Computer Sciences Commons^™

Beyond Textual Constraints : Learning Novel Diffusion Conditions With Fewer Examples, Yuyang Yu, Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Huaidong Zhang, Shengfeng He

Research Collection School Of Computing and Information Systems

In this paper, we delve into a novel aspect of learning novel diffusion conditions with datasets an order of magnitude smaller. The rationale behind our approach is the elimination of textual constraints during the few-shot learning process. To that end, we implement two optimization strategies. The first, prompt-free conditional learning, utilizes a prompt-free encoder derived from a pre-trained Stable Diffusion model. This strategy is designed to adapt new conditions to the diffusion process by minimizing the textual-visual cor-relation, thereby ensuring a more precise alignment between the generated content and the specified conditions. The second strategy entails condition-specific negative rectification, which …

Consistent3d: Towards Consistent High-Fidelity Text-To-3d Generation With Deterministic Sampling Prior, Zike Wu, Pan Zhou, Xuanyu Yi, Xiaoding Yuan, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Score distillation sampling (SDS) and its variants have greatly boosted the development of text-to-3D generation, but are vulnerable to geometry collapse and poor textures yet. To solve this issue, we first deeply analyze the SDS and find that its distillation sampling process indeed corresponds to the trajectory sampling of a stochastic differential equation (SDE): SDS samples along an SDE trajectory to yield a less noisy sample which then serves as a guidance to optimize a 3D model. However, the randomness in SDE sampling often leads to a diverse and unpredictable sample which is not always less noisy, and thus is …

Generalized Graph Prompt: Toward A Unification Of Pre-Training And Downstream Tasks On Graphs, Xingtong Yu, Zhenghao Liu, Yuan Fang, Et Al.

Research Collection School Of Computing and Information Systems

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the 'pre-train, fine-tune' and 'pre-train, prompt' paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of …

Open-Vocabulary Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Current video anomaly detection (VAD) approaches with weak supervisions are inherently limited to a closed-set setting and may struggle in open-world applications where there can be anomaly categories in the test data unseen during training. A few recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to de-tect unseen anomalies given seen anomalies and normal videos. However, such a setting focuses on predicting frame anomaly scores, having no ability to recognize the specific categories of anomalies, despite the fact that this ability is essential for building more informed video surveillance systems. This paper takes a step …

Drag Your Noise: Interactive Point-Based Editing Via Diffusion Semantic Propagation, Haofeng Liu, Chenshu Xu, Yifei Yang, Lihua Zeng, Shengfeng He

Research Collection School Of Computing and Information Systems

Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models. A concurrent work, DragDiffusion, updates the diffusion latent map in response to user inputs, causing global latent map alterations. This results in imprecise preservation of the original content and unsuccessful editing due to gradient vanishing. In contrast, we present DragNoise, offering robust and accelerated editing without retracing the latent map. The core rationale of DragNoise lies in utilizing the predicted noise output of each U-Net as a semantic editor. This approach is grounded in two critical observations: firstly, the bottleneck features of U-Net inherently …

Inceptionnext: When Inception Meets Convnext, Weihao Yu, Pan Zhou, Shuicheng Yan, Xinchao Wang

Research Collection School Of Computing and Information Systems

Inspired by the long-range modeling ability of ViTs, large-kernel convolutions are widely studied and adopted recently to enlarge the receptive field and improve model performance, like the remarkable work ConvNeXt which employs 7×7 depthwise convolution. Although such depthwise operator only consumes a few FLOPs, it largely harms the model efficiency on powerful computing devices due to the high memory access costs. For example, ConvNeXtT has similar FLOPs with ResNet-50 but only achieves ∼ 60% throughputs when trained on A100 GPUs with full precision. Although reducing the kernel size of ConvNeXt can improve speed, it results in significant performance degradation, which …

Posmlp-Video: Spatial And Temporal Relative Position Encoding For Efficient Video Recognition, Yanbin Hao, Diansong Zhou, Zhicai Wang, Chong-Wah Ngo, Xiangnan He, Meng Wang

Research Collection School Of Computing and Information Systems

In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding (RPE) to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP’s positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, …

Balancing Darkness And Visibility: An Algorithmic Approach To Light Placement In Low-Light, Ray-Traced Scenes, Briana Kuo

Master's Theses

In recent years, digital media has seen incredible advancements in rendering visually stunning computer graphics scenes. Photo-realistic games, animated films, and more leave viewers blown away by the sheer beauty of their graphics. However, challenges arise when depicting dark scenes, often resulting in visual monotony and difficulty in comprehension due to insufficient detail within the scene. In order to enhance readability and visual interest of a scene, additional, artificial lights can be placed throughout a scene to enhance the aesthetic. These lights, however, must be strategically placed in order to retain an essence of darkness and maintain the delicate balance …

Embodied Visions: Interactive Installations That Reimagine Bodily Presence In Digital Imaging Apparatuses As Shadows, Yunzi Shi

Dartmouth College Master’s Theses

Contextualized within a history of technological development, the evolution of imaging devices and technologies is accompanied by the abstraction of spatial relationships between the body of the observer, the apparatus, and physical reality, which leads to disembodying experiences for the observing subject. Compared with devices and interactive experiences, critical reflection on the epistemological impact of digital imaging devices has less priority in computational imaging and human-computer interaction research. Taking an artistic approach, this thesis describes Embodied Visions, an exhibition featuring three interactive installations exploring the technical infrastructure for imaging and reflecting on the (dis)embodied experiences in the digital age. …

Inchi Isotopologue And Isotopomer Specifications, Hunter N. B. Moseley, Philippe Rocca-Serra, Reza M. Salek, Masanori Arita, Emma L. Schymanski

Markey Cancer Center Faculty Publications

This work presents a proposed extension to the International Union of Pure and Applied Chemistry (IUPAC) International Chemical Identifier (InChI) standard that allows the representation of isotopically‑resolved chemi‑ cal entities at varying levels of ambiguity in isotope location. This extension includes an improved interpretation of the current isotopic layer within the InChI standard and a new isotopologue layer specification for representing chemical intensities with ambiguous isotope localization. Both improvements support the unique isotopically‑ resolved chemical identification of features detected and measured in analytical instrumentation, specifically nuclear magnetic resonance and mass spectrometry.

Scientific contribution

This new extension to the InChI standard …

Manipulative, Dark, And Unethical Design Practices In Ui & Ux Design, Ryan Edward Brown

Honors Theses

This thesis examines the pervasive and detrimental effects of manipulative user interface and user experience design (UI/UX) practices on individuals and society. Focusing on three critical areas – accessibility, dark patterns, and polarization – the study employs a mixed-methods approach, combining findings from a comprehensive literature review, an analysis of specific design patterns and methods, and a survey of user experiences.
The literature review covers topics such as the importance of accessibility in design education, the prevalence of dark patterns in mobile and desktop sites, the role of personalization algorithms in shaping user experiences, and the formation of echo chambers …

Companionship, Romance, And Self-Perception With Conversational Chatbots, Jonathan Windsor

Departmental Honors & Graduate Capstone Projects

Serving as a metaphorical gateway transcending the communicative barriers of physical relationships in interpersonal dialogues, artificial imators of human behavior and speech, also known as conversational chatbots; a simulation of human knowledge and existence in a bi-directional conversation, functions as a rhetor of expression. Spanning from contexts of professional to romantic, I serve to dissect and critically analyze the nuances of human-machine relationships based on pre-established literature, inviting ethical considerations and biases in their design and marketing. Corporate influences spark pre-established servitude-esque relationships with conversational agents. Professional applications, both task-oriented and emotionally based alike, paint a mixed picture of …

Simulating Cross-Scale Solid-Fluid Interaction Phenomena, Jinyuan Liu

Dartmouth College Ph.D Dissertations

Solid-fluid interactions are ubiquitous in nature, and accurate simulation methods are essential for realistic animation, industrial design, and engineering analysis. Com- pared to large-scale coupling phenomena, simulating fine-scale interactions poses extra challenges due to factors such as surface tension, material wettability, and geometric complexity. In this thesis, we pursue novel methodologies to accurately model in- terfacial dynamics between surface-tension fluids and codimensional solids, involving capillary interactions, controllable wettability, and robust contact behaviors. Our ini- tial approach involves developing a novel three-way coupling method, which utilizes a thin liquid membrane, modelled as a simplicial mesh, to facilitate accurate momen- tum transfer, …

Research Project Review: Human-Computer Interactions, Kylie E. Garcia

The Agora

A review of a body of research conducted by Dr. Gain Park, an assistant professor in the Department of Journalism and Media Studies at New Mexico State University. This review contains a summary of Dr. Park's research on human-computer interactions, commentary on its contributions and significance, as well as insights from Dr. Park.

Privacy Protection In Mobile Photography With Face Cloaking, Rithyka Heng

Computer Science and Computer Engineering Undergraduate Honors Theses

In a world of increasing connectivity, privacy is becoming ever-more difficult to maintain. People have little control over the capture of their image while in public and have even less control over the online sharing or posting of their image. This leaves many people vulnerable to being tracked or profiled via their image’s presence in other people’s photos. This thesis implements and evaluates an approach to privacy protection that involves the photographers protecting the privacy of bystanders. Because most photographs are now being taken by smartphones, a mobile application is decidedly the technology that would best achieve widespread adoption and …

An Exploration Of Procedural Methods In Game Level Design, Hector Salinas

Computer Science and Computer Engineering Undergraduate Honors Theses

Video games offer players immersive experiences within intricately crafted worlds, and the integration of procedural methods in game level designs extends this potential by introducing dynamic, algorithmically generated content that could stand on par with handcrafted environments. This research highlights the potential to provide players with engaging experiences through procedural level generation, while potentially reducing development time for game developers.

Through a focused exploration on two-dimensional cave generation techniques, this paper aims to provide efficient solutions tailored to this specific environment. This exploration encompasses several procedural generation methods, including Midpoint Displacement, Random Walk, Cellular Automata, Perlin Worms, and Binary Space …

Lecture-Style Tutorial: Towards Graph Foundation Models, Chuan Shi, Cheng Yang, Yuan Fang, Lichao Sun, Philip Yu

Research Collection School Of Computing and Information Systems

Emerging as fundamental building blocks for diverse artificial intelligence applications, foundation models have achieved notable success across natural language processing and many other domains. Concurrently, graph machine learning has gradually evolved from shallow methods to deep models to leverage the abundant graph-structured data that constitute an important pillar in the data ecosystem for artificial intelligence. Naturally, the emergence and homogenization capabilities of foundation models have piqued the interest of graph machine learning researchers. This has sparked discussions about developing a next-generation graph learning paradigm, one that is pre-trained on broad graph data and can be adapted to a wide range …

Automated Cinematographer For Vr Viewing Experiences, Zihan Wu

Dartmouth College Master’s Theses

As the virtual reality (VR) industry continues to evolve, the question of how to effectively capture VR experiences for an audience remains a challenge. The predominant method of showcasing VR applications through first-person recordings lacks cinematic interest, failing to capture other viewpoints and the essence of the moment. Meanwhile, manually setting up cameras and editing videos requires technical expertise on behalf of the user. In this paper, we propose the use of machine learning (ML) to automatically select the most compelling predefined viewpoint in a VR environment, at any given moment. Our models, trained on actor motion and voice volume, …

Vr Circuit Simulation With Advanced Visualization For Enhancing Comprehension In Electrical Engineering, Elliott Wolbach

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

As technology advances, the field of electrical and computer engineering continuously demands innovative tools and methodologies to facilitate effective learning and comprehension of fundamental concepts. Through a comprehensive literature review, it was discovered that there was a gap in the current research on using VR technology to effectively visualize and comprehend non-observable electrical characteristics of electronic circuits. This thesis explores the integration of Virtual Reality (VR) technology and real-time electronic circuit simulation with enhanced visualization of non-observable concepts such as voltage distribution and current flow within these circuits. The primary objective is to develop an immersive educational platform that makes …

Next-Generation Crop Monitoring Technologies: Case Studies About Edge Image Processing For Crop Monitoring And Soil Water Property Modeling Via Above-Ground Sensors, Nipuna Chamara

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Artificial Intelligence (AI) has advanced rapidly in the past two decades. Internet of Things (IoT) technology has advanced rapidly during the last decade. Merging these two technologies has immense potential in several industries, including agriculture.

We have identified several research gaps in utilizing IoT technology in agriculture. One problem was the digital divide between rural, unconnected, or limited connected areas and urban areas for utilizing images for decision-making, which has advanced with the growth of AI. Another area for improvement was the farmers' demotivation to use in-situ soil moisture sensors for irrigation decision-making due to inherited installation difficulties. As Nebraska …

3-D Reconstruction For Underwater Robots With A Monocular Camera And Lights, Monika Roznere

Dartmouth College Ph.D Dissertations

Before a robot can act, it must perceive its environment. Though, this is not a simple task when considering the challenges in underwater domains -- poor visibility conditions, limited sensor configurations, and lack of readily accessible localization. Underwater robots have, nevertheless, improved dramatically with more extensive sensor and navigation equipment. Robot and sensor use have enabled us to explore all reaches of our oceans. On the other hand, these same robots are not easily accessible or transferable to many practical tasks, including fishery management, infrastructure maintenance, disaster response, site conservation, and ecological surveys. There is a growing need for robots …

Exploring Diffusion Time-Steps For Unsupervised Representation Learning, Zhongqi Yue, Jiankun Wang, Qianru Sun, Lei Ji, Eric I-Chao Chang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Model (DM) in unsupervised learning of the modular attributes. We build a theoretical framework that connects the diffusion time-steps and the hidden attributes, which serves as an effective inductive bias for unsupervised learning. Specifically, the forward diffusion process incrementally adds Gaussian noise to samples at each time-step, which essentially collapses different samples into similar ones by losing attributes, e.g., fine-grained attributes such as texture are lost with less noise added (i.e., early time-steps), while coarse-grained ones such …

Diffusion-Based Negative Sampling On Graphs For Link Prediction, Yuan Fang, Yuan Fang

Research Collection School Of Computing and Information Systems

Link prediction is a fundamental task for graph analysis with important applications on the Web, such as social network analysis and recommendation systems, etc. Modern graph link prediction methods often employ a contrastive approach to learn robust node representations, where negative sampling is pivotal. Typical negative sampling methods aim to retrieve hard examples based on either predefined heuristics or automatic adversarial approaches, which might be inflexible or difficult to control. Furthermore, in the context of link prediction, most previous methods sample negative nodes from existing substructures of the graph, missing out on potentially more optimal samples in the latent space. …

Multigprompt For Multi-Task Pre-Training And Prompting On Graphs, Xingtong Yu, Chang Zhou, Yuan Fang, Xinming Zhan

Research Collection School Of Computing and Information Systems

Graph Neural Networks (GNNs) have emerged as a mainstream technique for graph representation learning. However, their efficacy within an end-to-end supervised framework is significantly tied to the availability of task-specific labels. To mitigate labeling costs and enhance robustness in few-shot settings, pre-training on self-supervised tasks has emerged as a promising method, while prompting has been proposed to further narrow the objective gap between pretext and downstream tasks. Although there has been some initial exploration of prompt-based learning on graphs, they primarily leverage a single pretext task, resulting in a limited subset of general knowledge that could be learned from the …

Multi-Script Handwriting Identification By Fragmenting Strokes, Joshua Jude Thomas

Graduate Theses and Dissertations (2019 - present)

This study tests the effectiveness of Multi-Script Handwriting Identification after simplifying character strokes, by segmenting them into sub-parts. Character simplification is performed through splitting the character by branching-points and end-points, a process called stroke fragmentation in this study. The resulting sub-parts of the character are called stroke fragments and are evaluated individually to identify the writer. This process shares similarities with the concept of stroke decomposition in Optical Character Recognition which attempts to recognize characters through the writing strokes that make them up. The main idea of this study is that the characters of different writing‑scripts (English, Chinese, etc.) may …

Exploring The Relationship Between Anxiety And Virtual Reality Sickness, David Wesley Woolverton

Graduate Theses and Dissertations (2019 - present)

As virtual reality (VR) becomes more commonly used in education, it is important to understand the technology’s weakness and mitigate any potential negative effects on student success. One adverse side-effect of VR use is simulation-induced motion sickness, known in the context of VR as VR sickness. Previous research by Howard and Van Zandt (2021) found that possessing a phobia had a significant positive correlation with VR sickness, but only if the phobia is triggered by the simulation, suggesting that symptoms are actually connected to the anxiety the phobia induces. This study explored the hypothesized correlation between anxiety and VR sickness, …

Cloud Computing Integration Into Mixed-Reality: Physical To Abstraction, Yassine Chahid, Patrick Slattery

Publications and Research

This research evaluates the progression of cloud computing and mixed-reality technologies, and to identify how these technologies influence advancements in the latter. Both cloud computing and mixed reality have significantly impacted the IT field and the services available to the public and various institutions. Cloud computing provides a valuable way to process information or allocate computational resources on otherwise limited hardware. Augmented or virtual reality hardware would greatly benefit from this by offloading resource-intensive tasks to other machines. The research methodology involves analyzing essential components of both innovations, divided into multiple categories. These components range from physical, hardware-based elements to …

The Kruger Collection Reimagined: A Case Study In 3d Scanning And Interactive Exhibit Design, Annissa Davis

Department of Anthropology: Theses and Student Research

This thesis examines the use of 3D modeling in museum exhibition to create exploratory exhibits that facilitate unique relationships between the visitors and the collection beyond what is provided by the collection’s in person counterparts. Typical use of 3D modeling in museums is currently often representative rather than exploratory. By employing a Digital Humanities lens to approach the development of a digital exhibition utilizing 3D technology and interactive elements created in a video game engine (Unity), this thesis project evaluates these potential new relationships. Using the Eloise Kruger Collection of Miniatures as a case study, the following text details the …

Instant3d: Instant Text-To-3d Generation, Ming Li, Pan Zhou, Jia-Wei Liu, Jussi Keppo, Shuicheng Yan, Xiangyu Xu

Research Collection School Of Computing and Information Systems

Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core …

Swapvid: Integrating Video Viewing And Document Exploration With Direct Manipulation, Taichi Murakami, Kazuyuki Fujita, Kotaro Hara, Kazuki Takashima, Yoshifumi Kitamura

Research Collection School Of Computing and Information Systems

Videos accompanied by documents—document-based videos—enable presenters to share contents beyond videos and audience to use them for detailed content comprehension. However, concurrently exploring multiple channels of information could be taxing. We propose SwapVid, a novel interface for viewing and exploring document-based videos. SwapVid seamlessly integrates a video and a document into a single view and lets the content behaves as both video and a document; it adaptively switches a document-based video to act as a video or a document upon direct manipulation (e.g., scrolling the document, manipulating the video timeline). We conducted a user study with twenty participants, comparing SwapVid …