Graphics and Human Computer Interfaces Commons^™

Focus: Evaluating Pre-Trained Vision-Language Models On Underspecification Reasoning, Kankan Zhou, Yibin Lai, Kyriakos Mouratidis, Jing Jiang

Research Collection School Of Computing and Information Systems

Humans possess a remarkable ability to interpret underspecified ambiguous statements by inferring their meanings from contexts such as visual inputs. This ability, however, may not be as developed in recent pre-trained visionlanguage models (VLMs). In this paper, we introduce a novel probing dataset called FOCUS to evaluate whether state-of-the-art VLMs have this ability. FOCUS consists of underspecified sentences paired with image contexts and carefully designed probing questions. Our experiments reveal that VLMs still fall short in handling underspecification even when visual inputs that can help resolve the ambiguities are available. To further support research in underspecification, FOCUS will be released …

Dreamanime: Learning Style-Identity Textual Disentanglement For Anime And Beyond, Chenshu Xu, Yangyang Xu, Huaidong Zhang, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Text-to-image generation models have significantly broadened the horizons of creative expression through the power of natural language. However, navigating these models to generate unique concepts, alter their appearance, or reimagine them in unfamiliar roles presents an intricate challenge. For instance, how can we exploit language-guided models to transpose an anime character into a different art style, or envision a beloved character in a radically different setting or role? This paper unveils a novel approach named DreamAnime, designed to provide this level of creative freedom. Using a minimal set of 2-3 images of a user-specified concept such as an anime character …

Quantizing Text-Attributed Graphs For Semantic-Structural Integration, Jianyuan Bo, Hao Wu, Yuan Fang

Research Collection School Of Computing and Information Systems

Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains. With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for graph learning. However, current approaches face significant challenges in embedding structural information into LLM-compatible formats, requiring either computationally expensive alignment mechanisms or manual graph verbalization techniques that often lose critical structural details. Moreover, these methods typically require labeled data from source domains for effective transfer learning, significantly constraining their adaptability. We propose STAG, a novel self-supervised framework that directly quantizes graph structural information into discrete tokens using …

Graph Positional Autoencoders As Self-Supervised Learners, Yang Liu, Deyu Bo, Wenxuan Cao, Yuan Fang, Yawen Li, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability. Typically, GAEs take incomplete graphs as input and predict missing elements, such as masked node features or edges. Although effective, our experimental investigation reveals that traditional feature or edge masking paradigms primarily capture low-frequency signals in the graph and fail to learn expressive structural information. To address these issues, we propose Graph Positional Autoencoders (GraphPAE), which employ a dual-path architecture to reconstruct both node features and positions. Specifically, the feature path …

Relightable Neural Radiance Fields For Novel View Synthesis, Malena I. Mahoney

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

This paper describes relighting neural radiance fields for novel view synthesis. View synthesis is the problem of using input images with corresponding camera angles to produce a photorealistic 3D model of an environment and its objects. Neural radiance fields (NeRFs) were created as a solution to view synthesis. Neural radiance field models work well for generating realistic 3D models from 2D image inputs; how-ever, they do not support changing the lighting or placing the objects from the input images into different environments. The problem comes from the fact that NeRFs rely on a neural network that is essentially overfitted to …

Modern Procedural Terrain Generation Techniques And Their Background, Hunter A. Barton

2025 Symposium

Procedural terrain generation has become a staple in many digital environments, enabling the automated creation of large-scale and realistic landscapes for applications such as video games and movies. This paper provides an in-depth look at smooth noise functions and their use for terrain generation, as well as an overview of some more modern methods of generation. A method utilizing machine learning stlye transfer was reproduced for this paper with some alterations to improve visualization and realism.

Enhancing Graph Representation Learning Through Self-Supervision: An Augmentation Perspective, Jianyuan Bo

Dissertations and Theses Collection (Open Access)

Graph representation learning has become fundamental in various domains, from social networks to molecular structures, enabling extraction of meaningful patterns from graph-structured data. While deep learning approaches, particularly graph neural networks, have shown promising results, their effectiveness is often limited by the scarcity of labeled data. This challenge is particularly acute in graph domains where annotation requires specialized expertise and is prohibitively expensive. Self-supervised learning has emerged as a promising direction to address this limitation by creating auxiliary tasks from unlabeled data, with augmentation strategies playing a crucial role in their success.

Current graph self-supervised learning methods face several critical …

Robust Relevance Feedback For Interactive Known-Item Video Search, Zhixin Ma, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Known-item search (KIS) involves only a single search target, making relevance feedback-typically a powerful technique for efficiently identifying multiple positive examples to infer user intent-inapplicable. PicHunter addresses this issue by asking users to select the top-k most similar examples to the unique search target from a displayed set. Under ideal conditions, when the user's perception aligns closely with the machine's perception of similarity, consistent and precise judgments can elevate the target to the top position within a few iterations. However, in practical scenarios, expecting users to provide consistent judgments is often unrealistic, especially when the underlying embedding features used for …

Experimental Analysis Of Satellite Operator Training Using Game-Based Virtual Reality Simulation, Lana Laskey

Doctoral Dissertations and Master's Theses

Satellite data plays a vital role in modern global infrastructure by enabling communications, navigation, and weather forecasting. As demand for satellite technology grows, so does the need for highly trained satellite ground operators. Traditional training regimens for satellite operators employ simulation using two-dimensional computer console displays paired with the varied ability of trainees to generate abstract mental imagery of the scenario. However, this development of mental imagery imposes a considerable learning curve and cognitive workload on the trainee, which may negatively impact the user experience and knowledge gained during the training scenario.

This experimental study investigated the effects of game-based …

Advancing Food Nutrition Estimation Via Visual-Ingredient Feature Fusion, Huiyan Qi, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Nutrition estimation is an important component of promoting healthy eating and mitigating diet-related health risks. Despite advances in tasks such as food classification and ingredient recognition, progress in nutrition estimation is limited due to the lack of datasets with nutritional annotations. To address this issue, we introduce FastFood, a dataset with 84,446 images across 908 fast food categories, featuring ingredient and nutritional annotations. In addition, we propose a new model-agnostic Visual-Ingredient Feature Fusion (VIF2 ) method to enhance nutrition estimation by integrating visual and ingredient features. Ingredient robustness is improved through synonym replacement and resampling strategies during training. The ingredient-aware …

Hdifftg: A Lightweight Hybrid Diffusion-Transformer-Gcn Architecture For 3d Human Pose Estimation, Yajie Fu, Chaorui Huang, Junwei Li, Hui Kong, Yibin Tian, Huakang Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

We propose HDiffTG, a novel 3D Human Pose Estimation (3DHPE) method that integrates Transformer, Graph Convolutional Network (GCN), and diffusion model into a unified framework. HDiffTG leverages the strengths of these techniques to significantly improve pose estimation accuracy and robustness while maintaining a lightweight design. The Transformer captures global spatiotemporal dependencies, the GCN models local skeletal structures, and the diffusion model provides step-by-step optimization for fine-tuning, achieving a complementary balance between global and local features. This integration enhances the model’s ability to handle pose estimation under occlusions and in complex scenarios. Furthermore, we introduce lightweight optimizations to the integrated model …

Cracking Aegis: An Adversarial Llm-Based Game For Raising Awareness Of Vulnerabilities In Privacy Protection, Jiaying Fu, Yiyang Lu, Zehua Yang, Fiona Fui-Hoon Nah, Ray Lc

Research Collection School Of Computing and Information Systems

Traditional methods for raising awareness of privacy protection often fail to engage users or provide hands-on insights into how privacy vulnerabilities are exploited. To address this, we incorporate an adversarial mechanic in the design of the dialogue-based serious game Cracking Aegis. Leveraging LLMs to simulate natural interactions, the game challenges players to impersonate characters and extract sensitive information from an AI agent, Aegis. A user study (n=22) revealed that players employed diverse deceptive linguistic strategies, including storytelling and emotional rapport, to manipulate Aegis. After playing, players reported connecting in-game scenarios with real-world privacy vulnerabilities, such as phishing and impersonation, and …

Full-Stack Web Applications: Infrastructure, Development Pipelines & Devsecops, Yassine Chahid, Patrick Slattery

Publications and Research

This research explores emerging development methodologies and technologies which facilitate the deployment and maintenance of software applications. It evaluates architectural styles for the development of software such as monolithic (legacy) and microservice models, with a focus on their key differences such as scalability or project structure through to the development of an application. By examining methodologies such as Agile and continuous integration/continuous development pipelines along with the deployment tools Docker and Git for version/release control, the study analyzes how these innovations speed up development, improve existing practices, and serve as the foundation for development operations. Cloud solutions for tasks such …

Efficient Prompt Tuning For Hierarchical Ingredient Recognition, Yinxuan Gui, Bin Zhu, Jingjing Chen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Fine-grained ingredient recognition presents a significant challenge due to the diverse appearances of ingredients, resulting from different cutting and cooking methods. While existing approaches have shown promising results, they still require extensive training costs and focus solely on fine-grained ingredient recognition. In this paper, we address these limitations by introducing an efficient prompt-tuning framework that adapts pretrained visual-language models (VLMs), such as CLIP, to the ingredient recognition task without requiring full model finetuning. Additionally, we introduce three-level ingredient hierarchies to enhance both training performance and evaluation robustness. Specifically, we propose a hierarchical ingredient recognition task, designed to evaluate model performance …

Empowering Weight Loss: A Pragmatic Randomized Controlled Trial Of A Theory-Driven Self-Regulation Mobile App For Young Adults With Excess Body Weight, H. S. J. Chew, J. W. Ngooi, R. C. Du, P. Z. Chan, M. Jansson, B. Zhu, Y. Cao, Chong-Wah Ngo, R. Foo, A. Shabbir, D. Ho, N. Sevdalis, K. Y. Ngiam

Research Collection School Of Computing and Information Systems

Background/Introduction: Obesity is projected to affect more than half of the global population by 2035, posing significant health and economic challenges. While lifestyle modification is considered a cornerstone of weight management, its effectiveness often relies on substantial support systems. Purpose: This study aimed to evaluate the effectiveness of a 12-week, standalone Temporal Self-Regulation Theory (TST)-based weight loss mobile application, which integrates self-regulation techniques, food logging, and dietary nudging, in promoting weight loss among young adults with excess body weight. Methods: A two-arm, parallel-group, 1:1 randomized controlled trial was conducted, adhering to the CONSORT-Outcomes 2022 Extension guidelines. Participants completed a face-to-face …

Retrieval Augmented Generation For Dynamic Graph Modeling, Yuxia Wu, Lizi Liao, Yuan Fang

Research Collection School Of Computing and Information Systems

Modeling dynamic graphs, such as those found in social networks, recommendation systems, and e-commerce platforms, is crucial for capturing evolving relationships and delivering relevant insights over time. Traditional approaches primarily rely on graph neural networks with temporal components or sequence generation models, which often focus narrowly on the historical context of target nodes. This limitation restricts the ability to adapt to new and emerging patterns in dynamic graphs. To address this challenge, we propose a novel framework, Retrieval-Augmented Generation for Dy namic Graph modeling (RAG4DyG ), which enhances dynamic graph predictions by incorporating contextually and temporally relevant examples from broader …

Grokformer: Graph Fourier Kolmogorov‑Arnold Transformers, Guoguo Ai, Guansong Pang, Hezhe Qiao, Yuan Gao, Hui Yan

Research Collection School Of Computing and Information Systems

Graph Transformers (GTs) have demonstrated remarkable performance in graph representation learning over popular graph neural networks (GNNs). However, self-attention, the core module of GTs, preserves only low-frequency signals in graph features, leading to ineffectiveness in capturing other important signals like high-frequency ones. Some recent GT models help alleviate this issue, but their flexibility and expressiveness are still limited since the filters they learn are fixed on predefined graph spectrum or spectral order. To tackle this challenge, we propose a Graph Fourier Kolmogorov-Arnold Transformer (GrokFormer), a novel GT model that learns highly expressive spectral filters with adaptive graph spectrum and spectral …

Instruct2see: Learning To Remove Any Obstructions Across Distributions, Junhang Li, Yu Guo, Chuhua Xian, Shengfeng He

Research Collection School Of Computing and Information Systems

Images are often obstructed by various obstacles due to capture limitations, hindering the observation of objects of interest. Most existing methods address occlusions from specific elements like fences or raindrops, but are constrained by the wide range of real-world obstructions, making comprehensive data collection impractical. To overcome these challenges, we propose Instruct2See, a novel zero-shot framework capable of handling both seen and unseen obstacles. The core idea of our approach is to unify obstruction removal by treating it as a soft-hard mask restoration problem, where any obstruction can be represented using multi-modal prompts, such as visual semantics and textual instructions, …

Action Dubber: Timing Audible Actions Via Inflectional Flow, Wenlong Wan, Weiying Zheng, Tianyi Xiang, Guiqing Li, Shengfeng He

Research Collection School Of Computing and Information Systems

We introduce the task of Audible Action Temporal Localization, which aims to identify the spatiotemporal coordinates of audible movements. Unlike conventional tasks such as action recognition and temporal action localization, which broadly analyze video content, our task focuses on the distinct kinematic dynamics of audible actions. It is based on the premise that key actions are driven by inflectional movements; for example, collisions that produce sound often involve abrupt changes in motion. To capture this, we propose T A2Net, a novel architecture that estimates inflectional flow using the second derivative of motion to determine collision timings without relying on audio …

Unambiguous Granularity Distillation For Asymmetric Image Retrieval, Hongrui Zhang, Yi Xie, Haoquan Zhang, Cheng Xu, Xuandi Luo, Donglei Chen, Xuemiao Xu, Huaidong Zhang, Pheng Ann Heng, Shengfeng He

Research Collection School Of Computing and Information Systems

Previous asymmetric image retrieval methods based on knowledge distillation have primarily focused on aligning the global features of two networks to transfer global semantic information from the gallery network to the query network. However, these methods often fail to effectively transfer local semantic information, limiting the fine-grained alignment of feature representation spaces between the two networks. To overcome this limitation, we propose a novel approach called Layered-Granularity Localized Distillation (GranDist). GranDist constructs layered feature representations that balance the richness of contextual information with the granularity of local features. As we progress through the layers, the contextual information becomes more detailed, …