检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Biyyala, Varun Kathuria, Bharat Chanderprakash Li, Jialu Zhang, Youshan Graduate Computer Science and Engineering Department Katz School of Science and Health Yeshiva University 205 Lexington Avenue New YorkNY10016 United States

Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and hierarchical dependencies, while image scores fail to assess temporal consistency. We present SST-EM (Semantic, Spatial, and Temporal Evaluation Metric), a novel evaluation framework that leverages modern Vision-Language Models (VLMs), Object Detection, and Temporal Consistency checks. SST-EM comprises four components: (1) semantic extraction from frames using a VLM, (2) primary object tracking with Object Detection, (3) focused object refinement via an LLM agent, and (4) temporal consistency assessment using a Vision Transformer (ViT). These components are integrated into a unified metric with weights derived from human evaluations and regression analysis. The name SST-EM reflects its focus on Semantic, Spatial, and Temporal aspects of video evaluation. SST-EM provides a comprehensive evaluation of semantic fidelity and temporal smoothness in video editing. The source code is available in the GitHub Repository. © 2025, CC0.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Where Do You Go? Pedestrian Trajectory Prediction using Scene Features

arXiv

引用

arXiv 2025年

作者： Rezaei, Mohammad Ali Ayar, Fardin Javanmardi, Ehsan Tsukada, Manabu Javanmardi, Mahdi Department of Computer Engineering Amirkabir University of Technology Tehran Iran Graduate School of Information Science and Technology The University of Tokyo Tokyo Japan

Accurate prediction of pedestrian trajectories is crucial for enhancing the safety of autonomous vehicles and reducing traffic fatalities involving pedestrians. While numerous studies have focused on modeling interactions among pedestrians to forecast their movements, the influence of environmental factors and scene-object placements has been comparatively underexplored. In this paper, we present a novel trajectory prediction model that integrates both pedestrian interactions and environmental context to improve prediction accuracy. Our approach captures spatial and temporal interactions among pedestrians within a sparse graph framework. To account for pedestrian-scene interactions, we employ advanced image enhancement and semantic segmentation techniques to extract detailed scene features. These scene and interaction features are then fused through a cross-attention mechanism, enabling the model to prioritize relevant environmental factors that influence pedestrian movements. Finally, a temporal convolutional network processes the fused features to predict future pedestrian trajectories. Experimental results demonstrate that our method significantly outperforms existing state-of-the-art approaches, achieving ADE and FDE values of 0.252 and 0.372 meters, respectively, underscoring the importance of incorporating both social interactions and environmental context in pedestrian trajectory prediction. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polyp Detection in Colonoscopy Videos via Boosted Multi-Scale Feature Fusion

Polyp Detection in Colonoscopy Videos via Boosted Multi-Scal...

引用

IEEE International Symposium on Biomedical Imaging

作者： Jatin Kayasth Ashish Beary Likun Xia Youshan Zhang Ming Ma Department of Graduate Computer Science and Engineering Katz School of Science and Health Yeshiva University New York NY USA Capital Normal University Beijing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

computer-aided detection (CAD) systems are vital for advancing colorectal cancer screening and prevention through effective polyp detection approaches. Recent breakthroughs in deep learning technology have greatly enhanced medical image analysis and CAD systems for polyp detection. This paper proposes to use a boosted multi-scale feature fusion method for polyp detection in colonoscopy videos. The method is evaluated on a publicly available colonoscopy video dataset, in terms of metrics mAP, precision, recall and F1-score. In comparison with other state-of-the-art polyp detection methods, our method achieves better performance in both accuracy and efficiency, positioning it as a robust choice for real-time polyp detection in colonoscopy videos.

关键词： Deep learning Measurement Image analysis Prevention and mitigation Colonoscopy Feature extraction Market research Real-time systems Videos Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Intelligent Reflecting Surface-Assisted Millimeter Wave Communications: Cross Attention-aided Variational Autoencoder-based Precoding Design

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Wu, Meng-Hsun Chen, Hong-Yunn Yang, Ta-Wei Hsu, Chih-Chuan Huang, Chih-Wei Chou, Cheng-Fu National Taiwan University Department of Computer Science and Information Engineering Taipei Taiwan National Pingtung University Department of Computer Science and Information Engineering Pingtung Taiwan National Taiwan University Graduate Institute of Networking and Multimedia Taipei Taiwan National Taiwan University Department of Forestry and Resource Conservation Taipei Taiwan National Central University Department of Communication Engineering Taoyuan Taiwan

Sixth-generation technology, which surpasses 5G with faster speeds, lower latency, and increased capacity, highlights the pivotal intelligent reflecting surface (IRS) and optimizes wireless communication by precisely handling incoming radio waves, resulting in enhanced network coverage, capacity, and energy efficiency. In real-world scenarios, however, hybrid precoding in the IRS is affected by noise and interference. To address this, we propose DVAE-CATT-Precoding (variational denoising autoencoder model with cross attention precoding), in which cross attention enhances channel precoding by reevaluating the significance of the time domain. A variational autoencoder (VAE) is trained with reconstruction and regularization losses for parameter optimization, and its learned latent space facilitates feature capture for intra-channel precoding in both the frequency and spatial domains. We use an autoencoder to reconstruct the latent space, improving our analog precoding module's ability to capture global domain features. Additionally, a CNN models frequency and spatial domain intricacies for efficient channel precoding, reducing interference in the proposed digital precoding module. Numerical results show remarkable improvements in MSE, achievable rate, generalizability, and robustness compared to previous works. © 2015 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Knowledge Retrieval Based on Generative AI

arXiv

引用

arXiv 2025年

作者： Yang, Te-Lun Liu, Jyi-Shane Tseng, Yuen-Hsien Jang, Jyh-Shing Roger Graduate Institute of Networking and Multimedia National Taiwan University Taiwan Department of Computer Science National Chengchi University Taiwan Graduate Institute of Library & Information Studies National Taiwan Normal University Taiwan Department of Computer Science & Information Engineering National Taiwan University Taiwan

This study develops a question-answering system based on Retrieval-Augmented Generation (RAG) using Chinese Wikipedia and Lawbank as retrieval sources. Using TTQA and TMMLU+ as evaluation datasets, the system employs BGEM3 for dense vector retrieval to obtain highly relevant search results and BGE-reranker to reorder these results based on query relevance. The most pertinent retrieval outcomes serve as reference knowledge for a Large Language Model (LLM), enhancing its ability to answer questions and establishing a knowledge retrieval system grounded in generative AI. The system's effectiveness is assessed through a two-stage evaluation: automatic and assisted performance evaluations. The automatic evaluation calculates accuracy by comparing the model's auto-generated labels with ground truth answers, measuring performance under standardized conditions without human intervention. The assisted performance evaluation involves 20 finance-related multiple-choice questions answered by 20 participants without financial backgrounds. Initially, participants answer independently. Later, they receive system-generated reference information to assist in answering, examining whether the system improves accuracy when assistance is provided. The main contributions of this research are: (1) Enhanced LLM Capability: By integrating BGE-M3 and BGE-reranker, the system retrieves and reorders highly relevant results, reduces hallucinations, and dynamically accesses authorized or public knowledge sources. (2) Improved Data Privacy: A customized RAG architecture enables local operation of the LLM, eliminating the need to send private data to external servers. This approach enhances data security, reduces reliance on commercial services, lowers operational costs, and mitigates privacy risks. © 2025, CC BY.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy Efficiency in Wireless-Powered MEC Systems through Lyapunov-Guided Deep Reinforcement Learning

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhu, Bincheng Huang, Liang Chi, Kaikai Alharbi, Abdullah Yu, Keping Guizani, Mohsen Zhejiang University of Technology School of Computer Science and Technology China King Saud University Community College Computer Science Department Riyadh11437 Saudi Arabia Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan United Arab Emirates

This paper addresses long-term energy efficiency in a wireless power transfer-enabled mobile-edge computing (MEC) system, facing challenges from time-varying channels and stochastic task arrivals. We formulate the problem to optimize offloading, power transfer duration, and energy consumption while ensuring queue stability. We propose a novel Lyapunov-guided deep reinforcement learning (LyCNN-DRL) algorithm to efficiently solve the long-term mixed integer non-linear programming problem without prior knowledge of future conditions. The approach decomposes the problem into resource allocation and binary offloading components, using a convolutional neural network for near-optimal offloading decisions and the Lagrange dual function for optimal resource allocation. Extensive simulations show that LyCNN-DRL outperforms benchmark algorithms in energy efficiency and latency, achieving over 97% of the optimal utility while reducing execution latency to approximately 50 milliseconds in ten-WD networks. Additionally, we derive the trade-off between energy efficiency and queue length as [O(1/V),O(V)], where V is the Lyapunov control parameter. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Single-Longitudinal Mode Ytterbium-Doped Fiber Laser Using Four 2 × 2 Fiber Couplers for Multiple Subring Ring Cavities

引用

IEEE Journal of Quantum Electronics 2025年第2期61卷

作者： Wang, Zi Pamukti, Brian Meng, Fan-Chang Liaw, Shien-Kuei Yeh, Chien-Hung Chen, Jem-Kun National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei10607 Taiwan National Taiwan University of Science and Technology Graduate Institute of Electro-Optical Engineering Taipei10607 Taiwan Feng Chia University Department of Photonics Taichung40724 Taiwan National Taiwan University of Science and Technology Department of Materials Science and Engineering Taipei10607 Taiwan

In this paper, we present a single-longitudinal mode (SLM) Ytterbium-doped fiber laser (YDFL) featuring a six-subring cavity (SSRC) structure. The YDFL achieves SLM output through use of the SSRC architecture. We evaluated the stability of both wavelength and power during the experimental measurements. The results show that the wavelength and power fluctuations over one hour were less than 0.01 nm and 0.03 dB, respectively. Measurements confirmed that the YDFL, with the SSRC structure, operates stably in a SLM state. Finally, by applying Lorentzian fitting to the measured data, a linewidth of 2.4 kHz was obtained. © 1965-2012 IEEE.

关键词： Linewidth

来源：评论

学校读者我要写书评

暂无评论

A Survey on Intelligent Solutions for Increased Video Delivery Quality in Cloud-Edge-End Networks

引用

IEEE Communications Surveys and Tutorials 2025年第2期27卷 1363-1394页

作者： Shi, Wanxin Li, Qing Yu, Qian Wang, Fulin Shen, Gengbiao Jiang, Yong Xu, Yang Ma, Lianbo Muntean, Gabriel-Miro Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518055 China Fudan University School of Computer Science Shanghai200433 China Peng Cheng Laboratory Department of Strategic and Advanced Interdisciplinary Research Shenzhen518066 China Institute of Future Networks Southern University of Science and Technology Shenzhen518055 China Tecorigin Software Department Shanghai200120 China Peng Cheng Laboratory Department of Strategic and Advanced Interdisciplinary Research Shenzhen518055 China Northeastern University College of Software Shenyang110819 China Dublin City University Performance Engineering Laboratory School of Electronic Engineering DublinD09 DD7R Ireland

The digital age has brought a significant increase in video traffic. This traffic growth, driven by rapid Internet advancements and a surge in multimedia applications, presents both challenges and opportunities to video transmissions. Users seek high-quality video content, prompting service providers to offer high-definition options to improve user experience and increase profits. However, traditional end-to-end best-effort networks struggle to meet the demands of extensive video streaming and ensure good user Quality of Experience (QoE), especially in high user mobility scenarios or fluctuating network conditions. Addressing some of these challenges, content delivery networks (CDN) are instrumental in delivering video content, but they are under increased pressure to support high quality and reduce their deployment and maintenance costs. Currently, cloud-edge-end fusion technologies have become one of the optimization directions for network services due to their flexibility and scalability. At the same time, in the context of the recent advancements in computing-focused network paradigms, intelligent enhancement techniques (e.g., super-resolution), commonly utilized in image optimization, have been adopted as a pivotal solution for increasing video delivery quality. To illustrate the essence and employment of the intelligent enhancement solutions for video streaming, this paper first outlines the video streaming process, discusses relevant evaluation metrics, and examines aspects related to the intelligent solutions. Then the paper presents the intelligent enhancement process of video streaming, analyzes various typical intelligent models for content enhancement and highlights their distinct characteristics. This exploration delves deeper into various intelligent quality-improved solutions, scrutinizing their applicability across different transmission scenarios like Video on Demand (VoD) and live streaming, and shedding light on their strengths and weaknesses from

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Diffusion Models in Low-Level Vision: A Survey

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4630-4651页

作者： He, Chunming Shen, Yuqi Fang, Chengyu Xiao, Fengyang Tang, Longxiang Zhang, Yulun Zuo, Wangmeng Guo, Zhenhua Li, Xiu Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518055 China Duke University Department of Biomedical Engineering DurhamNC27708 United States Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai China Harbin Institute of Technology School of Computer Science and Technology Harbin150006 China Tianyijiaotong Technology Ltd. Suzhou215131 China

Deep generative models have gained considerable attention in low-level vision tasks due to their powerful generative capabilities. Among these, diffusion model-based approaches, which employ a forward diffusion process to degrade an image and a reverse denoising process for image generation, have become particularly prominent for producing high-quality, diverse samples with intricate texture details. Despite their widespread success in low-level vision, there remains a lack of a comprehensive, insightful survey that synthesizes and organizes the advances in diffusion model-based techniques. To address this gap, this paper presents the first comprehensive review focused on denoising diffusion models applied to low-level vision tasks, covering both theoretical and practical contributions. We outline three general diffusion modeling frameworks and explore their connections with other popular deep generative models, establishing a solid theoretical foundation for subsequent analysis. We then categorize diffusion models used in low-level vision tasks from multiple perspectives, considering both the underlying framework and the target application. Beyond natural image processing, we also summarize diffusion models applied to other low-level vision domains, including medical imaging, remote sensing, and video processing. Additionally, we provide an overview of widely used benchmarks and evaluation metrics in low-level vision tasks. Our review includes an extensive evaluation of diffusion model-based techniques across six representative tasks, with both quantitative and qualitative analysis. Finally, we highlight the limitations of current diffusion models and propose four promising directions for future research. This comprehensive review aims to foster a deeper understanding of the role of denoising diffusion models in low-level vision. For those interested, a curated list of diffusion model-based techniques, datasets, and related information across over 20 low-level visi

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Soybean Disease Detection via Interpretable Hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with Cross-Modal Attention

arXiv

引用

arXiv 2025年

作者： Jahin, Md Abrar Soudeep, Shahriar Mridha, M.F. Dey, Nilanjan Okinawa Institute of Science and Technology Graduate University Okinawa904-0412 Japan Department of Computer Science American International University-Bangladesh Dhaka1229 Bangladesh Department of Computer Science & Engineering Techno International New Town Kolkata700156 India

Soybean leaf disease detection is critical for agricultural productivity but faces challenges due to visually similar symptoms and limited interpretability in conventional methods. While Convolutional Neural Networks (CNNs) excel in spatial feature extraction, they often neglect inter-image relational dependencies, leading to misclassifications. This paper proposes an interpretable hybrid Sequential CNN-Graph Neural Network (GNN) framework that synergizes MobileNetV2 for localized feature extraction and GraphSAGE for relational modeling. The framework constructs a graph where nodes represent leaf images, with edges defined by cosine similarity-based adjacency matrices and adaptive neighborhood sampling. This design captures fine-grained lesion features and global symptom patterns, addressing inter-class similarity challenges. Cross-modal interpretability is achieved via Grad-CAM and Eigen-CAM visualizations, generating heatmaps to highlight disease-influential regions. Evaluated on a dataset of ten soybean leaf diseases, the model achieves 97.16% accuracy, surpassing standalone CNNs (≤95.04%) and traditional machine learning models (≤77.05%). Ablation studies validate the sequential architecture’s superiority over parallel or single-model configurations. With only 2.3 million parameters, the lightweight MobileNetV2-GraphSAGE combination ensures computational efficiency, enabling real-time deployment in resource-constrained environments. The proposed approach bridges the gap between accurate classification and practical applicability, offering a robust, interpretable tool for agricultural diagnostics while advancing CNN-GNN integration in plant pathology research. © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：