evaluate their investment strategies, and for investors to understand their investment. However, it is challenging to profile a fund's investment style as it requires a comprehensive analysis of complex multi-dimensional temporal data. In addition, different fund managers and investors have different focuses when analysing a fund's investment style. To address the issue, we propose iFUNDit, an interactive visual analytic system for fund investment style analysis. The system decomposes a fund's critical features into performance attributes …

Mosaic: Spatially-Multiplexed Edge Ai Optimization Over Multiple Concurrent Video Sensing Streams, Ila Gokarn, Hemanth Sabbella, Yigong Hu, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and complexity of DNN models. One promising approach involves criticality-aware processing, where the computation is directed selectively to "critical" portions of individual image frames. We introduce MOSAIC, a novel system for such criticality-aware concurrent processing of multiple vision sensing streams that provides a multiplicative increase in the achievable throughput with negligible loss in perception fidelity. MOSAIC determines critical regions from images received from multiple vision …

Towards A Smaller Student: Capacity Dynamic Distillation For Efficient Image Retrieval, Yi Xie, Huaidong Zhang, Xuemiao Xu, Jianqing Zhu, Shengfeng He

Research Collection School Of Computing and Information Systems

Previous Knowledge Distillation based efficient image retrieval methods employ a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective knowledge imitation during the most critical early training period, causing final performance degeneration. To tackle this issue, we propose a Capacity Dynamic Distillation framework, which constructs a student model with editable representation capacity. Specifically, the employed student model is initially a heavy model to fruitfully learn distilled knowledge in the early training epochs, and the student model is gradually compressed during the training. To dynamically adjust the model capacity, our …

Class-Incremental Exemplar Compression For Class-Incremental Learning, Zilin Luo, Yaoyao Liu, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

Exemplar-based class-incremental learning (CIL) finetunes the model with all samples of new classes but few-shot exemplars of old classes in each incremental phase, where the "few-shot" abides by the limited memory budget. In this paper, we break this "few-shot" limit based on a simple yet surprisingly effective idea: compressing exemplars by downsampling non-discriminative pixels and saving "many-shot" compressed exemplars in the memory. Without needing any manual annotation, we achieve this compression by generating 0-1 masks on discriminative pixels from class activation maps (CAM). We propose an adaptive mask generation model called class-incremental masking (CIM) to explicitly resolve two difficulties of …

Extracting Class Activation Maps From Non-Discriminative Features As Well, Zhaozheng Chen, Qianru Sun

Research Collection School Of Computing and Information Systems

Extracting class activation maps (CAM) from a classification model often results in poor coverage on foreground objects, i.e., only the discriminative region (e.g., the “head” of “sheep”) is recognized and the rest (e.g., the “leg” of “sheep”) mistakenly as background. The crux behind is that the weight of the classifier (used to compute CAM) captures only the discriminative features of objects. We tackle this by introducing a new computation method for CAM that explicitly captures non-discriminative features as well, thereby expanding CAM to cover whole objects. Specifically, we omit the last pooling layer of the classification model, and perform clustering …

Freestyle Layout-To-Image Synthesis, Han Xue, Zhiwu Huang, Qianru Sun, Li Song, Wenjun Zhang

Research Collection School Of Computing and Information Systems

Typical layout-to-image synthesis (LIS) models generate images for a close set of semantic classes, e.g., 182 common objects in COCO-Stuff. In this work, we explore the freestyle capability of the model, i.e., how far can it generate unseen semantics (e.g., classes, attributes, and styles) onto a given layout, and call the task Freestyle LIS (FLIS). Thanks to the development of large-scale pre-trained language-image models, a number of discriminative models (e.g., image classification and object detection) trained on limited base classes are empowered with the ability of unseen class prediction. Inspired by this, we opt to leverage large-scale pre-trained text-to-image diffusion …

Semantic Scene Completion With Cleaner Self, Fengyun Wang, Dong Zhang, Hanwang Zhang, Jinhui Tang, Qianru Sun

Research Collection School Of Computing and Information Systems

Semantic Scene Completion (SSC) transforms an image of single-view depth and/or RGB 2D pixels into 3D voxels, each of whose semantic labels are predicted. SSC is a well-known ill-posed problem as the prediction model has to “imagine” what is behind the visible surface, which is usually represented by Truncated Signed Distance Function (TSDF). Due to the sensory imperfection of the depth camera, most existing methods based on the noisy TSDF estimated from depth values suffer from 1) incomplete volumetric predictions and 2) confused semantic labels. To this end, we use the ground-truth 3D voxels to generate a perfect visible surface, …

Unbiased Multiple Instance Learning For Weakly Supervised Video Anomaly Detection, Hui Lyu, Zhongqi Yue, Qianru Sun, Bin Luo, Zhen Cui, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training …

Evading Deepfake Detectors Via Adversarial Statistical Consistency, Yang Hou, Qing Guo, Yihao Huang, Xiaofei Xie, Lei Ma, Jianjun Zhao

Research Collection School Of Computing and Information Systems

In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds, more and more DeepFake detection techniques have been proposed. These methods typically rely on detecting statistical differences between natural (i.e., real) and DeepFake-generated images in both spatial and frequency domains. In this work, we propose to explicitly minimize the statistical differences to evade state-of-the-art DeepFake detectors. To this end, we propose a statistical consistency attack (StatAttack) against DeepFake detectors, which contains two main parts. First, we select several statistical-sensitive natural degradations (i.e., exposure, blur, and noise) and add them to the fake images …

Gnnlens: A Visual Analytics Approach For Prediction Error Diagnosis Of Graph Neural Networks., Zhihua Jin, Yong Wang, Qianwen Wang, Yao Ming, Tengfei Ma, Huamin Qu

Research Collection School Of Computing and Information Systems

Graph Neural Networks (GNNs) aim to extend deep learning techniques to graph data and have achieved significant progress in graph analysis tasks (e.g., node classification) in recent years. However, similar to other deep neural networks like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), GNNs behave like a black box with their details hidden from model developers and users. It is therefore difficult to diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs and RNNs, little research has addressed the challenges for GNNs. This paper fills the research gap with an interactive visual analysis …

Venus: A Geometrical Representation For Quantum State Visualization, Shaolun Ruan, Ribo Yuan, Qiang Guan, Yanna Lin, Ying Mao, Weiwen Jiang, Zhepeng Wang, Wei Xu, Yong Wang

Research Collection School Of Computing and Information Systems

Visualizations have played a crucial role in helping quantum computing users explore quantum states in various quantum computing applications. Among them, Bloch Sphere is the widely-used visualization for showing quantum states, which leverages angles to represent quantum amplitudes. However, it cannot support the visualization of quantum entanglement and superposition, the two essential properties of quantum computing. To address this issue, we propose VENUS, a novel visualization for quantum state representation. By explicitly correlating 2D geometric shapes based on the math foundation of quantum computing characteristics, VENUS effectively represents quantum amplitudes of both the single qubit and two qubits for quantum …

Human And Technical Factors In The Adoption Of Quantum Cryptographic Algorithms, Alyssa Pinkston

Mathematical Sciences Technical Reports (MSTR)

The purpose of this research is to understand what factors would cause users to choose quantum key distribution (QKD) over other methods of cryptography. An Advanced Encryption Standard (AES) key can be exchanged through communication using the Rivest, Shamir, Adleman (RSA) cryptographic algorithm, QKD, or post-quantum cryptography (PQC). QKD relies on quantum physics where RSA and PQC use complex mathematics to encrypt data. The BB84 quantum cryptographic protocol involves communication over a quantum channel and a public channel. The quantum channel can be technically attacked by beamsplitting or intercept/resend. QKD, like other forms of cryptography, is vulnerable to social attacks …

An Assistive Interface For Displaying Novice's Code History, Ruiwei Xiao

McKelvey School of Engineering Graduate Student Theses & Dissertations

As Teaching Assistant (TA) programs grow in number and size in introductory CS courses, TAs play a significant role in novice programmers' experience and contribute to their success. However, many TAs are also relative beginners themselves and thus have limited experience in programming and teaching. Thus the effectiveness and consistency of their guidance can vary significantly. To improve interaction quality and assist TAs in providing better support, we examine the difficulties encountered by inexperienced TAs in previous literature and then identify the potential for the high cognitive load as an unaddressed difficulty that may prevent new TAs from initiating effective …

Expressive Marks: Art In The Age Of Augmented Reality, Carson G. Levine

Dartmouth College Master’s Theses

Augmented reality (AR) and non-fungible tokens (NFTs) introduce new considerations for the long-standing debate of what it means for digital art to be “real.” However, the ability to create AR experiences is limited to those who are technically skilled or who can afford to consult someone else. This paper addresses the need for an accessible tool that enables artists of all technical backgrounds to expressively create marks in AR. The solution includes a mobile application called CrayonAR. The system was designed to be modular, minimal, and physically engaging, and was developed in Unity using ARFoundation and Firebase Storage and Realtime …

Visualized Algorithm Engineering On Two Graph Partitioning Problems, Zizhen Chen

Computer Science and Engineering Theses and Dissertations

Concepts of graph theory are frequently used by computer scientists as abstractions when modeling a problem. Partitioning a graph (or a network) into smaller parts is one of the fundamental algorithmic operations that plays a key role in classifying and clustering. Since the early 1970s, graph partitioning rapidly expanded for applications in wide areas. It applies in both engineering applications, as well as research. Current technology generates massive data (“Big Data”) from business interactions and social exchanges, so high-performance algorithms of partitioning graphs are a critical need.

This dissertation presents engineering models for two graph partitioning problems arising from completely …

Beyond Algorithms: A User-Centered Evaluation Of A Feature Recommender System In Requirements Engineering, Oluwatobi Lasisi

Theses and Dissertations

Several studies have applied recommender technologies to support requirements engineering activities. As in other application areas of recommender systems (RS), many studies have focused on the algorithms’ prediction accuracy, while there have been limited discussions around users’ interactions with the systems. Since recommender systems are designed to aid users in information retrieval, they should be assessed not just as recommendation algorithms but also from the users’ perspective. In contrast to accuracy measures, user-related issues can only be effectively investigated via empirical studies involving real users. Furthermore, researchers are becoming increasingly aware that the effectiveness of the systems goes beyond recommendation …

Augmented & Virtual Reality: Advancement Of Technology And Its Impacts On Medicine, Education, And Other Industries, Yassine Chahid

Publications and Research

Throughout the early 2000s, the ways in which the World Wide Web was used would undergo major changes. The introduction of these changes around this time period would be collectively known as Web 2.0. With Web 2.0, accessibility and distribution of applications became more simplified. During the 2000s, much has evolved from hard capabilities to the internet and its widespread usage amongst companies and general consumers. In contemporary times, multiple technologies, both hardware and digital are becoming more advanced, with general consumers either rejecting or accepting these gradual shifts in what may become everyday technology. Web 3.0, the theoretical advancement …

Developing A Multi-Platform Application To Facilitate Internal Campus Hiring, Carissa Patton

Computer Science and Computer Engineering Undergraduate Honors Theses

Undergraduate research has proven to be highly beneficial to students, yet there are many students who do not know how to get involved or who are too timid to approach professors to inquire about potential research opportunities. Our hypothesis is that a cross-platform application has the potential to bridge the gap and help more students get involved in undergraduate research by providing them information about open positions and the faculty or staff members who are mentoring the projects. The key focus of this thesis is to develop an application that provides details about participating faculty or staff including their research …

Culture In Computing: The Importance Of Developing Gender-Inclusive Software, Creighton France

Computer Science and Computer Engineering Undergraduate Honors Theses

The field of computing as we know it today exists because of the contributions of numerous female mathematicians, computer scientists, and programmers. While working with hardware was viewed as “a man’s job” during the mid-20th century, computing and programming was viewed as a noble and high-paying field for women to occupy. However, as time has progressed, the U.S. has seen a decrease in the number of women pursuing computer science. The idea that computing is a masculine discipline is common in the U.S. today for reasons such as male-centered marketing of electronics and gadgets, an inaccurate representation of what it …