检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Li, Jiaqi Xiong, Gaojie Wu, Xing Harbin Institute of Technology Computer Sciense and Technology Guangdong Shenzhen China University of Electronic Science and Technology School of Information and Software Engineering Sichuan Chengdu China Zhejiang Vocational Academy of Art Zhejiang Hangzhou China

ISBN: (纸本)9798350317558

Multimedia database online integration system plays an important role in today's information age. However, the performance of the integrated system is limited by the problems of low accuracy, insufficient recall rate and long running time of traditional methods in processing multimedia data. This paper designs an online integration system based on artificial intelligence (AI) and verifies its effectiveness and feasibility through experiments so as to overcome these problems. In the study, multimedia datasets suitable for the experimental needs are selected and the AI-based online integration system is compared with traditional methods. Through the analysis of accuracy, recall, F1 value and mean square error, it is found that the online integration system based on AI has obvious advantages in multimedia data integration. The results of this paper demonstrate the feasibility and effectiveness of an online integration system based on AI. It is able to enhance the accuracy and efficiency of multimedia data integration while reducing runtime and resource consumption. © 2024 IEEE.

关键词： artificial intelligence integration efficiency multimedia database online integration

来源：评论

学校读者我要写书评

暂无评论

KANOCLIP: ZERO-SHOT ANOMALY DETECTION THROUGH KNOWLEDGE-DRIVEN PROMPT LEARNING AND ENHANCED CROSS-MODAL INTEGRATION

arXiv

引用

arXiv 2025年

作者： Li, Chengyuan Zhou, Suyang Kong, Jieping Qi, Lei Xue, Hui College of Software Engineering Southeast University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show potential in ZSAD but have limitations: relying on manually crafted fixed textual descriptions or anomaly prompts is time-consuming and prone to semantic ambiguity, and CLIP struggles with pixel-level anomaly segmentation, focusing more on global semantics than local details. To address these limitations, We introduce KAnoCLIP, a novel ZSAD framework that leverages vision-language models. KAnoCLIP combines general knowledge from a Large Language Model (GPT-3.5) and fine-grained, image-specific knowledge from a Visual Question Answering system (Llama3) via Knowledge-Driven Prompt Learning (KnPL). KnPL uses a knowledge-driven (KD) loss function to create learnable anomaly prompts, removing the need for fixed text prompts and enhancing generalization. KAnoCLIP includes the CLIP visual encoder with V-V attention (CLIP-VV), Bi-Directional Cross-Attention for Multi-Level Cross-Modal Interaction (Bi-CMCI), and Conv-Adapter. These components preserve local visual semantics, improve local cross-modal fusion, and align global visual features with textual information, enhancing pixel-level anomaly detection. KAnoCLIP achieves state-of-the-art performance in ZSAD across 12 industrial and medical datasets, demonstrating superior generalization compared to existing methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LogMT: A Self-supervised Log Anomaly Detection Method Based on Multi-Tasks

LogMT: A Self-supervised Log Anomaly Detection Method Based ...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Wenhui Xie Qingjian Ni College of Software Engineering Southeast University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

With the rapid development of software systems, logs have become essential data for monitoring the security and stability of computer systems. Current log anomaly detection methods usually rely on large volumes of labeled data, which can lead to class imbalance and fail to fully leverage the features of log sequences. To address these problems, we propose a novel anomaly detection model LogMT, which performs anomaly detection based on multiple self-supervised tasks. LogMT uses Transformer encoder to extract feature vectors from log event sequences and trains the model through self-supervised tasks for anomaly detection. To better capture the bidirectional context information of log sequences, we introduce the dynamic masked log templates prediction task, which enhances the contextual understanding of the model through predicting masked log templates in the log sequence. In the minimization of outlier factor task, we map log sequence features to a high-dimensional space and cluster similar normal log sequences together, improving the model's capability to distinguish anomaly features. Finally, we conducted extensive experiments on three public datasets, and the experimental results demonstrate the effectiveness and superiority of LogMT.

关键词： Production Predictive models Feature extraction Transformers Minimization software systems Multitasking Vectors Stability analysis Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Large Point-to-Gaussian Model for Image-to-3D Generation 24

Large Point-to-Gaussian Model for Image-to-3D Generation

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Lu, Longfei Gao, Huachen Dai, Tao Zha, Yaohua Hou, Zhi Wu, Junta Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Tencent Shenzhen Hunyuan China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798400706868

Recently, image-to-3D approaches have significantly advanced the generation quality and speed of 3D assets based on large reconstruction models, particularly 3D Gaussian reconstruction models. Existing large 3D Gaussian models directly map 2D image to 3D Gaussian parameters, while regressing 2D image to 3D Gaussian representations is challenging without 3D priors. In this paper, we propose a large Point-to-Gaussian model, that inputs the initial point cloud produced from large 3D diffusion model conditional on 2D image to generate the Gaussian parameters, for image-to-3D generation. The point cloud provides initial 3D geometry prior for Gaussian generation, thus significantly facilitating image-to-3D Generation. Moreover, we present the Attention mechanism, Projection mechanism, and Point feature extractor, dubbed as APP block, for fusing the image features with point cloud features. The qualitative and quantitative experiments extensively demonstrate the effectiveness of the proposed approach on GSO and Objaverse datasets, and show the proposed method achieves state-of-the-art performance. © 2024 ACM.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Optimizing Generative AI Applications: A Comparative Study of Effective Prompting Techniques

Optimizing Generative AI Applications: A Comparative Study o...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Shivya Jyoti Moulik Tejpal Jothi K R Department of Software Systems School of Computer Science & Engineering Vellore Institute of Technology Vellore India Department of Computational Intelligence School of Computer Science & Engineering Vellore Institute of Technology Vellore India

ISBN: (数字)9798331535193

ISBN: (纸本)9798331535209

Generative Artificial Intelligence (GenAI) has emerged as a pivotal technology across various industries, driving advancements in automation, decision-making, and content generation. This paper investigates the efficacy of the prompt engineering methods such as zero-shot, one-shot, and few-shot prompting—in optimizing GenAI systems for diverse applications. Through a comprehensive literature review and an empirical survey involving 13 use cases such as chatbots, content creation, and medical decision support, we evaluate the performance of these prompting methods. The findings reveal that few-shot prompting excels in complex tasks, while zero-shot and one-shot prompting are more effective for simpler tasks. These insights provide practical guidance for leveraging GenAI across different domains, contributing to the advancement of AI-driven solutions.

关键词： Surveys Pervasive computing Industries Decision support systems Social networking (online) Large language models Chatbots Prompt engineering Human resource management Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Learning to Schedule Job-Shop Problems via Hierarchical Reinforcement Learning

Learning to Schedule Job-Shop Problems via Hierarchical Rein...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Liao, Zijun Li, Qiwen Dai, Yuanzhi Zhang, Zizhen Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Brown University Department of Computer Science ProvidenceRI United States Sun Yat-sen University School of Software Engineering Zhuhai China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

The job-shop scheduling problem (JSSP) is a classic combinatorial optimization problem in the areas of computer science and operations research. It is closely associated with many industrial scenarios. In today's society, the demand for efficient and stable scheduling algorithms has significantly increased. More and more researchers have recently tried new methods to solve JSSP. In this paper, we effectively formulate the scheduling process of JSSP as a Semi-Markov Decision Process. We then propose a method of using hierarchical reinforcement learning with graph neural networks to solve JSSP. We also demonstrate that larger-sized instances require the support of a bigger number of sub-policies and different scheduling phases require using different sub-policies. © 2022 IEEE.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Hierarchies and Invariant Disease-Indicative Feature Learning for computer Aided Diagnosis of Multiple Fundus Diseases 39

Deep Hierarchies and Invariant Disease-Indicative Feature Le...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lin, Yuxin Wang, Wei Luo, Xiaoling Wu, Zhihao Liu, Chengliang Wen, Jie Xu, Yong School of Computer Science and Technology Harbin Institute of Technology Shenzhen China College of Computer Science and Software Engineering Shenzhen University China Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)157735897X

With the advancement of computer vision, numerous models have been proposed for screening of fundus diseases. However, the recognition of multiple fundus diseases is often hampered by the simultaneous presence of multiple disease types and the confluence of lesion types in fundus images. This paper addresses these challenges by conceptualizing them as multi-level feature fusion and self-supervised disease-indicative feature learning problems. We decode fundus images at various levels of granularity to delineate scenarios wherein multiple diseases and lesions co-occur. To effectively integrate these features, we introduce a hierarchical vision transformer (HVT) that adeptly captures both inter-level and intra-level dependencies. A novel forward-attention module is proposed to enhance the integration of lower-level semantic information into higher semantic layers, thereby enriching the representation of complex features. Additionally, we introduce a novel self-supervised mask-consistent feature learner (MCFL). Unlike traditional mask-autoencoders that reconstruct original images using encoder-decoder structures, MCFL utilizes a teacher-student framework to reconstruct mask-consistent feature maps. In this setup, exponential moving averaging is employed to derive classification-guided features, serving as labels for reconstruction rather than merely reconstructing the original images. This innovative approach facilitates the extraction of disease-indicative features. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art models. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Empowering visible-infrared person re-identification with large foundation models 24

Empowering visible-infrared person re-identification with la...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhangyi Hu Bin Yang Mang Ye National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9798331314385

Visible-Infrared Person Re-identification (VI-ReID) is a challenging cross-modal retrieval task due to significant modality differences, primarily resulting from the absence of color information in the infrared modality. The development of large foundation models like Large Language Models (LLMs) and Vision Language Models (VLMs) motivates us to explore a feasible solution to empower VI-ReID with off-the-shelf large foundation models. To this end, we propose a novel Text-enhanced VI-ReID framework driven by Large Foundation Models (TVI-LFM). The core idea is to enrich the representation of the infrared modality with textual descriptions automatically generated by VLMs. Specifically, we incorporate a pre-trained VLM to extract textual features from texts generated by VLM and augmented by LLM, and incrementally fine-tune the text encoder to minimize the domain gap between generated texts and original visual modalities. Meanwhile, to enhance the infrared modality with extracted textual representations, we leverage modality alignment capabilities of VLMs and VLM-generated feature-level filters. This enables the text model to learn complementary features from the infrared modality, ensuring the semantic structural consistency between the fusion modality and the visible modality. Furthermore, we introduce modality joint learning to align features across all modalities, ensuring that textual features maintain stable semantic representation of overall pedestrian appearance during complementary information learning. Additionally, a modality ensemble retrieval strategy is proposed to leverage complementary strengths of each query modality to improve retrieval effectiveness and robustness. Extensive experiments on three expanded VI-ReID datasets demonstrate that our method significantly improves the retrieval performance, paving the way for the utilization of large foundation models in downstream multi-modal retrieval tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on the Performance of Amorphous IGZO TFT Thin-Film Transistor with Ti/Au Stacking as the Source/Drain 8

Study on the Performance of Amorphous IGZO TFT Thin-Film Tra...

引用

8th International Conference on Signal and Image Processing, ICSIP 2023

作者： Lu, Qingru Li, Bing Chen, Rui Huang, Xiaodong Southeast University Cheng Xian College School of Electron and Computer Nanjing China Southeast University School of Cyber Science and Engineering Nanjing China Nanjing Vocational University of Industry Technology School of Computer and Software Engineering Nanjing China Southeast University Key Laboratory of MEMS of the Ministry of Education Nanjing China

ISBN: (纸本)9798350397932

Through magnetron sputtering, a Ti/Au stack was adopted as the source/drain of the transistor, and Amorphous indium-gallium-zinc-oxide (α-IGZO or IGZO) was utilized as the active layer (150μm×150μm) to fabricate a bottom-gate contact thin-film transistor (TFT) with a structure of Ti/Au/IGZO (150μm×150μm)/SiO2/P. The electrical characteristics of this device were studied. The experiment showed that by depositing Ti/Au electrodes as the source/drain, and generating a TiOx oxide layer at the interface between the IGZO layer and the Ti/Au electrodes after annealing, the threshold voltage of the device was 4.7V, and the sub-threshold swing was relatively small. The gate bias voltage had excellent regulation on the leakage current of the device, and the device exhibited good cut-off characteristics. © 2023 IEEE.

关键词： Thin film transistors

来源：评论

学校读者我要写书评

暂无评论

An efficient and balanced feature pyramid network: shared-FPN

引用

Optoelectronics Letters 2025年

作者： Tian Sulong Qin Longfei Pang Wenchao Gao Ying Zhao Dexin School of Computer Science and Engineering， Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology， Tianjin University of Technology

In the field of object detection， it is challenging to achieve a balance between neck complexity and accuracy. To address this issue， we propose an efficient and decoupled neck module called Shared-FPN(Shared Feature Pyramid Network). Our design aims to effectively address the trade-off between these two factors. Neck modules are crucial for effectively fusing multi-scale information in neural network models. However， traditional neck designs， with their single structure， have struggled to significantly improve detection performance. In recent years， the incorporation of neural architecture search techniques in neck design has led to an increase in model complexity. This trade-off between model complexity and detection performance highlights the need for more efficient neck design approaches. Not only does Shared-FPN not increase the number of model parameters and FLOPs， but it also can be easily ported to any of the detection models. It improves on PAFPN by using transposed convolution with a large convolution kernel as the upsampling module， designing spatial pyramidal pooling-fast downsampling(SPPFD) based on shared pooling， and designing shared convolution as the right part module. To evaluate the performance of Shared-FPN in object detection tasks， we conducted experiments on object detection datasets. The results show that Shared-FPN achieved excellent performance across all sizes. In particular， on the VOC 2012 dataset， which contains mostly large objects， Shared-FPN's mAP was improved by 11.2% compared to FPN with YOLOX-s as the detector. On the COCO dataset， which contains mostly small objects， Shared-FPN's mAP was improved by 7.8% compared to FPN and 7.1% compared to PAFPN with Faster RCNN as the detector. Shared-FPN can be easily inserted into any of the detectors for better performance in various scenarios， such as small， medium or large objects.

关键词：

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：