教学课程资源库 更多>>

关键词： Videos   Visualization   Semantics   Chatbots   Image recognition   Electronic mail   Refining   Computer science   Benchmark testing   Training   Egocentric Action Recognition   Zero-Shot Learning   Vision-Language Learning  

摘要： Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown impressive performance in various visual recognition tasks. This advancement paves the way for notable performance in some egocentric tasks, Zero-Shot Egocentric Action Recognition (ZS-EAR), entailing VLMs zero-shot to recognize actions from first-person videos enriched in more realistic human-environment interactions. Typically, VLMs handle ZS-EAR as a global video-text matching task, which often leads to suboptimal alignment of vision and linguistic knowledge. We propose a refined approach for ZS-EAR using VLMs, emphasizing fine-grained concept-description alignment that capitalizes on the rich semantic and contextual details in egocentric videos. In this work, we introduce a straightforward yet remarkably potent VLM framework, aka GPT4Ego, designed to enhance the fine-grained alignment of concept and description between vision and language. Specifically, we first propose a new Ego-oriented Text Prompting (EgoTP ) scheme, which effectively prompts action-related text-contextual semantics by evolving word-level class names to sentence-level contextual descriptions by ChatGPT with well-designed chain-of-thought textual prompts. Moreover, we design a new Ego-oriented Visual Parsing (EgoVP ) strategy that learns action-related vision-contextual semantics by refining global-level images to part-level contextual concepts with the help of SAM. Extensive experiments demonstrate GPT4Ego significantly outperforms existing VLMs on three large-scale egocentric video benchmarks, i.e., EPIC-KITCHENS-100 (33.2% up arrow (+9.4) ), EGTEA (39.6% up arrow (+5.5) ), and CharadesEgo (31.5% up arrow (+2.6) ). In addition, benefiting from the novel mechanism of fine-grained concept and description alignment, GPT4Ego can sustainably evolve with the advancement of ever-growing pre-trained foundational models. We hope this work can encourage the egocentric community to build more investigation into pre-trained v

关键词： Students  

摘要： Contribution: This study enhances the understanding of the factors that impact academic performance and self-efficacy among computer science (CS) students, specifically focusing on gender differences. Background: The motivation behind this study stems from the gender disparity observed within undergraduate CS programs. This gender gap undermines diversity within the tech industry and hampers its potential for innovation. Research Questions: Do female CS students exhibit lower levels of school belonging and academic self-efficacy? Are there gender differences in academic achievement? What is the predictive power of prior academic performance, academic self-efficacy, and sense of belonging on first-semester grades? Methodology: In this study, 113 undergraduate students (82 males) were surveyed. The questionnaire was administered midway through the semester, in early November. High school math exam scores were assessed along with self-reported measures of academic self-efficacy and sense of belonging. Findings: The findings revealed several noteworthy observations: Female students exhibited a statistically significant higher grade point average (GPA) at the end of the first semester despite reporting lower levels of academic self-efficacy. Regression analysis identified gender, academic self-efficacy, and high school math exam scores as significant predictors of first-semester GPA. Implications: The implications of the study underscore the importance of fostering a supportive learning environment within CS education. Specifically, this study advocates for implementing teaching practices that prioritize social aspects and help enhance field-specific self-efficacy for all students. © 1963-2012 IEEE.

ISBN: (纸本)9780472077182;9780472904808

摘要： Starting in 1966, African American activist Stokely Carmichael and other political leaders adopted the phrase "Black Power!" The slogan captured a mil...

关键词： Remote sensing   Superresolution   Image enhancement   Spatial resolution   Image quality   Image color analysis   Computer science   Accuracy   Colored noise   Classification algorithms   Image classification   image enhancement   image processing   image recognition   remote sensing  

摘要： Oceans and seas cover more than 70% of the Earth's surface. If compared with the land mass there are a lot of unexplored locations, a wealth of natural resources, and diverse ocean creatures that are inaccessible to us humans. Underwater rovers and vehicles play a vital role in discovering these resources, yet limited visibility in deep waters and technological constraints impede underwater exploration. To address these issues, advanced image super-resolution and enhancement techniques are crucial for reliable resource identification, species recognition, and underwater ecosystem study. This will ultimately bridge the current gap in environmental monitoring by facilitating resource tracking and underwater waste assessment. This article proposes a novel multistage fusion algorithm for underwater image super-resolution, designed to enhance the quality and spatial resolution of low-resolution underwater images toward a more accurate object characterization. The effectiveness of the proposed super-resolution technique is demonstrated using multiple performance metrics including accuracy, f1-score, recall, and precision. By enhancing the spatial resolution of underwater images, our approach meets the increasing demand for detailed and accurate information in underwater earth observation applications.

关键词： Anomaly detection   Feature extraction   Protocols   Filling   Vectors   Image edge detection   Graph neural networks   Decoding   Computer science   Deep learning   attributed network   graph convolutional network   reconstruction   mask-filling   neighborhood association  

摘要： As a widely adopted protocol for anomaly detection in attributed networks, reconstruction error prioritizes comprehensive feature extraction to detect anomalies over interrogating the differential representation between normal and abnormal nodes. Intuitively, in attributed networks, normal nodes and their neighbors often exhibit similarities, whereas abnormal nodes demonstrate behaviors distinct from their neighbors. Hence, normal nodes can be accurately represented through their neighbors and effectively reconstructed. As opposed to normal nodes, abnormal nodes represented by their neighbors may be erroneously reconstructed as normal, resulting in increased reconstruction error. Leveraging from this observation, we propose a novel anomaly detection protocol called Neighbor-aware Mask-Filling Anomaly Detection (NMFAD) for attributed networks, aiming to maximize the variability between original and reconstructed features of abnormal nodes filled with information from their neighbors. Specifically, we utilize random-mask on nodes and integrate them into the backbone Graph Neural Networks (GNNs) to map nodes into a latent space. Subsequently, we fill the masked nodes with embeddings from their neighbors and smooth the abnormal nodes closer to the distribution of normal nodes. This optimization improves the likelihood of the decoder to reconstructing abnormal nodes as normal, thereby maximizing the reconstruction error of abnormal nodes. Experimental results demonstrate that, compared to the existing models, NMFAD exhibits superior *** attributed networks.

关键词： Students  

摘要： This study focused on an XR camp designed to integrate multiple subjects into one course, providing students with an immersive, creative, and engaging interdisciplinary learning experience. This study explored the distribution of cognitive development stages among computer science students (CSSs) and engineering students (ESs). Additionally, we compared differences in learning styles, levels of participation and contributions, and learning outcomes between the two groups and verified whether the degree of participation and contributions could predict learning outcomes. The subjects were 54 students (39 = CSSs, 15 = ESs) who participated in the XR camp course from 2020–2021. The students completed the active experiment scale in the 1st week;rated team members using a peer assessment rubric and projects using a work rubric in the 6th, 11th, and 16th weeks;completed the learning ability scales;and participated in interviews in the 18th week. Following their participation in the XR camp, 87% of the students developed high-level cognitive abilities in the XR camp. For the CSSs, course participation positively predicted cognitive development stages, work performance, and collaborative problem-solving abilities, with peer assessments positively influencing work performance. The ESs demonstrated greater interdisciplinary competence, and course participation also positively predicted work performance. These students could also apply XR knowledge and technology to other situations, confirming that the XR camp is conducive to learning for students from diverse backgrounds. © 2025 TEMPUS Publications.

关键词： expectation   practical programming tasks   probability courses  

摘要： The concept of expectation is fundamental in computer science education, especially for analyzing the time efficiency of algorithms. However, the gap between theoretical knowledge and practical application can make it challenging for students to appreciate the importance of expectation in real-world contexts. This paper seeks to bridge that gap by highlighting the relationship between expectation and the population mean. To accomplish this, two experiments are presented, with tasks specifically designed to engage students in hands-on learning experiences in practical problem-solving. The first experiment focuses on the number of successes of the careless clerk, while the second experiment involves searching for all occurrences of a value in a randomly selected array, addressing the key question of the algorithm's expected time complexity. By presenting tasks that demonstrate the practical application of expectation, we aim to equip students with the tools needed to make informed decisions when designing and optimizing algorithms. © 2025 Teaching Statistics Trust.

关键词： Sun   Tensors   Vectors   Optimization   Computer science   Complexity theory   Bipartite graph   Artificial intelligence   Feature extraction   Surges   Dynamic anchor learning   incomplete multi-view clustering   bipartite graph learning   pseudo-label supervise learning   low-rank tensor  

摘要： Compared to static anchor selection, existing dynamic anchor learning could automatically learn more flexible anchors to improve the performance of large-scale multi-view clustering. Despite improving the flexibility of anchors, these methods do not pay sufficient attention to the alignment and fairness of learned anchors. Specifically, within each cluster, the positions and quantities of cross-view anchors may not align, or even anchor absence in some clusters, leading to severe anchor misalignment and imbalance issues. These issues result in inaccurate graph fusion and a reduction in clustering performance. Besides, in practical applications, missing information caused by sensor malfunctions or data losses could further exacerbate anchor misalignment and imbalance. To overcome such challenges, a novel Incomplete Multi-view Clustering with Paired and Balanced Dynamic Anchor Learning (PBDAL) is proposed to ensure the alignment and fairness of anchors. Unlike existing unsupervised anchor learning, we first design a paired and balanced dynamic anchor learning scheme to supervise dynamic anchors to be aligned and fair in each cluster. Meanwhile, we develop an enhanced bipartite graph tensor learning to refine paired and balanced anchors. Our superiority, effectiveness, and efficiency are all validated by performing extensive experiments on multiple public datasets.

关键词： Education   Computer science   Computer science education   Generative adversarial networks   Computational modeling   Indexes   Ethics   Chatbots   Training   Testing   Automated MCQ generation   conditional generative adversarial networks (cGANs)   computer science education   dataset curation   educational assessment  

摘要： This work presents a novel perspective towards generating automated multiple-choice questions (MCQs)-a task fundamentally different due to the highly dynamic nature of computer science education, which spans several sub-domains. Taking advantage of Conditional Generative Adversarial Networks (cGANs), our model provides a versatile approach to addressing the need for diversity and context in relevant MCQ generation across proficiency levels, topic areas. Resulting MCQs inspire implementations within a variety of educational environments - from classrooms, to online courses, and finally exams - equipping teachers with an instrument that could be easily adapted based on the specific needs o students. The model is trained on a carefully constructed dataset that includes material from more than 20 subareas in computer science, consisting of materials such as textbooks, online encyclopedias and Q&A websites. Through rigorous evaluation using comprehensive performance metrics, including Question Relevance Score (QRS), Diversity Index (DI), and Difficulty Alignment Accuracy (DAA), we demonstrate the efficacy and robustness of our framework in generating high-quality MCQs. Moreover, we address ethical considerations inherent in AI-driven educational assessment, ensuring fairness, transparency, and accountability in the MCQ generation process. The cGAN architecture facilitates the generation of contextually relevant MCQs across various proficiency levels and subject domains, enhancing the educational assessment process. The comprehensive dataset developed for this study encompasses diverse computer science topics curated from authoritative textbooks, online resources, question banks, and instructor-generated content. Additionally, a user-friendly QT application has been developed, enabling seamless integration of the cGAN model into educational environments. Through rigorous evaluation and ethical considerations, this framework demonstrates its efficacy, ensuring fairness, tr

关键词： Computer Technology   Railway Transportation   Technological Innovation   Technology Transfer   MPSO Algorithm  

摘要： This article aims to discuss the influence of computer technology on the innovation and technology transfer of modern railway transportation. By historical analysis and empirical research, this article first reviews the evolution of railway transportation from steam locomotive to High-Speed Railways, and then compares and analyzes the performance of the improved multi-objective particle swarm optimization (MPSO) algorithm and traditional particle swarm optimization (PSO) algorithm in train operation scheduling through designing simulation experiments. The experiment selected the representative train operation data sets, and the first 25 and 15 data items are used as training sets respectively to predict the subsequent data items, and the prediction results of MPSO algorithm, traditional PSO algorithm and support vector machine algorithm are compared. The results show that MPSO algorithm is excellent in prediction accuracy, convergence speed and error control, and its prediction results are closer to the actual train running state, which verifies the effectiveness of computer technology in optimizing railway transportation scheduling.