Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences

Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 3721 - 3750 of 20711

Full-Text Articles in Entire DC Network

A Psychometric Analysis Of Natural Language Inference Using Transformer Language Models, Antonio Laverghetta Jr. Oct 2023

A Psychometric Analysis Of Natural Language Inference Using Transformer Language Models, Antonio Laverghetta Jr.

USF Tampa Graduate Theses and Dissertations

Large language models (LLMs) are poised to transform both academia and industry. But the excitement around these generative AIs has also been met with concern for the true extent of their capabilities. This dissertation helps to address these questions by examining the capabilities of LLMs using the tools of psychometrics. We focus on analyzing the capabilities of LLMs on the task of natural language inference (NLI), a foundational benchmark often used to evaluate new models. We demonstrate that LLMs can reliably predict the psychometric properties of NLI items were those items administered to humans. Through a series of experiments, we …

Go to article

Yet Another Model For Arabic Dialect Identification, Ajinkya Kulkarni, Hanan Al Darmaki Oct 2023

Yet Another Model For Arabic Dialect Identification, Ajinkya Kulkarni, Hanan Al Darmaki

Natural Language Processing Faculty Publications

In this paper, we describe a spoken Arabic dialect identification (ADI) model for Arabic that consistently outperforms previously published results on two benchmark datasets: ADI-5 and ADI-17. We explore two architectural variations: ResNet and ECAPA-TDNN, coupled with two types of acoustic features: MFCCs and features exratected from the pre-trained self-supervised model UniSpeech-SAT Large, as well as a fusion of all four variants. We find that individually, ECAPA-TDNN network outperforms ResNet, and models with UniSpeech-SAT features outperform models with MFCCs by a large margin. Furthermore, a fusion of all four variants consistently outperforms individual models. Our best models outperform previously reported …

Go to article

Improving Human-Automation Collaboration In Motion Planning, Torin J. Adamson Oct 2023

Improving Human-Automation Collaboration In Motion Planning, Torin J. Adamson

Computer Science ETDs

Human-automation collaboration is becoming a part of everyday life as AI helps us drive, make decisions, and solve a variety of other tasks. However, safe and effective collaboration systems depend on factors in trust, communication, and more. Existing studies to explore these are typically carried out in laboratory settings, providing robust data under tight environmental control. However, human behavior evolves over time, driven by external factors that cannot be fully captured in single participation sessions. These factors form the "human context", contextualizing the behavioral data for a more complete understanding. In this thesis, video game adaptations upon conventional subject studies …

Go to article

Hprop: Hierarchical Privacy-Preserving Route Planning For Smart Cities, Francis Tiausas, Keiichi Yasumoto, Jose Paolo Talusan, Hayato Yamana, Hirozumi Yamaguchi, Shameek Bhattacharjee, Abhishek Dubey, Sajal K. Das Oct 2023

Hprop: Hierarchical Privacy-Preserving Route Planning For Smart Cities, Francis Tiausas, Keiichi Yasumoto, Jose Paolo Talusan, Hayato Yamana, Hirozumi Yamaguchi, Shameek Bhattacharjee, Abhishek Dubey, Sajal K. Das

Computer Science Faculty Research & Creative Works

Route Planning Systems (RPS) are a core component of autonomous personal transport systems essential for safe and efficient navigation of dynamic urban environments with the support of edge-based smart city infrastructure, but they also raise concerns about user route privacy in the context of both privately owned and commercial vehicles. Numerous high-profile data breaches in recent years have fortunately motivated research on privacy preserving RPS, but most of them are rendered impractical by greatly increased communication and processing overhead. We address this by proposing an approach called Hierarchical Privacy-Preserving Route Planning (HPRoP), which divides and distributes the route-planning task across …

Go to article

Dtitd: An Intelligent Insider Threat Detection Framework Based On Digital Twin And Self-Attention Based Deep Learning Models, Zhi Qiang Wang, Abdulmotaleb El Saddik Oct 2023

Dtitd: An Intelligent Insider Threat Detection Framework Based On Digital Twin And Self-Attention Based Deep Learning Models, Zhi Qiang Wang, Abdulmotaleb El Saddik

Computer Vision Faculty Publications

Recent statistics and studies show that the loss generated by insider threats is much higher than that generated by external attacks. More and more organizations are investing in or purchasing insider threat detection systems to prevent insider risks. However, the accurate and timely detection of insider threats faces significant challenges. In this study, we proposed an intelligent insider threat detection framework based on Digital Twins and self-attentions based deep learning models. First, this paper introduces insider threats and the challenges in detecting them. Then this paper presents recent related works on solving insider threat detection problems and their limitations. Next, …

Go to article

Exploring Network Security Educator Knowledge, Jennifer B. Chauvot, Deniz Gurkan, Cathy Horn Oct 2023

Exploring Network Security Educator Knowledge, Jennifer B. Chauvot, Deniz Gurkan, Cathy Horn

Journal of Cybersecurity Education, Research and Practice

It is critical for nations to have trained professionals in network security who can safeguard hardware, information systems, and electronic data. Network security education is a key knowledge unit of the National Centers of Academic Excellence in Cybersecurity and various information systems security curricula at the master's and bachelor's levels in higher education. Network security units are components of computer science curricula in high school contexts as well. Educators who teach these concepts play a significant role in developing a skilled workforce of network security experts for both governmental and non-governmental organizations. Understanding the necessary knowledge and skills of network …

Go to article

Cybersecurity Challenges And Awareness Of The Multi-Generational Learners In Nepal, Raj Kumar Dhungana, Lina Gurung Dr, Hem Poudyal Oct 2023

Cybersecurity Challenges And Awareness Of The Multi-Generational Learners In Nepal, Raj Kumar Dhungana, Lina Gurung Dr, Hem Poudyal

Journal of Cybersecurity Education, Research and Practice

Increased exposure to technologies has lately emerged as one of the everyday realities of digital natives, especially K-12 students, and teachers, the digital immigrants. Protection from cybersecurity risks in digital learning spaces is a human right, but students are increasingly exposed to high-risk cyberspace without time to cope with cybersecurity risks. This study, using a survey (N-891 students and 157 teachers) and in-depth interviews (27 students and 14 teachers), described the students' cybersecurity-related experiences and challenges in Nepal. This study revealed that the school’s cybersecurity support system is poor and teachers has very low awareness and competencies to protect students …

Go to article

Adapting The Adapters For Code-Switching In Multilingual Asr, Atharva Kulkarni, Ajinkya Kulkarni, Miguel Couceiro, Hanan Al Darmaki Oct 2023

Adapting The Adapters For Code-Switching In Multilingual Asr, Atharva Kulkarni, Ajinkya Kulkarni, Miguel Couceiro, Hanan Al Darmaki

Natural Language Processing Faculty Publications

Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages. Some of these models employ language adapters in their formulation, which helps to improve monolingual performance and avoids some of the drawbacks of multi-lingual modeling on resource-rich languages. However, this formulation restricts the usability of these models on code-switched speech, where two languages are mixed together in the same utterance. In this work, we propose ways to effectively fine-tune such models on code-switched speech, by assimilating information from both language adapters at each language adaptation point in the network. We also …

Go to article

Editorial For "Automated Breast Density Assessment In Mri Using Deep Learning And Radiomics: Strategies For Reducing Inter-Observer Variability"., Pegah Khosravi Oct 2023

Editorial For "Automated Breast Density Assessment In Mri Using Deep Learning And Radiomics: Strategies For Reducing Inter-Observer Variability"., Pegah Khosravi

Publications and Research

No abstract provided.

Go to article

Cybervandalism Detection In Wikipedia Using Light Architecture Of 1d-Cnn, Azha Talal Mohammed Ali, Huda Hallawi, Noor D. Al-Shakarchy Oct 2023

Cybervandalism Detection In Wikipedia Using Light Architecture Of 1d-Cnn, Azha Talal Mohammed Ali, Huda Hallawi, Noor D. Al-Shakarchy

Karbala International Journal of Modern Science

The rapid expansion of human-software-agent interaction has come with new issues. Accordingly, different engage-ments are necessary to adapt to changing human needs in dynamic socio-technical systems. Generally, cybervandalism is the act of leaving any negative impact on any piece of writing in an attempt to modify it. In Wikipedia, vandalism is any attempt to modify an article in a way that negatively affects the article's quality. Recently, several automatic detec-tion techniques and related features have been developed to address this issue. This work introduces a deep learning model with a new and light architecture to detect vandalism in Wikipedia articles. …

Go to article

Trcaptionnet: A Novel And Accurate Deep Turkish Image Captioning Model With Vision Transformer Based Image Encoders And Deep Linguistic Text Decoders, Serdar Yildiz, Abbas Memi̇ş, Songül Varli Oct 2023

Trcaptionnet: A Novel And Accurate Deep Turkish Image Captioning Model With Vision Transformer Based Image Encoders And Deep Linguistic Text Decoders, Serdar Yildiz, Abbas Memi̇ş, Songül Varli

Turkish Journal of Electrical Engineering and Computer Sciences

Image captioning is known as a fundamental computer vision task aiming to figure out and describe what is happening in an image or image region. Through an image captioning process, it is ensured to describe and define the actions and the relations of the objects within the images. In this manner, the contents of the images can be understood and interpreted automatically by visual computing systems. In this paper, we proposed the TRCaptionNet a novel deep learning-based Turkish image captioning (TIC) model for the automatic generation of Turkish captions. The model we propose essentially consists of a basic image encoder, …

Go to article

Solving Geospatial Problems Under Extreme Time Constraints: A Call For Inclusive Geocomputational Education, Coline C. Dony Oct 2023

Solving Geospatial Problems Under Extreme Time Constraints: A Call For Inclusive Geocomputational Education, Coline C. Dony

I-GUIDE Forum

To prepare our next generation to face geospatial problems that have extreme time constraints (e.g., disasters, climate change) we need to create educational pathways that help students develop their geocomputational thinking skills. First, educators are central in helping us create those pathways, therefore, we need to clearly convey to them why and in which contexts this thinking is necessary. For that purpose, a new definition for geocomputational thinking is suggested that makes it clear that this thinking is needed for geospatial problems that have extreme time constraints. Secondly, we can not further burden educators with more demands, rather we should …

Go to article

Broadband Equity, Access, And Deployment In Nevada, Brad Wimmer Oct 2023

Broadband Equity, Access, And Deployment In Nevada, Brad Wimmer

Policy Briefs and Reports

The $45.45 billion Broadband, Equity, Access, and Deployment (BEAD) program’s primary objective is to extend broadband service to all unserved and underserved locations in the U.S. and its territories. Several industry studies predict that the BEAD program can meet its goal of providing universal access to broadband service if eligible entities execute their grant programs well. My review of the BEAD program indicates that policy makers can enhance the likelihood of program success by designing competitive grant programs that give applicants the incentive to undercut the subsidies proposed by their rivals and provide applicants the flexibility to design networks that …

Go to article

A Survey Of Eeg And Machine Learning-Based Methods For Neural Rehabilitation, Jaiteg Singh, Farman Ali, Rupali Gill, Babar Shah, Daehan Kwak Oct 2023

A Survey Of Eeg And Machine Learning-Based Methods For Neural Rehabilitation, Jaiteg Singh, Farman Ali, Rupali Gill, Babar Shah, Daehan Kwak

All Works

One approach to therapy and training for the restoration of damaged muscles and motor systems is rehabilitation. EEG-assisted Brain-Computer Interface (BCI) may assist in restoring or enhancing ‘lost motor abilities in the brain. Assisted by brain activity, BCI offers simple-to-use technology aids and robotic prosthetics. This systematic literature review aims to explore the latest developments in BCI and motor control for rehabilitation. Additionally, we have explored typical EEG apparatuses that are available for BCI-driven rehabilitative purposes. Furthermore, a comparison of significant studies in rehabilitation assessment using machine learning techniques has been summarized. The results of this study may influence policymakers’ …

Go to article

An Ai-Based Framework For Translating American Sign Language To English And Vice Versa, Vijayendra D. Avina, Md Amiruzzaman, Stefanie Amiruzzaman, Linh B. Ngo, M. Ali Akber Dewan Oct 2023

An Ai-Based Framework For Translating American Sign Language To English And Vice Versa, Vijayendra D. Avina, Md Amiruzzaman, Stefanie Amiruzzaman, Linh B. Ngo, M. Ali Akber Dewan

Computer Science Faculty Publications

Abstract: In this paper, we propose a framework to convert American Sign Language (ASL) to English and English to ASL. Within this framework, we use a deep learning model along with the rolling average prediction that captures image frames from videos and classifies the signs from the image frames. The classified frames are then used to construct ASL words and sentences to support people with hearing impairments. We also use the same deep learning model to capture signs from the people with deaf symptoms and convert them into ASL words and English sentences. Based on this framework, we developed a …

Go to article

Understanding The Effect Of Counterfactual Explanations On Trust And Reliance On Ai For Human-Ai Collaborative Clinical Decision Making, Min Hun Lee, Chong Jun Chew Oct 2023

Understanding The Effect Of Counterfactual Explanations On Trust And Reliance On Ai For Human-Ai Collaborative Clinical Decision Making, Min Hun Lee, Chong Jun Chew

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) is increasingly being considered to assist human decision-making in high-stake domains (e.g. health). However, researchers have discussed an issue that humans can over-rely on wrong suggestions of the AI model instead of achieving human AI complementary performance. In this work, we utilized salient feature explanations along with what-if, counterfactual explanations to make humans review AI suggestions more analytically to reduce overreliance on AI and explored the effect of these explanations on trust and reliance on AI during clinical decision-making. We conducted an experiment with seven therapists and ten laypersons on the task of assessing post-stroke survivors' quality …

Go to article

Towards An Effective And Interpretable Refinement Approach For Dnn Verification, Jiaying Li, Guangdong Bai, Long H. Pham, Jun Sun Oct 2023

Towards An Effective And Interpretable Refinement Approach For Dnn Verification, Jiaying Li, Guangdong Bai, Long H. Pham, Jun Sun

Research Collection School Of Computing and Information Systems

Recently, several abstraction refinement techniques have been proposed to improve the verification precision for deep neural networks (DNNs). However, these techniques usually take many refinement steps to verify a property and the refinement decision in each step is hard to interpret, thus hindering their analysis, reasoning and optimization.In this work, we propose SURGEON, a novel DNN verification refinement approach that is both effective and interpretable, allowing analyst to understand why and how each refinement decision is made. The main insight is to leverage the ‘interpretable’ nature of debugging processes and formulate the verification refinement problem as a debugging problem. Given …

Go to article

Robust Underwater State Estimation And Mapping, Bharat Joshi Oct 2023

Robust Underwater State Estimation And Mapping, Bharat Joshi

Theses and Dissertations

The ocean covers two-thirds of Earth, which is relatively unexplored compared to the landmass. Mapping underwater structures is essential for both archaeological and conservation purposes. This dissertation focuses on employing a robot team to map underwater structures using vision-based simultaneous localization and mapping (SLAM). The overarching goal of this research is to create a team of autonomous robots to map large underwater structures in a coordinated fashion. This requires maintaining an accurate robust pose estimate of oneself and knowing the relative pose of the other robots in the team. However, the GPS-denied and communication-constrained underwater environment, along with low visibility, …

Go to article

Smart Homes And You: Iot Device Data Risks In An Ever-Changing World, Autumn Person Oct 2023

Smart Homes And You: Iot Device Data Risks In An Ever-Changing World, Autumn Person

Theses and Dissertations

Social media applications are increasingly seen as a national security threat and a cause for concern because they can be used to create user profiles on government personnel and on US citizens. These profiles could be used for big data and artificial intelligence purposes of interest to foreign governments. With the rise of big data and AI being used, foreign governments could use this data for a variety of purposes that can affect normal everyday citizens, not just high value personnel. IoT (Internet of Things) devices that the population uses everyday can also pose the same threat. These devices can …

Go to article

Docker Technology For Small Scenario-Based Excercises In Cybersecurity, Zeinab Ahmed Oct 2023

Docker Technology For Small Scenario-Based Excercises In Cybersecurity, Zeinab Ahmed

Theses and Dissertations

This study aims to better prepare students for cybersecurity roles by providing practical tools that bridge the gap between theory and real-world applications. We investigate the role of small scenario-based exercises for students’ understanding of cybersecurity concepts. In particular, we assess the use of Docker technology to deliver training that includes a simple small scenario on html code injection. The effectiveness of scenario-based learning has long been defined and by using SBL, we are going to create hands-on activity that involves the fundamental topics in cybersecurity using Docker technology, allowing students to see the exploitation of the vulnerabilities and defense …

Go to article

Spoken Language Processing And Modeling For Aviation Communications, Aaron Van De Brook Oct 2023

Spoken Language Processing And Modeling For Aviation Communications, Aaron Van De Brook

Doctoral Dissertations and Master's Theses

With recent advances in machine learning and deep learning technologies and the creation of larger aviation-specific corpora, applying natural language processing technologies, especially those based on transformer neural networks, to aviation communications is becoming increasingly feasible. Previous work has focused on machine learning applications to natural language processing, such as N-grams and word lattices. This thesis experiments with a process for pretraining transformer-based language models on aviation English corpora and compare the effectiveness and performance of language models transfer learned from pretrained checkpoints and those trained from their base weight initializations (trained from scratch). The results suggest that transformer language …

Go to article

Catching Elusive Depression Via Facial Micro-Expression Recognition, Xiaohui Chen, Tony Tie (T.) Luo Oct 2023

Catching Elusive Depression Via Facial Micro-Expression Recognition, Xiaohui Chen, Tony Tie (T.) Luo

Computer Science Faculty Research & Creative Works

Depression is a common mental health disorder that can cause consequential symptoms with continuously depressed mood that leads to emotional distress. One category of depression is Concealed Depression, where patients intentionally or unintentionally hide their genuine emotions through exterior optimism, thereby complicating and delaying diagnosis and treatment and leading to unexpected suicides. In this article, we propose to diagnose concealed depression by using facial micro-expressions (FMEs) to detect and recognize underlying true emotions. However, the extremely low intensity and subtle nature of FMEs make their recognition a tough task. We propose a facial landmark-based Region-of-Interest (ROI) approach to address the …

Go to article

Stprivacy: Spatio-Temporal Privacy-Preserving Action Recognition, Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan Oct 2023

Stprivacy: Spatio-Temporal Privacy-Preserving Action Recognition, Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification …

Go to article

Visilience: An Interactive Visualization Framework For Resilience Analysis Using Control-Flow Graph, Hailong Jiang, Shaolun Ruan, Bo Fang, Yong Wang, Qiang Guan Oct 2023

Visilience: An Interactive Visualization Framework For Resilience Analysis Using Control-Flow Graph, Hailong Jiang, Shaolun Ruan, Bo Fang, Yong Wang, Qiang Guan

Research Collection School Of Computing and Information Systems

Soft errors have become one of the main concerns for the resilience of HPC applications, as these errors can cause HPC applications to generate serious outcomes such as silent data corruption (SDC). Many approaches have been proposed to analyze the resilience of HPC applications. However, existing studies rarely address the challenges of analysis result perception. Specifically, resilience analysis techniques often produce a massive volume of unstructured data, making it difficult for programmers to perform resilience analysis due to non-intuitive raw data. Furthermore, different analysis models produce diverse results with multiple levels of detail, which can create obstacles to compare and …

Go to article

The Future Can't Help Fix The Past: Assessing Program Repair In The Wild, Vinay Kabadi, Dezhen Kong, Siyu Xie, Lingfeng Bao, Gede Artha Azriadi Prana, Tien Duy B. Le, Xuan Bach D. Le, David Lo Oct 2023

The Future Can't Help Fix The Past: Assessing Program Repair In The Wild, Vinay Kabadi, Dezhen Kong, Siyu Xie, Lingfeng Bao, Gede Artha Azriadi Prana, Tien Duy B. Le, Xuan Bach D. Le, David Lo

Research Collection School Of Computing and Information Systems

Automated program repair (APR) has been gaining ground with substantial effort devoted to the area, opening up many challenges and opportunities. One such challenge is that the state-of-the-art repair techniques often resort to incomplete specifications, e.g., test cases that witness buggy behavior, to generate repairs. In practice, bug-exposing test cases are often available when: (1) developers, at the same time of (or after) submitting bug fixes, create the tests to assure the correctness of the fixes, or (2) regression errors occur. The former case – a scenario commonly used for creating popular bug datasets – however, may not be suitable …

Go to article

Affine Image Registration Of Arterial Spin Labeling Mri Using Deep Learning Networks, Zongpai Zhang, Huiyuan Yang, Yanchen Guo, Nicolas R. Bolo, Matcheri Keshavan, Eve Derosa, Adam K. Anderson, David C. Alsop, Lijun Yin, Weiying Dai Oct 2023

Affine Image Registration Of Arterial Spin Labeling Mri Using Deep Learning Networks, Zongpai Zhang, Huiyuan Yang, Yanchen Guo, Nicolas R. Bolo, Matcheri Keshavan, Eve Derosa, Adam K. Anderson, David C. Alsop, Lijun Yin, Weiying Dai

Computer Science Faculty Research & Creative Works

Convolutional neural networks (CNN) have demonstrated good accuracy and speed in spatially registering high signal-to-noise ratio (SNR) structural magnetic resonance imaging (sMRI) images. However, some functional magnetic resonance imaging (fMRI) images, e.g., those acquired from arterial spin labeling (ASL) perfusion fMRI, are of intrinsically low SNR and therefore the quality of registering ASL images using CNN is not clear. In this work, we aimed to explore the feasibility of a CNN-based affine registration network (ARN) for registration of low-SNR three-dimensional ASL perfusion image time series and compare its performance with that from the state-of-the-art statistical parametric mapping (SPM) algorithm. The …

Go to article

Effective Entity Augmentation By Querying External Data Sources, Christopher Buss, Jasmin Mousavi, Mikhail Tokarev, Arash Termehchy, David Maier, Stefan Lee Oct 2023

Effective Entity Augmentation By Querying External Data Sources, Christopher Buss, Jasmin Mousavi, Mikhail Tokarev, Arash Termehchy, David Maier, Stefan Lee

Computer Science Faculty Publications and Presentations

Users often want to augment and enrich entities in their datasets with relevant information from external data sources. As many external sources are accessible only via keyword-search interfaces, a user usually has to manually formulate a keyword query that extract relevant information for each entity. This approach is challenging as many data sources contain numerous tuples, only a small fraction of which may contain entity-relevant information. Furthermore, different datasets may represent the same information in distinct forms and under different terms (e.g., different data source may use different names to refer to the same person). In such cases, it is …

Go to article

Boosting Adversarial Training In Safety-Critical Systems Through Boundary Data Selection, Yifan Jia, Christopher M. Poskitt, Peixin Zhang, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay Oct 2023

Boosting Adversarial Training In Safety-Critical Systems Through Boundary Data Selection, Yifan Jia, Christopher M. Poskitt, Peixin Zhang, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay

Research Collection School Of Computing and Information Systems

AI-enabled collaborative robots are designed to be used in close collaboration with humans, thus requiring stringent safety standards and quick response times. Adversarial attacks pose a significant threat to the deep learning models of these systems, making it crucial to develop methods to improve the models' robustness against them. Adversarial training is one approach to improve their robustness: it works by augmenting the training data with adversarial examples. This, unfortunately, comes with the cost of increased computational overhead and extended training times. In this work, we balance the need for additional adversarial data with the goal of minimizing the training …

Go to article

Objectfusion: Multi-Modal 3d Object Detection With Object-Centric Fusion, Q. Cai, Y. Pan, T. Yao, Chong-Wah Ngo, T. Mei Oct 2023

Objectfusion: Multi-Modal 3d Object Detection With Object-Centric Fusion, Q. Cai, Y. Pan, T. Yao, Chong-Wah Ngo, T. Mei

Research Collection School Of Computing and Information Systems

Recent progress on multi-modal 3D object detection has featured BEV (Bird-Eye-View) based fusion, which effectively unifies both LiDAR point clouds and camera images in a shared BEV space. Nevertheless, it is not trivial to perform camera-to-BEV transformation due to the inherently ambiguous depth estimation of each pixel, resulting in spatial misalignment between these two multi-modal features. Moreover, such transformation also inevitably leads to projection distortion of camera image features in BEV space. In this paper, we propose a novel Object-centric Fusion (ObjectFusion) paradigm, which completely gets rid of camera-to-BEV transformation during fusion to align object-centric features across different modalities for …

Go to article

Feature Prediction Diffusion Model For Video Anomaly Detection, Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang Oct 2023

Feature Prediction Diffusion Model For Video Anomaly Detection, Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang

Research Collection School Of Computing and Information Systems

Anomaly detection in the video is an important research area and a challenging task in real applications. Due to the unavailability of large-scale annotated anomaly events, most existing video anomaly detection (VAD) methods focus on learning the distribution of normal samples to detect the substantially deviated samples as anomalies. To well learn the distribution of normal motion and appearance, many auxiliary networks are employed to extract foreground object or action information. These high-level semantic features effectively filter the noise from the background to decrease its influence on detection models. However, the capability of these extra semantic models heavily affects the …

Go to article

First Prev Next Last