检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Ning, Xin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University Beijing China School of Computing Macquarie University Sydney Australia Institute of Semiconductors Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400706868

The development of person search techniques has been greatly promoted in recent years for its superior practicality and challenging goals. Despite their significant progress, existing person search models still lack the ability to continually learn from increasing real-world data and adaptively process input from different domains. To this end, this work introduces the continual person search task that sequentially learns on multiple domains and then performs person search on all seen domains. This requires balancing the stability and plasticity of the model to continually learn new knowledge without catastrophic forgetting. For this, we propose a Prompt-based Continual Person Search (PoPS) model in this paper. First, we design a compositional person search transformer to construct an effective pre-trained transformer without exhaustive pre-training from scratch on large-scale person search data. This serves as the fundamental for prompt-based continual learning. On top of that, we design a domain incremental prompt pool with a diverse attribute matching module. For each domain, we independently learn a set of prompts to encode the domain-oriented knowledge. Meanwhile, we jointly learn a group of diverse attribute projections and prototype embeddings to capture discriminative domain attributes. By matching an input image with the learned attributes across domains, the learned prompts can be properly selected for model inference. Extensive experiments are conducted to validate the proposed method for continual person search. The source code is available at https://***/PatrickZad/PoPS. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game 38

Error Analysis of Spherically Constrained Least Squares Refo...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Xiyuan Liu, Weiwei School of Computer Science Wuhan University China National Engineering Research Center for Multimedia Software Wuhan University China Institute of Artificial Intelligence Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

The Stackelberg prediction game (SPG) is a popular model for characterizing strategic interactions between a learner and an adversarial data provider. Although optimization problems in SPGs are often NP-hard, a notable special case involving the least squares loss (SPG-LS) has gained significant research attention recently [1, 2, 3]. The latest state-of-the-art method for solving the SPG-LS problem is the spherically constrained least squares reformulation (SCLS) method proposed in the work of [3]. However, the paper [3] lacks theoretical analysis on the error of the SCLS method, which limits its large-scale applications. In this paper, we investigate the estimation error between the learner obtained by the SCLS method and the actual learner. Specifically, we reframe the estimation error of the SCLS method as a Primary Optimization (PO) problem and utilize the Convex Gaussian min-max theorem (CGMT) to transform the PO problem into an Auxiliary Optimization (AO) problem. Subsequently, we provide a theoretical error analysis for the SCLS method based on this simplified AO problem. This analysis not only strengthens the theoretical framework of the SCLS method but also confirms the reliability of the learner produced by it. We further conduct experiments to validate our theorems, and the results are in excellent agreement with our theoretical predictions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emergency Transportation and Structural Prediction and Optimization of Goods Based on ARIMA and Multi-objective E-commerce Logistics Network Model 1

Emergency Transportation and Structural Prediction and Optim...

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Nie, Yiyang Chen, Xiang Wu, Xuanli Deng, Zihao Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China Hunan University of Science and Technology Shcool of Mathematics and Computational Science Xiangtan China

ISBN: (纸本)9798350323795

With the development of the internet, online shopping has gradually become a popular way of shopping among the general public, which in turn poses a greater challenge to the e-commerce logistics network. Predicting the volume of goods for each logistics site and route, and establishing a model for quickly adjusting the network in response to sudden situations can save logistics network costs and improve its efficiency. Therefore, this article has done the following work: first, it establishes an effective logistics network volume prediction model;second, for the two scenarios of network structure that cannot be modified and can be modified, it provides a model that can effectively guide the adjustment of the volume of goods on each route when a logistics site is closed;finally, it establishes a logistics network evaluation model to evaluate the importance of logistics sites and routes. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Traffic Anomaly Detection Using Optimized Faster R-CNN

Traffic Anomaly Detection Using Optimized Faster R-CNN

引用

2024 International Conference on Electronics, Electrical and Information engineering, ICEEIE 2024

作者： Karim, Shahid Qadir, Akeel Han, Gao Li, Jing Ibrar, Muhammad Bibi, Irfana School of Information Engineering Xi'an Eurasia University 710065 China Software College Shenyang Normal University Shenyang China Department of Computer Science Faculty of Computing and Information Technology University of Punjab Punjab Lahore Pakistan

ISBN: (数字)9781510686809

ISBN: (纸本)9781510686793

This paper introduces a new method for traffic anomaly identification within the Faster R-CNN framework by combining the DenseNet module with the region proposals (RPs) processing block. The suggested approach seeks to improve feature extraction and RP creation in aerial imagery or CCTV frames to get beyond the drawbacks of the current methods. Discriminative features are extracted through DenseNet, and the RPs block makes it easier to provide a wide range of accurate and varied area proposals. Contrast correction techniques are applied to overcome the difficulties presented by low-resolution and low-contrast images frequently seen in surveillance scenarios. Comparing experimental results to state-of-the-art techniques, one can observe notable resilience and detection accuracy increases. The suggested method works exceptionally well in various traffic scenarios and environmental circumstances, indicating its potential for practical implementation in traffic surveillance systems. Overall, the study contributes to advancing the efficacy and reliability of anomaly detection in urban traffic environments. © 2024 SPIE.

关键词： Aerial photography

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

Self-Bidirectional Decoupled Distillation for Time Series Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4101-4110页

作者： Xiao, Zhiwen Xing, Huanlai Qu, Rong Li, Hui Feng, Li Zhao, Bowen Yang, Jiayi Southwest Jiaotong University School of Computing and Artificial Intelligence Chengdu610031 China Tangshan Institute of Southwest Jiaotong University Tangshan063000 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China University of Nottingham School of Computer Science NottinghamNG7 2RD 455356 United Kingdom Xi'an Jiaotong University School of Mathematics and Statistics Xi'an710049 China Tongji University School of Software Engineering Shanghai201804 China

Over the years, many deep learning algorithms have been developed for time series classification (TSC). A learning model's performance usually depends on the quality of the semantic information extracted from lower and higher levels within the representation hierarchy. Efficiently promoting mutual learning between higher and lower levels is vital to enhance the model's performance during model learning. To this end, we propose a self-bidirectional decoupled distillation (self-BiDecKD) method for TSC. Unlike most self-distillation algorithms that usually transfer the target-class knowledge from higher to lower levels, self-BiDecKD encourages the output of the output layer and the output of each lower level block to form a bidirectional decoupled knowledge distillation (KD) pair. The bidirectional decoupled KD promotes mutual learning between lower and higher level semantic information and extracts the knowledge hidden in the target and nontarget classes, helping self-BiDecKD capture rich representations from the data. Experimental results show that compared with a number of self-distillation algorithms, self-BiDecKD wins 35 out of 85 University of California, Riverside (UCR) 2018 datasets and achieves the smallest AVeraGe (AVG)_rank score, namely 3.2882. In particular, compared with a nonself-distillation baseline, self-BiDecKD results in 58/8/19 regarding 'win'/'tie'/'lose.' © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Blockchain Development 7th

Blockchain Development

引用

7th International Conference on Smart Computing and Communication, SmartCom 2022

作者： Xie, Siqi Cai, Jiahong Zhu, Hangyu Yang, Ce Chen, Lin Xiao, Weidong School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan411201 China Guangdong Financial High-Tech Zone "Blockchain +" Fintech Research Institute Foshan528253 China School of Software Engineering Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9783031281235

In recent years, blockchain research has set off an upsurge in academia, and it is called the next generation of value Internet. Because of its decentralization, anonymity, security, immutability, traceability and other characteristics, blockchain is gradually accepted and developed by people. With the deepening of research and the integration of technologies such as deep learning, blockchain has gradually been applied to various fields such as credit reporting, government, medical care, and industrial Internet of Things, not just the initial virtual currency field. This article mainly discusses the three important stages of blockchain public chain development, namely Bitcoin, Ethereum, and meta-verse, and introduces some basic supporting technologies of blockchain, as well as the research status and future trends of blockchain. Simple Analysis. By vertically introducing the development history of the blockchain, researchers can have a more concrete understanding of the status quo of the blockchain, and provide ideas for blockchain-related research. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Smart contract

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

Aspect-Based Sentiment Analysis on Amharic Text for Evaluating Ethio-Telecom Services 2

Aspect-Based Sentiment Analysis on Amharic Text for Evaluati...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Tesfa, Tarikwa Belete, Befikadu Abera, Samuel Mohapatra, Sudhir Kumar Das, Tapan Kumar Addis Ababa Science and Technology University Department of Software Engineering Addis Ababa Ethiopia Ethio Telecom Services Addis Ababa Ethiopia Sri Sri University Faculty of Emerging Technologies Cuttack India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

People are increasingly expressing their views and opinions about a company's goods or service on social media these days. For all types of businesses and organizations, sentiment analysis in text can be used to find prospective customers and obtain quick feedback on the services or goods they provided. As a result, the organization has a better chance and opportunity to meet the needs of the consumer. Using sentiment analysis, we may extract important information from the thoughts and emotions of an organization's supporters and clients. It examines natural language content produced about services and goods. Detailed opinion mining at the aspect/feature level to serve consumer and organizational needs. In this study, three different machine learning algorithms, these are Naïve Bayes (NB), Support Vector Machine (SVM), and K- Nearest Neighbor (KNN) are used to build the proposed aspect-based sentiment analysis model from the customer comments in Amharic text which is collected from Ethio-telecom official Facebook page. The collected data is annotated into sentiment polarity and aspect-based sentiment classes by the help of five annotators. After data annotation, different preprocessing tasks were implemented. Bag of words and TF-IDF word representation techniques were used to represent each unique word to their vector representation. The experiment was conducted on those three models and the result was validated. The labeled aspects were not balanced so that a SMOTE class imbalance handling technique was employed to the dataset. Finally, SVM model trained with TF-IDF word representation technique with SMOTE oversampled dataset has achieved the highest accuracy result of 98% as compared to NB and KNN. © 2024 IEEE.

关键词： Sentiment analysis

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：