Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Artificial Intelligence and Robotics (1388)
- Engineering (887)
- Computer Engineering (500)
- Numerical Analysis and Scientific Computing (363)
- Social and Behavioral Sciences (350)
-
- Databases and Information Systems (312)
- Operations Research, Systems Engineering and Industrial Engineering (309)
- Software Engineering (269)
- Information Security (265)
- Systems Science (245)
- Medicine and Health Sciences (206)
- Graphics and Human Computer Interfaces (199)
- Data Science (185)
- Education (180)
- Electrical and Computer Engineering (174)
- Business (160)
- Life Sciences (152)
- Theory and Algorithms (144)
- Public Affairs, Public Policy and Public Administration (132)
- Other Computer Sciences (121)
- Arts and Humanities (114)
- Mathematics (114)
- Science and Technology Policy (86)
- Physics (85)
- Technology and Innovation (72)
- Programming Languages and Compilers (67)
- Cybersecurity (65)
- Chemistry (60)
- Institution
-
- Singapore Management University (660)
- China Simulation Federation (242)
- Old Dominion University (199)
- Kennesaw State University (173)
- Missouri University of Science and Technology (117)
-
- Neutrosophic Systems with Applications (112)
- Utah State University (92)
- Chinese Academy of Sciences (82)
- Chulalongkorn University (81)
- Zayed University (76)
- University of Texas at El Paso (69)
- Edith Cowan University (56)
- Air Force Institute of Technology (54)
- Lindenwood University (53)
- Dartmouth College (52)
- TÜBİTAK (51)
- Karbala International Journal of Modern Science (49)
- University of Nebraska - Lincoln (47)
- Chapman University (45)
- University of South Florida (40)
- Portland State University (39)
- Clemson University (36)
- United Arab Emirates University (35)
- University of Texas Rio Grande Valley (32)
- Michigan Technological University (31)
- University of Arkansas, Fayetteville (31)
- City University of New York (CUNY) (30)
- California Polytechnic State University, San Luis Obispo (27)
- Loyola University Chicago (27)
- The Texas Medical Center Library (25)
- Keyword
-
- Machine learning (213)
- Artificial intelligence (209)
- Deep learning (122)
- Artificial Intelligence (112)
- Machine Learning (94)
-
- Cybersecurity (64)
- Generative AI (59)
- AI (58)
- Deep Learning (58)
- Technical Reports (58)
- UTEP Computer Science Department (58)
- Computer Science (51)
- Natural language processing (45)
- ChatGPT (41)
- Security (41)
- Privacy (38)
- Computer vision (36)
- Large language models (35)
- Reinforcement learning (35)
- Large Language Models (33)
- Blockchain (31)
- Classification (28)
- Neural networks (28)
- Algorithms (27)
- Engineering (26)
- Humans (26)
- Large Language Model (24)
- Optimization (23)
- Federated learning (22)
- Natural Language Processing (22)
- Publication
-
- Research Collection School Of Computing and Information Systems (583)
- Journal of System Simulation (242)
- C-Day Computing Showcase (131)
- Neutrosophic Systems with Applications (112)
- Theses and Dissertations (102)
-
- Bulletin of Chinese Academy of Sciences (Chinese Version) (82)
- Chulalongkorn University Theses and Dissertations (Chula ETD) (81)
- Computer Science Faculty Research & Creative Works (81)
- All Works (76)
- Computer Science Faculty Publications (63)
- Departmental Technical Reports (CS) (58)
- Research outputs 2022 to 2026 (53)
- Turkish Journal of Electrical Engineering and Computer Sciences (51)
- Faculty Scholarship (50)
- Karbala International Journal of Modern Science (49)
- Teaching and Generative AI: Pedagogical Possibilities and Productive Tensions (46)
- USF Tampa Graduate Theses and Dissertations (38)
- Dissertations and Theses Collection (Open Access) (35)
- Faculty Publications (32)
- Dissertations (28)
- Theses (27)
- Computer Science: Faculty Publications and Other Works (26)
- Computer Science Senior Theses (24)
- Master's Theses (24)
- ICT (22)
- McKelvey School of Engineering Graduate Student Theses & Dissertations (20)
- All Graduate Theses and Dissertations, Fall 2023 to Present (19)
- Electrical & Computer Engineering Faculty Publications (19)
- Electrical and Computer Engineering Faculty Research & Creative Works (19)
- Electronic Theses and Dissertations (19)
- Publication Type
- File Type
Articles 721 - 750 of 3697
Full-Text Articles in Computer Sciences
Reducing Selection Bias In The Training Data Of Asl Champ! To Improve The Sign Language Recognition (Slr) System, Nushla Pradhan '26, Laine Silverman
Reducing Selection Bias In The Training Data Of Asl Champ! To Improve The Sign Language Recognition (Slr) System, Nushla Pradhan '26, Laine Silverman
Annual Student Research Poster Session
American Sign Language (ASL) is a natural language that is critical for effective communication within the Deaf community and also to bridge the gap between hearing and Deaf or Hard-of-Hearing individuals. Conventional methods of ASL learning apart from in person classroom instruction provide foundational knowledge but often lack the immersive and interactive elements. People often opt to learn ASL through textbooks and videos due to the limited availability of proficient ASL instructors, lack of other educational resources and limited time. This creates challenges of replicating real-life conversational scenarios and lack of real time feedback. To address these limitations, Virtual Reality …
Optimizing Transport Predictive Modeling With Simulation-Based Statistical Inference, Quyen Tran '27, Mamunur Rashid
Optimizing Transport Predictive Modeling With Simulation-Based Statistical Inference, Quyen Tran '27, Mamunur Rashid
Annual Student Research Poster Session
Simulation-based statistical inference (SBI) leverages computer simulations to help scientists understand and analyze complex data. This project explores how SBI techniques can be used to analyze transportation data. We use modern computational methods, including machine learning models, to improve the accuracy of predictions and decision-making in transportation planning. Our study focuses on applying two SBI methods, Approximate Bayesian Computation - Markov Chain Monte Carlo and Synthetic Likelihood, to create synthetic data for training machine learning models. These models show the potential of SBI to handle uncertain data. It also highlights the practical benefits of SBI in making predictions and decisions …
Bibliography For "Ai: The Next Chapter Display", Arianna Tillman, Isabella Piechota
Bibliography For "Ai: The Next Chapter Display", Arianna Tillman, Isabella Piechota
Library Displays and Bibliographies
A bibliography created to support a display about artificial intelligence at the Leatherby Libraries during Fall 2024 at the Leatherby Libraries at Chapman University.
A Survey Of Unikernel Security: Insights And Trends From A Quantitative Analysis, Alex Wollman, John Hastings
A Survey Of Unikernel Security: Insights And Trends From A Quantitative Analysis, Alex Wollman, John Hastings
Research & Publications
Unikernels, an evolution of LibOSs, are emerging as a virtualization technology to rival those currently used by cloud providers. Unikernels combine the user and kernel space into one ``uni''fied memory space and omit functionality that is not necessary for its application to run, thus drastically reducing the required resources. The removed functionality is significant however, and includes components that have become common security technologies such as Address Space Layout Randomization (ASLR), Data Execution Prevention (DEP), and Non-executable bits (NX bits). This raises questions about the security of unikernels. This research presents a quantitative methodology using TF-IDF to analyze the focus …
Solubility Characterization Of Organic Molecules For Aqueous Organic Redox Flow Batteries, Anthony W. Ferrell, Harkeerith K. Vij, Seamus D. Jones
Solubility Characterization Of Organic Molecules For Aqueous Organic Redox Flow Batteries, Anthony W. Ferrell, Harkeerith K. Vij, Seamus D. Jones
College of Engineering Summer Undergraduate Research Program
The major obstacle to renewable energy sources is a lack of long-term energy storage capabilities. Energy produced during the day dissipates, leaving insufficient electricity for at night. The goal of the project is to design an Aqueous Organic Redox Flow Battery (AORFB) to act as long-term energy storage. Work has been done using machine learning to identify suitable compounds for the batteries. In this work there was no indication as to the aqueous solubility of the molecules; this controls the device’s energy storage capabilities. We used a machine learning model to determine the aqueous solubility of slightly more than 3000 …
Targeting Federated Learning: A Study Of Membership Inference Attacks On Healthcare Data, Brett W. Hillyard, Aditi S. Lappathi
Targeting Federated Learning: A Study Of Membership Inference Attacks On Healthcare Data, Brett W. Hillyard, Aditi S. Lappathi
College of Engineering Summer Undergraduate Research Program
This study investigates the vulnerabilities of federated learning models in the healthcare domain, specifically focusing on membership inference attacks (MIA). Federated learning allows local models to train on sensitive healthcare data without sharing the data itself, making it an attractive method for protecting privacy. However, even in this decentralized framework, models remain vulnerable to MIAs, where attackers can infer whether certain data points were used to train a model by analyzing model updates. Using the Texas100 dataset, this study demonstrates that as the number of local models increases, the attack accuracy of MIAs also increases due to higher bias …
Fast And High-Resolution View Synthesis From A Single Input Panorama, Nam Nguyen, Angela V. Chen, Theresa Zhu, Seth Johnson, Pranav Dumpa, Benjamin Geil
Fast And High-Resolution View Synthesis From A Single Input Panorama, Nam Nguyen, Angela V. Chen, Theresa Zhu, Seth Johnson, Pranav Dumpa, Benjamin Geil
College of Engineering Summer Undergraduate Research Program
We introduce a novel method to convert a single input panorama into a 3D colored mesh representation of the scene. Unlike recent methods based on neural rendering, which are limited to low-resolution inputs and offline rendering, our approach supports 4k resolution inputs and real time rendering in a virtual reality headset. We first estimate a depth map and produce an initial layered depth image (LDI) representation. We fill unseen regions behind objects by iteratively cutting and inpainting the LDI. We then convert the LDI into an optimized, texture mapped mesh to achieve a compact representation
Optimizing Sensor Placements For Fixed Source Localization: A Distinct Subset Distance Sum Problem, Peter Chinh
Optimizing Sensor Placements For Fixed Source Localization: A Distinct Subset Distance Sum Problem, Peter Chinh
College of Engineering Summer Undergraduate Research Program
This research addresses the problem of optimizing sensor placements for fixed source localization using distinct subset distance sums. Given a line L in R2 and a set P of n points on one side of L, we seek to locate a minimal set S of points on L such that for any two distinct subsets Q and R of P, there exists a point s∈S where the sum of reciprocal distances from Q to s uniquely identifies Q. Our results show that a minimal sensor set S of size 1 is always feasible, but computing this set exactly proves …
"Deep Learning For Microscope Image Denoising", Nasreen Buhn, Sriya Adunur, Guy Hagen, Jonathan Ventura
"Deep Learning For Microscope Image Denoising", Nasreen Buhn, Sriya Adunur, Guy Hagen, Jonathan Ventura
College of Engineering Summer Undergraduate Research Program
In order to avoid damaging live cells, optical microscope imaging must be conducted under low-excitation light intensity and/or short exposure times, resulting in low signal-to-noise ratios (SNR). Deep learning methods offer an effective solution for removing microscope noise, utilizing algorithms that are able to reconstruct finer features in low SNR images. This research explores the denoising capability of several deep learning methods based on PSNR and SSIM. Tested methods include traditional approaches (BMED), supervised learning (CARE and Restormer), and unsupervised methods (Noise2Fast, N2V, SSD-Unsupervised, and SASSID). The Restormer model, which employs an encoder-decoder transformer architecture and progressive learning, stood out …
Empirical Support For Algorithmic Conjectures, Shayan Daijavad
Empirical Support For Algorithmic Conjectures, Shayan Daijavad
College of Engineering Summer Undergraduate Research Program
Our project focuses on a particular Markov Chain Monte Carlo algorithm, with applications in statistical physics, known as hardcore model Glauber dynamics. The target distribution of Glauber dynamics is a distribution of all of the independent sets within a graph. An independent set is a set of vertices within a graph with no two vertices in the set containing an edge between them. Our goal is to find whether or not the Glauber dynamics for sampling independent sets on trees mixes in time O(nlogn), and determining how the mixing time changes if we bias the algorithm in favor of larger …
Measurement Automation & Measurement System Research Endowment, Brian Bivinetto, Beneda Loya, Shiron Bendrihem
Measurement Automation & Measurement System Research Endowment, Brian Bivinetto, Beneda Loya, Shiron Bendrihem
College of Engineering Summer Undergraduate Research Program
Road travel safety is always the most important issue in transportation systems. In general, several factors cause road accidents, such as human error, vehicle mechanical failure, roadway limitations (e.g. pavement, lane geometry, etc.), and inclement weather conditions. The major focus of today’s transportation developments is related to making highway transportation safer, smarter, and greener to enhance livability. Many accidents are caused when drivers lack a better understanding of the surrounding traffic conditions because the driver not only needs to control his/her vehicle but also needs to be aware of the movements of the vehicles around him/her. A driver cannot be …
Digital Twin For Shelf Intelligence: Ai-Driven Inventory Management For Minimizing Food Waste, Charlotte Maples, Marvin Velazquez
Digital Twin For Shelf Intelligence: Ai-Driven Inventory Management For Minimizing Food Waste, Charlotte Maples, Marvin Velazquez
College of Engineering Summer Undergraduate Research Program
This project aims to develop a solution for improving grocery store inventory management by leveraging AI-driven image recognition. Traditional inventory methods, which rely on manual counting or barcode scanning, are inefficient, labor-intensive, and prone to human error. Over an 8-week period, we designed and developed a basic iPad app capable of identifying specific types of fruit and automatically updating inventory records in real time. By utilizing the iPad’s camera and machine learning algorithms, the app demonstrates the potential to streamline inventory tracking, reduce manual labor, and improve accuracy in managing perishable goods. Future work will focus on expanding the app’s …
Surrogate Models For Stress-Strain Mapping Of Microscale Physics, Samuel Roach, Dr. Eric Ocegueda
Surrogate Models For Stress-Strain Mapping Of Microscale Physics, Samuel Roach, Dr. Eric Ocegueda
College of Engineering Summer Undergraduate Research Program
•Learn the difference between different neural networks within machine learning (ML) •Develop a working understanding of the ML tool Pytorch and machine learning operator: Recurrent Neural Operator •Use MATLAB to create and process time dependent stress/strain matrices to display the hyper-parameters for different RNOs •Apply RNO to train the strain-stress mapping of tri-laminate and granular cases
Enhancing Place-Based Interaction With Emotion Ai And Augmented Reality, Jake Maier, Ivan Martinez
Enhancing Place-Based Interaction With Emotion Ai And Augmented Reality, Jake Maier, Ivan Martinez
College of Engineering Summer Undergraduate Research Program
This project explores the integration of augmented reality (AR) and Emotion AI technologies to enhance user experiences in physical environments. By seamlessly merging virtual elements with real-world contexts, we aim to deepen individuals’ interactions and perceptions of their surroundings. Leveraging AR technology enables users to access contextual information, engage with interactive content, and navigate spaces with heightened immersion and understanding. Additionally, Emotion AI enhances these experiences by detecting and responding to users’ emotional states, fostering personalized and emotionally resonant interactions. We aim to integrate digital content within physical environments using mixed-reality headsets equipped with eye-tracking capabilities and consumer-grade wireless EEG …
Leveraging Tradespace-Exploration For A Senior Project Team Formation Application, Miguel Saenz
Leveraging Tradespace-Exploration For A Senior Project Team Formation Application, Miguel Saenz
College of Engineering Summer Undergraduate Research Program
This project revolves around the development of an app in MATLAB that leverages the VASSAR rule-based system and a genetic algorithm to form groups of teams for the Mechanical Engineering Senior Design project class. We leveraged the iterative design process to eventually attain a functional app with a reasonable runtime that works provided correctly formatted rulesheets describing student project preference and member preference.
Reversing File Access Control Using Disk Forensics On Low-Level Flash Memory, Caleb J. Rother, Bo Chen
Reversing File Access Control Using Disk Forensics On Low-Level Flash Memory, Caleb J. Rother, Bo Chen
Michigan Tech Publications
In the history of access control, nearly every system designed has relied on the operating system (OS) to enforce the access control protocols. However, if the OS (and specifically root access) is compromised, there are few if any solutions that can get users back into their system efficiently. In this work, we have proposed a novel approach that allows secure and efficient rollback of file access control after an adversary compromises the OS and corrupts the access control metadata. Our key observation is that the underlying flash memory typically performs out-of-place updates. Taking advantage of this unique feature, we can …
Cisc 3310 Principles Of Computer Architecture, Miriam Briskman
Cisc 3310 Principles Of Computer Architecture, Miriam Briskman
Open Educational Resources
Introduction to digital logic. Basic digital circuits. Boolean algebra and combinational logic, data representation and transfer, digital arithmetic. Instruction sets. Introduction to assembly languages ALU and memory reference instructions, flow control, subroutine linkage, arrays and structures. Memory. I/O systems. Performance. Relationship between software and architecture.
Cisc 3130 Data Structures, Moshe Lach
Cisc 3130 Data Structures, Moshe Lach
Open Educational Resources
Container classes: their design, implementations, and applications. Sequences: vectors, linked lists, stacks, queues, deques, lists. Associative structures: sets, maps and their hash and tree underlying representations. Sorting and searching techniques. Collection frameworks and hierarchies.
Towards A Unified Xai-Based Framework For Digital Forensic Investigations, Zainab Khalid, Farkhund Iqbal, Benjamin C.M. Fung
Towards A Unified Xai-Based Framework For Digital Forensic Investigations, Zainab Khalid, Farkhund Iqbal, Benjamin C.M. Fung
All Works
Explainable Artificial Intelligence (XAI) aims to alleviate the black-box AI conundrum in the field of Digital Forensics (DF) (and others) by providing layman-interpretable explanations to predictions made by AI models. It also handles the increasing volumes of forensic images that are impossible to investigate via manual methods; or even automated forensic tools. A holistic, generalized, yet exhaustive framework detailing the workflow of XAI for DF is proposed for standardization. A case study examining the implementation of the framework in a network forensics investigative scenario is presented for demonstration. In addition, the XAI-DF project lays the basis for a collaborative effort …
Promise And Peril Of Collaborative Code Generation Models : Balancing Effectiveness And Memorization, Zhi Chen, Lingxiao Jiang
Promise And Peril Of Collaborative Code Generation Models : Balancing Effectiveness And Memorization, Zhi Chen, Lingxiao Jiang
Research Collection School Of Computing and Information Systems
In the rapidly evolving field of machine learning, training models with datasets from various locations and organizations presents significant challenges due to privacy and legal concerns. The exploration of effective collaborative training settings, which are capable of leveraging valuable knowledge from distributed and isolated datasets, is increasingly crucial. This study investigates key factors that impact the effectiveness of collaborative training methods in code next-token prediction, as well as the correctness and utility of the generated code, showing the promise of such methods. Additionally, we evaluate the memorization of different participant training data across various collaborative training settings, including centralized, federated, …
Can Federated Learning Solve Ai’S Data Privacy Problem?: A Legal Analysis, Warren B. Chik, Florian Gamper
Can Federated Learning Solve Ai’S Data Privacy Problem?: A Legal Analysis, Warren B. Chik, Florian Gamper
Research Collection Yong Pung How School Of Law
Federated learning (FL) is a method of training AI systems on different datasets without sharing data. The promise of FL is to enable AI systems to be trained on data, including personal data, while preserving data privacy and confidentiality, and thus, inter alia, facilitate compliance with data protection legislation. FL has generated a considerable interest amongst the computer science community, yet there is a dearth of legal analysis of FL. This is a problem because the question of whether FL facilitates compliance with data protection legislation is a legal question. This article will fill this lacuna by providing a comprehensive …
Symbolic Regression For Data-Driven Equation Discovery: A Physics-Informed Approach, Anusha Reddy Singireddy
Symbolic Regression For Data-Driven Equation Discovery: A Physics-Informed Approach, Anusha Reddy Singireddy
Computer Science Theses & Dissertations
Symbolic Regression (SR) is a cutting-edge machine learning technique that discovers mathematical expressions representing the underlying patterns in data. Unlike traditional regression, SR explores a wide range of mathematical models, allowing for flexible and interpretable solutions. We utilize PySR, a highly customizable symbolic regression package, which combines genetic programming and modern optimization methods to efficiently search for interpretable equations. PySR balances model complexity with performance by penalizing overly complex expressions while optimizing accuracy. In this thesis, we apply Physics-informed Symbolic Regression through PySR to model the x and t dependence of the flavor isovector combination Hu − d( …
Etdsuite: A Toolkit To Mine Electronic Theses And Dissertations To Enrich Scholarly Big Data Using Natural Language Processing And Computer Vision, Muntabir Hasan Choudhury
Etdsuite: A Toolkit To Mine Electronic Theses And Dissertations To Enrich Scholarly Big Data Using Natural Language Processing And Computer Vision, Muntabir Hasan Choudhury
Computer Science Theses & Dissertations
In the past decades, there has been a growing interest in mining scientific documents to obtain domain knowledge automatically. One of the understudied types of scientific documents is Electronic Theses and Dissertations (ETDs), as ETDs have distinct features compared with conference proceedings and journal articles. ETDs usually serve as partial requirements of academic degrees for students pursuing higher education. They are book-length documents (i.e., 100 – 400 pages long), and the topics may shift across chapters, exhibit the significant contribution of a student’s research over the entire degree pursuing period, and have unique metadata schema and page layouts. However, the …
Interactive Example-Based Explanations To Improve Health Professionals’ Onboarding With Ai For Human-Ai Collaborative Decision Making, Min Hun Lee, Renee Bao Xuan Ng, Silvana Xinyi Choo, Shamala Thilarajah
Interactive Example-Based Explanations To Improve Health Professionals’ Onboarding With Ai For Human-Ai Collaborative Decision Making, Min Hun Lee, Renee Bao Xuan Ng, Silvana Xinyi Choo, Shamala Thilarajah
Research Collection School Of Computing and Information Systems
A growing research explores the usage of AI explanations on user’s decision phases for human-AI collaborative decision-making. However, previous studies found the issues of overreliance on ‘wrong’ AI outputs. In this paper, we propose interactive example-based explanations to improve health professionals’ onboarding with AI for their better reliance on AI during AI-assisted decision-making. We implemented an AI-based decision support system that utilizes a neural network to assess the quality of post-stroke survivors’ exercises and interactive example-based explanations that systematically surface the nearest neighborhoods of a test/task sample from the training set of the AI model to assist users’ onboarding with …
Generative Ai In Software Engineering Must Be Human-Centered: The Copenhagen Manifesto, D. Russo, S. Van Berkel Baltes, Christoph Treude
Generative Ai In Software Engineering Must Be Human-Centered: The Copenhagen Manifesto, D. Russo, S. Van Berkel Baltes, Christoph Treude
Research Collection School Of Computing and Information Systems
The advent of Generative Artificial Intelligence—systems that can produce human-like content such as text, music, visual art, or source code—marks not only a significant leap for Artificial Intelligence (AI) but also a pivotal moment for software practitioners and researchers. The role of software engineering researchers and practitioners in adopting the technologies that shape our world is critical. Historically, the human aspects of developing software have been treated as secondary to more technical innovations. However, the emergence of Generative AI will simultaneously enhance human capabilities while surfacing complex ethical, social, legal, and technical challenges.While primarily aimed at software engineering (SE) researchers …
Innovative Strategies For Healthcare Data Integration: Enhancing Etl Efficiency Through Containerization And Parallel Computing, Ehsan Soltanmohammadi
Innovative Strategies For Healthcare Data Integration: Enhancing Etl Efficiency Through Containerization And Parallel Computing, Ehsan Soltanmohammadi
Theses and Dissertations
The healthcare industry is rapidly transforming due to technology adoption, resulting in an explosion of data. Extract, Transform, Load (ETL) processes are crucial for integrating and analyzing this data to support decision-making and enhance patient care. However, ETL processes face significant challenges, including data diversity, quality issues, security and compliance, and scalability. Opportunities exist to optimize ETL processes through advanced technologies like big data analytics, containerization, and parallel computing, improving data quality, and enhancing security. This literature review examines current ETL processes in healthcare, highlighting challenges and opportunities for future improvement, ultimately aiming to enhance healthcare outcomes and patient experiences. …
Navigating Governance Paradigms: A Cross-Regional Comparative Study Of Generative Ai Governance Processes & Principle, Jose Luna, Ivan Tan, Xiaofei Xie, Lingxiao Jiang
Navigating Governance Paradigms: A Cross-Regional Comparative Study Of Generative Ai Governance Processes & Principle, Jose Luna, Ivan Tan, Xiaofei Xie, Lingxiao Jiang
Research Collection School Of Computing and Information Systems
As Generative Artificial Intelligence (GenAI) technologies evolve at an unprecedented rate, global governance approaches struggle to keep pace with the technology, highlighting a critical issue in the governance adaptation of significant challenges. Depicting the nuances of nascent and diverse governance approaches based on risks, rules, outcomes, principles, or a mix across different regions around the globe is fundamental to discern discrepancies and convergences and to shed light on specific limitations that need to be addressed, thereby facilitating the safe and trustworthy adoption of GenAI. In response to the need and the evolving nature of GenAI, this paper seeks to provide …
Collaborative Cross-Modal Fusion With Large Language Model For Recommendation, Zhongzhou Liu, Hao Zhang, Kuicai Dong, Yuan Fang
Collaborative Cross-Modal Fusion With Large Language Model For Recommendation, Zhongzhou Liu, Hao Zhang, Kuicai Dong, Yuan Fang
Research Collection School Of Computing and Information Systems
Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual attributes of users and items. Recent focus on the application of large language models for recommendation (LLM4Rec) has highlighted their capability for effective semantic knowledge capture. However, these methods often overlook the collaborative signals in user behaviors. Some simply instruct-tune a language model, while others directly inject the embeddings of a CF-based model, lacking a synergistic fusion of different modalities. To address these issues, we propose a framework of Collaborative Cross-modal Fusion with Large Language Models, termed CCF-LLM, …
Pvp-Ssd: Point-Voxel Fusion With Partitioned Point Cloud Sampling For Anchor-Free Single-Stage Small 3d Object Detection, Xinlin Wu, Yibin Tian, Yin Pan, Zhiyuan Zhang, Xuesong Wu, Ruisheng Wang, Zhi Zeng
Pvp-Ssd: Point-Voxel Fusion With Partitioned Point Cloud Sampling For Anchor-Free Single-Stage Small 3d Object Detection, Xinlin Wu, Yibin Tian, Yin Pan, Zhiyuan Zhang, Xuesong Wu, Ruisheng Wang, Zhi Zeng
Research Collection School Of Computing and Information Systems
Single-stage object detection from 3D point clouds in autonomous driving faces significant challenges, particularly in accurately detecting small objects. To address this issue, we propose a novel method called Point-Voxel dual-branch feature extraction with Partitioned point cloud sampling for anchor-free Single-Stage Detection of 3D objects (PVP-SSD). The network comprises two branches: a point branch and a voxel branch. In the point branch, a partitioned point cloud sampling strategy leverages axial features to divide the point cloud. Then, it assigns different sampling weights to various segments to enhance the sampling accuracy. Additionally, a local feature enhancement module explicitly calculates the correlation …
Video Editing For Video Retrieval, Bin Zhu, Kevin Flanagan, Adriano Fragomeni, Michael Wray, Dima Damen
Video Editing For Video Retrieval, Bin Zhu, Kevin Flanagan, Adriano Fragomeni, Michael Wray, Dima Damen
Research Collection School Of Computing and Information Systems
Though pre-training vision-language models have demonstrated significant benefits in boosting video-text retrieval performance from large-scale web videos, fine-tuning still plays a critical role with manually annotated clips with start and end times, which requires considerable human effort. To address this issue, we explore an alternative cheaper source of annotations, single timestamps, for video-text retrieval. We initialise clips from timestamps in a heuristic way to warm up a retrieval model. Then a video clip editing method is proposed to refine the initial rough boundaries to improve retrieval performance. A student-teacher network is introduced for video clip editing: the teacher model is …