Digital Commons Network^™

Efficient Cascaded Multiscale Adaptive Network For Image Restoration, Yichen Zhou, Pan Zhou, Teck Khim Ng

Research Collection School Of Computing and Information Systems

Image restoration, encompassing tasks such as deblurring, denoising, and super-resolution, remains a pivotal area in computer vision. However, efficiently addressing the spatially varying artifacts of various low-quality images with local adaptiveness and handling their degradations at different scales poses significant challenges. To efficiently tackle these issues, we propose the novel Efficient Cascaded Multiscale Adaptive (ECMA) Network. ECMA employs Local Adaptive Module, LAM, which dynamically adjusts convolution kernels across local image regions to efficiently handle varying artifacts. Thus, LAM addresses the local adaptiveness challenge more efficiently than costlier mechanisms like self-attention, due to its less computationally intensive convolutions. To construct a …

Self-Adaptive Fine-Grained Multi-Modal Data Augmentation For Semi-Supervised Muti-Modal Coreference Resolution, Li Zheng, Boyu Chen, Hao Fei, Fei Li, Shengqiong Wu, Lizi Liao, Donghong Ji

Research Collection School Of Computing and Information Systems

Coreference resolution, an essential task in natural language processing, is particularly challenging in multi-modal scenarios where data comes in various forms and modalities. Despite advancements, limitations due to scarce labeled data and underleveraged unlabeled data persist. We address these issues with a self-adaptive fine-grained multi-modal data augmentation framework for semi-supervised MCR, focusing on enriching training data from labeled datasets and tapping into the untapped potential of unlabeled data. Regarding the former issue, we first leverage text coreference resolution datasets and diffusion models,to perform fine-grained text-to-image generation with aligned text entities and image bounding boxes. We then introduce a self-adaptive selection …

Enhancing Recipe Retrieval With Foundation Models: A Data Augmentation Perspective, Fangzhou Song, Bin Zhu, Yanbin Hao, Shuo Wang

Research Collection School Of Computing and Information Systems

Learning recipe and food image representation in common embedding space is non-trivial but crucial for cross-modal recipe retrieval. In this paper, we propose a new perspective for this problem by utilizing foundation models for data augmentation. Leveraging on the remarkable capabilities of foundation models (i.e., Llama2 and SAM), we propose to augment recipe and food image by extracting alignable information related to the counterpart. Specifically, Llama2 is employed to generate a textual description from the recipe, aiming to capture the visual cues of a food image, and SAM is used to produce image segments that correspond to key ingredients in …

Risurconv : Rotation Invariant Surface Attention-Augmented Convolutions For 3d Point Cloud Classification And Segmentation, Zhiyuan Zhang, Licheng Yang, Xiang Zhiyu

Research Collection School Of Computing and Information Systems

Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several recent studies achieve rotation invariance at the cost of lower accuracies. In this work, we close this gap by proposing a novel yet effective rotation invariant architecture for 3D point cloud classification and segmentation. Instead of traditional pointwise operations, we construct local triangle surfaces to capture more detailed surface structure, based on which we can extract highly expressive rotation invariant surface properties which are …

Desk2desk : Optimization-Based Mixed Reality Workspace Integration For Remote Side-By-Side Collaboration, Ludwig Sidenmark, Tianyu Zhang, Leen Al Lababidi, Jiannan Li, Tovi Grossman

Research Collection School Of Computing and Information Systems

Mixed Reality enables hybrid workspaces where physical and virtual monitors are adaptively created and moved to suit the current environment and needs. However, in shared settings, individual users’ workspaces are rarely aligned and can vary significantly in the number of monitors, available physical space, and workspace layout, creating inconsistencies between workspaces which may cause confusion and reduce collaboration. We present Desk2Desk, an optimization-based approach for remote collaboration in which the hybrid workspaces of two collaborators are fully integrated to enable immersive side-by-side collaboration. The optimization adjusts each user’s workspace in layout and number of shared monitors and creates a mapping …

Improving Out-Of-Distribution Detection With Disentangled Foreground And Background Features, Choubo Ding, Guansong Pang

Research Collection School Of Computing and Information Systems

Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn from arbitrary distributions and exhibit deviations from in-distribution (ID) data in various dimensions, such as foreground features (e.g., objects in CIFAR100 images vs. those in CIFAR10 images) and background features (e.g., textural images vs. objects in CIFAR10). Existing methods can confound foreground and background features in training, failing to utilize the background features for OOD detection. This paper considers the importance of feature disentanglement in out-of-distribution detection and proposes the simultaneous exploitation of both foreground and …

Densetrack : Drone-Based Crowd Tracking Via Density-Aware Motion-Appearance Synergy, Yi Lei, Huilin Zhu, Jingling Yuan, Guangli Xiang, Xian Zhong, Shengfeng He

Research Collection School Of Computing and Information Systems

Drone-based crowd tracking faces difficulties in accurately identifying and monitoring objects from an aerial perspective, largely due to their small size and close proximity to each other, which complicates both localization and tracking. To address these challenges, we present the Density-aware Tracking (DenseTrack) framework. DenseTrack capitalizes on crowd counting to precisely determine object locations, blending visual and motion cues to improve the tracking of small-scale objects. It specifically addresses the problem of cross-frame motion to enhance tracking accuracy and dependability. DenseTrack employs crowd density estimates as anchors for exact object localization within video frames. These estimates are merged with motion …

Zero-Shot Object Counting With Good Exemplars, Huilin Zhu, Jingling Yuan, Zhengwei Yang, Yu Guo, Zheng Wang, Xian Zhong, Shengfeng He

Research Collection School Of Computing and Information Systems

Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a critical challenge in current ZOC methods lies in their inability to identify high-quality exemplars effectively. This deficiency hampers scalability across diverse classes and undermines the development of strong visual associations between the identified classes and image content. To this end, we propose the Visual Association-based Zero-shot Object Counting (VA-Count) framework. VACount consists of an Exemplar Enhancement Module (EEM) and a Noise Suppression Module (NSM) that synergistically refine the process of class exemplar identification …

Onerestore : A Universal Restoration Framework For Composite Degradation, Yu Guo, Yuan Gao, Yuxu Lu, Huilin Zhu, Ryan Wen Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target isolated degradation types, thereby falling short in environments where multiple degrading factors coexist. To bridge this gap, our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios. In this context, we propose OneRestore, a novel transformer-based framework designed for adaptive, controllable scene restoration. The proposed framework leverages a unique cross-attention mechanism, merging degraded scene descriptors with image features, …

Documenting Ethical Considerations In Open Source Ai Models, Haoyu Gao, Mansooreh Zahedi, Christoph Treude, Sarita Rosenstock, Marc Cheong

Research Collection School Of Computing and Information Systems

Background: The development of AI-enabled software heavily depends on AI model documentation, such as model cards, due to different domain expertise between software engineers and model developers. From an ethical standpoint, AI model documentation conveys critical information on ethical considerations along with mitigation strategies for downstream developers to ensure the delivery of ethically compliant software. However, knowledge on such documentation practice remains scarce. Aims: The objective of our study is to investigate how developers document ethical aspects of open source AI models in practice, aiming at providing recommendations for future documentation endeavours. Method: We selected three sources of documentation on …

Latent Representation Learning For Geospatial Entities, Ween Jiann Lee, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Representation learning has been instrumental in the success of machine learning, offering compact and performant data representations for diverse downstream tasks. In the spatial domain, it has been pivotal in extracting latent patterns from various data types, including points, polylines, polygons, and networked structures. However, existing approaches often fall short of explicitly capturing both semantic and spatial information, relying on proxies and synthetic features. This article presents GeoNN, a novel graph neural network-based model designed to learn spatially-aware embeddings for geospatial entities. GeoNN leverages edge features generated from geodesic functions, dynamically selecting relevant features based on relative locations. It introduces …

An Empirical Study Of Automatic Program Repair Techniques For Injection Vulnerabilities, Tingwei Zhu, Tongtong Xu, Kui Liu, Jiayuan Zhou, Xing Hu, Xin Xia, Tian Zhang, David Lo

Research Collection School Of Computing and Information Systems

Injection vulnerabilities are among the most serious and dangerous security defects, as they can be exploited by attackers to inject malicious inputs and carry out cybercrimes. Timely fixing of injection vulnerabilities is crucial. However, manual repairs of injection vulnerabilities often require specialized knowledge and are prone to errors, posing a challenge and a heavy burden on developers. In recent years, Automated Program Repair (APR) techniques have shown promising momentum in automatically fixing general defects. Yet, there has been no research on how APR techniques perform in repairing injection vulnerabilities. Therefore, in this paper, we conduct an empirical study. We first …

Gradualreality : Enhancing Physical Object Interaction In Virtual Reality Via Interaction State-Aware Blending, Hyuna Seo, Juheon Yi, Rajesh Krishna Balan, Youngki Lee

Research Collection School Of Computing and Information Systems

We present GradualReality, a novel interface enabling a Cross Reality experience that includes gradual interaction with physical objects in a virtual environment and supports both presence and usability. Daily Cross Reality interaction is challenging as the user’s physical object interaction state is continuously changing over time, causing their attention to frequently shift between the virtual and physical worlds. As such, presence in the virtual environment and seamless usability for interacting with physical objects should be maintained at a high level. To address this issue, we present an Interaction State-Aware Blending approach that (i) balances immersion and interaction capability and (ii) …

Graph Continual Learning With Debiased Lossless Memory Replay, Chaoxi Niu, Guansong Pang, Ling Chen

Research Collection School Of Computing and Information Systems

Real-life graph data often expands continually, rendering the learning of graph neural networks (GNNs) on static graph data impractical. Graph continual learning (GCL) tackles this problem by continually adapting GNNs to the expanded graph of the current task while maintaining the performance over the graph of previous tasks. Memory replay-based methods, which aim to replay data of previous tasks when learning new tasks, have been explored as one principled approach to mitigate the forgetting of the knowledge learned from the previous tasks. In this paper we extend this methodology with a novel framework, called Debiased Lossless Memory replay (DeLoMe). Unlike …

A Fresh Look At Judicial Remedies In Eu Equality Law And Beyond: The Untapped Possibility Of Structural Injunctions., Daniel H. Halberstam, Sina Van Den Bogaert

Articles

This article proposes a shift in thinking about judicial remedies (or “sanctions”), from anti-discrimination law to equal pay and beyond.We suggest the currently preferred remedies – one-off declarations, compensation, fines, and simple orders to obey the law – may be insufficient when confronting a recalcitrant institution, complex violations, and broad, ongoing harm. In such cases, we suggest considering a remedy long overlooked in Europe: a “structural injunction”, i.e. ordering changes to an offending organization’s structure, processes, or rules. We argue that under certain circumstances, an injunction, including a structural injunction, may be appropriate or required under EU law to remedy …

The Origins Of The Major Questions Doctrine, Rachel Rothschild

Articles

In a series of recent cases, the Supreme Court has invoked the newly named “major questions doctrine” to strike down agency regulations that protect public health and the environment. Several Justices have argued that while the name “major questions” may be new, these decisions are simply the latest iteration in a longstanding effort of the courts to curtail the explosive growth of the administrative state since 1970. The first paradigmatic example of this line of cases is the 1980 “Benzene” case, in which the Supreme Court set aside the Occupational Safety and Health Administration (OSHA)’s new workplace standards for the …

Cal Poly Humboldt Library Digest, October 2024, Cal Poly Humboldt Library

Library Publications

No abstract provided.

Check Out The Library, 2024 Fall Issue, Cal Poly Humboldt Library

Library Publications

No abstract provided.

Response To Letter To The Editor Concerning The Article "The Clinical And Economic Impact Of Extended Battery Longevity Of A Substernal Extravascular Implantable Cardioverter Defibrillator"., Bradley P Knight, Nicolas Clémenty, Anish Amin, Ulrika Maria Birgersdotter-Green, Henri Roukoz, Reece Holbrook, Jaimie Manlucu

Heart and Vascular Articles

No abstract provided.

Impact Of Functional Recovery On Patients Having Heart Surgery., Richard J Snow, Lauren Mckown, Geoffrey Blossom, Karen Vogel, Amy Creighton, Jason Shriver, Linda Will, Katie Lentz, Elizabeth Snow, Teresa Caulin-Glaser

Heart and Vascular Articles

OBJECTIVE: To describe the results of a program developed to manage institutional postacute care (IPAC) (postacute skilled nursing, inpatient rehabilitation facility, and long-term acute care) in a CMS Bundled Payments for Care Improvement (BPCI) project for coronary artery bypass graft (CABG) surgery.

STUDY DESIGN: We compared pre- and postutilization patterns during a 3-year period by evaluating risk-adjusted national, state, and other BPCI participant comparisons using a difference-in-differences (DID) analysis in a large urban community tertiary center with a CABG surgery program. Included in the analysis were all Medicare patients receiving CABG surgery at the institution (n = 504), across the …

Fabrication And Evaluation Of Multicomponent Biomimetic Scaffolds For Bone Tissue Engineering, Mozan Osman Hassan

Dissertations

Bones have an inherent ability to remodel, but critical-size defects can hinder regeneration, leading to delayed healing or non-union fractures. Traditional bone grafts have limitations, such as donor site morbidity and immune rejection, driving the need for synthetic bone substitutes. Bone tissue engineering (BTE) addresses this by developing biomimetic scaffolds that replicate bone properties. This research aimed to fabricate composite scaffolds from strontium (Sr) and zinc (Zn) doped nano-hydroxyapatite (nHAp), collagen, and poly(lactide-co-glycolide) (PLGA). Different doping percentages of Sr/Zn (1%, 2.5%, 4%) were used to fabricate the scaffolds using supercritical CO2 (ScCO2) and electrospinning techniques. Scaffolds were then analyzed for …

A Quantitative Study Assessing The Impact Of Financial Sector Safeguards Rules On Us Publicly Traded Companies' Cybersecurity Breach Frequency And Severity, Alan Dinerman

School of Public Service Theses & Dissertations

Cybersecurity failure in the private sector is a growing federal policy priority. Nevertheless, US policy makers struggle with policy instrumentation in this domain. Behavioral public policy theory asserts that a linkage exists between policy target behavioral & cultural attributes and effective policy tool instrumentation. The federal government is now embracing a regulation heavy approach, but little empirical study exists at the nexus of behavioral public policy theory and use of regulatory tools in the cybersecurity policy domain. Since the early 2000s, the financial sector has employed a regulation heavy approach using the Safeguards regulations to facilitate cybersecurity in financial private …

How Multilingual Writers Talk About, Write About, And Engage With Sources In First-Year Composition, Mary Ann Zehr

English Theses & Dissertations

This study makes a contribution to the rhetoric and composition field by documenting the research and writing processes of a diverse group of 15 multilingual writers in first-year composition (FYC) at a small private southeastern university. I collected and analyzed data from three assignments: 1) a video think-aloud capturing participants’ first online search for sources, 2) a two-page reflection on the use of sources in the first full draft of students’ research paper, and 3) their first full draft of the research paper. The study is the first to systematically examine how multilingual writers in FYC at a U.S. university …

Intercellular Mitochondrial Transfer Contributes To Microenvironmental Fate Redirection Of Mammary Cancer Cells, Julie Sofie Bjerring

Biomedical Sciences Theses & Dissertations

The dynamic cellular microenvironment, made up of resident cells and various macromolecules, differs markedly across tissues in the body. The multidirectional signals that cells receive from this microenvironment, along with the signaling they send back, heavily influence their physiology and behavior. Recent important findings have further validated this notion as the mammary microenvironment has been shown to suppress tumor progression by redirecting cancer cells to adopt a normal mammary epithelial progenitor fate in vivo. However, the mechanism(s) driving changes in metabolic reprogramming and cancer fate redirection is understudied. The work presented in this dissertation focuses on exploring the impact of …

Real-Time Navigation System For Breast Cancer Surgery With Pre- And Intra-Operative Imaging Using Neural Networks, Motaz Alqaoud

Biomedical Engineering Theses & Dissertations

Breast cancer is one of the most frequently diagnosed malignancies in women worldwide, necessitating precise diagnosis and treatment. Breast-conserving surgery (BCS) is the primary treatment for nonpalpable cases, yet current approaches often lack accuracy due to the absence of real-time 3D imaging during surgery. This limitation impairs surgeons’ ability to visualize tumor locations, compromising outcomes and potentially leading to repeat surgeries with higher risks, undesirable cosmetic results, increased costs, and, in some cases, mastectomy. Thus, there is a critical need for a navigation system to facilitate accurate tumor excision in nonpalpable breast cancer through real-time patient-specific 3D tracking.

This study …

Investigating The Effects Of Empathy On Implicit Race Bias, Macy Kisiel

Psychology Theses & Dissertations

Over the years there have been changes to social norms, which now discourage expressions of prejudice, and changes in many people’s self-reported attitudes, but prejudice is still a major issue in present-day American society. One important step toward addressing prejudice and social injustices is to understand the psychological processes that underlie and strengthen them. The current study aimed to use an empathy passage to positively prime the schema about a minority person of color and manipulate regulation of implicit bias. The study utilized a mixed 2 × 2 design. Sixty-four participants (Mage = 20.88 years, SD = 4.75 years) were …

A New Era Of Deference: From Chevron To Loper Bright, Daniel E. Walters

Faculty Scholarship

Deference to administrative agencies’ interpretations of ambiguous statutory provisions has been a hallmark of administrative law and regulatory policy for the past forty years. The Supreme Court recently upended that settled allocation of power between agencies and courts, granting interpretive primacy to courts even where statutes essentially require policy choices. However, questions remain about precisely how courts will exercise this policymaking authority that agencies used to exercise, as well as about the multiple “offramps” from this nondeferential standard that the Court left open. Rather than a new era of nondeference, it is just as likely we are embarking on a …

Cisg, Wayne R. Barnes

Faculty Scholarship

This survey article discusses cases during the prior year, which are decided based on one or more provisions of the United Nations Convention on Contracts for the International Sale of Goods (CISG). The CISG is a United Nations treaty that provides a uniform international sales law. It was adopted in Vienna in 1980 and went into effect in 1988. The CISG governs contracts for the international sale of goods between businesses located in different countries that have ratified the treaty. It has been adopted by 95+ countries, including major trading nations like the United States, China, and most European countries. …

Uniform Commercial Code: Introduction, Jennifer S. Martin, Colin P. Marks, Wayne R. Barnes

Faculty Scholarship

The survey that follows highlights the most important developments of 2023 dealing with domestic and international sales of goods, personal property leases, payments, letters of credit, documents of title, investment securities, and secured transactions. Along with the usual descriptions of interesting judicial decisions highlighted in the survey, there has also been legislative progress in several areas. The 2022 Amendments to the Uniform Commercial Code ("U.C.C.") (the "2022 Amendments") have been adopted in twenty-four states plus the District of Colombia and introduced in five states.

Editorial: Novel Computational Fluid Dynamics Methods For Diagnosis, Monitoring, Prediction, And Personalized Treatment For Cardiovascular Disease And Cancer Metastasis, Zahra Keshavarz Motamed, Nima Maftoon, Lakshmi Prasad Dasi, John F. Ladisa Jr.

Biomedical Engineering Faculty Research and Publications

No abstract provided.