检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Xu, Bo Li, Shufei Jing, Hongyu Du, Ming Song, Hui Wang, Hongya Xiao, Yanghua School of Computer Science and Technology Donghua University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

ISBN: (纸本)9798891761964

Text-to-SQL is a technology that converts natural language questions into executable SQL queries, allowing users to query and manage relational databases more easily. In recent years, large language models have significantly advanced the development of text-to-SQL. However, existing methods often overlook validation of the generated results during the SQL generation process. Current error identification methods are mainly divided into self-correction approaches based on large models and feedback methods based on SQL execution, both of which have limitations. We categorize SQL errors into three main types: system errors, skeleton errors, and value errors, and propose a multi-grained error identification method. Experimental results demonstrate that this method can be integrated as a plugin into various methods, providing effective error identification and correction capabilities. © 2025 Association for Computational Linguistics.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation 31

Enhancing Multimodal Named Entity Recognition through Adapti...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xu, Bo Jiang, Haiqi Wei, Jie Jing, Hongyu Du, Ming Song, Hui Wang, Hongya Xiao, Yanghua School of Computer Science and Technology Donghua University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

ISBN: (纸本)9798891761964

Multimodal named entity recognition (MNER) extends traditional named entity recognition (NER) by integrating visual and textual information. However, current methods still face significant challenges due to the text-image mismatch problem. Recent advancements in text-to-image synthesis provide promising solutions, as synthesized images can introduce additional visual context to enhance MNER model performance. To fully leverage the benefits of both original and synthesized images, we propose an adaptive mixup image augmentation method. This method generates augmented images by determining the mixing ratio based on the matching score between the text and image, utilizing a triplet loss-based Gaussian Mixture Model (TL-GMM). Our approach is highly adaptable and can be seamlessly integrated into existing MNER models. Extensive experiments demonstrate consistent performance improvements, and detailed ablation studies and case studies confirm the effectiveness of our method. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Gloss-driven Conditional Diffusion Models for Sign Language Production

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2025年第4期21卷 1-17页

作者： Tang, Shengeng Xue, Feng Wu, Jingjing Wang, Shuo Hong, Richang School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Software Hefei University of Technology Hefei China School of Data Science School of Information Science and Technology University of Science and Technology of China Hefei China

Sign Language Production (SLP) aims to convert text or audio sentences into sign language videos corresponding to their semantics, which is challenging due to the diversity and complexity of sign languages, and cross-modal semantic mapping issues. In this work, we propose a Gloss-driven Conditional Diffusion Model (GCDM) for SLP. The core of the GCDM is a diffusion model architecture, in which the sign gloss sequence is encoded by a Transformer-based encoder and input into the diffusion model as a semantic prior condition. In the process of sign pose generation, the textual semantic priors carried in the encoded gloss features are integrated into the embedded Gaussian noise via cross-attention. Subsequently, the model converts the fused features into sign language pose sequences through T-round denoising steps. During the training process, the model uses the ground-truth labels of sign poses as the starting point, generates Gaussian noise through T rounds of noise, and then performs T rounds of denoising to approximate the real sign language gestures. The entire process is constrained by the MAE loss function to ensure that the generated sign language gestures are as close as possible to the real labels. In the inference phase, the model directly randomly samples a set of Gaussian noise, generates multiple sign language gesture sequence hypotheses under the guidance of the gloss sequence, and outputs a high-confidence sign language gesture video by averaging multiple hypotheses. Experimental results on the Phoenix2014T dataset show that the proposed GCDM method achieves competitiveness in both quantitative performance and qualitative visualization. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Forming

来源：评论

学校读者我要写书评

暂无评论

Einocchio: Efficiently Outsourcing Polynomial Computation with Verifiable Computation and Optimized Newton Interpolation

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 1981-1992页

作者： Pei, Xintao Chen, Yuling Long, Yangyang Sang, Haiwei Luo, Yun Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China

Cloud computing, as a promising service platform, has gained significant popularity in addressing emerging data privacy issues in applications such as machine learning and data mining. Researchers have proposed the verifiable computing that allows the cloud users to delegate their computation tasks to the cloud server. Then, the cloud server computes the cryptographic proofs that verify the correctness of the results, a process that is generally faster ompared to local manual computation. However, performing computation tasks or verifying the correctness of encrypted data, such as multivariate polynomial functions, remains a significant challenge. To solve this problem, we propose Einocchio: A verifiable computation scheme that combines the efficient Pinocchio system with homomorphic encryption, which allows the public verification of the computational results on the server side while ensuring data confidentiality and the results. Compared with the existing solutions, Einocchio does not reveal the client's input. Furthermore, we extrapolate Einocchio by optimizing the Pinocchio's quadratic arithmetic program component using a differential optimization method, which reduces the computational workload owing to the conversion from quadratic to linear complexity, thereby increasing the efficiency of the quadratic arithmetic program preprocessing stage. Security analysis demonstrates that Einocchio achieves IND-CPA security. Finally, the performance evaluation confirmed its effectiveness and suitability for cloud computing environments. Compared to the corresponding scheme based on Newton interpolation, Einocchio achieves a threefold greater computational efficiency, with the generation of interpolation polynomials for 50 data inputs occurring in a mere 0.31 ms, while simultaneously reducing the number of computations. © 2005-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

PLC-MDT: A Framework for Detecting Anomalies With Digital Twins of Industrial Control Systems

引用

IEEE Sensors Journal 2025年第10期25卷 17739-17749页

作者： Xu, Zidong Zhang, Zhenyong Zheqiu, Hetu Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China

The attack events (such as the Stuxnet and BlackEnergy) that targeted the industrial control system (ICS) have validated its vulnerability to cyber intrusions. The prevention of ICS from cyberattacks is undoubtedly important and practical as it operates dangerous equipment and produces products that people need. Traditional anomaly detection methods, which rely heavily on SCADA data, are often unreliable due to the limitation of such data in accurately reflecting real-time system states under attacks. Therefore, we propose PLC-MDT, a novel anomaly detection method based on digital twins (DTs), exploiting the modern communication technology and computing resources of ICS. PLC-MDT does not depend solely on SCADA data;instead, it leverages the interaction between DT and real-world ICS, utilizing both DT and field-site data to perform anomaly detection. Specifically, for PLC-MDT, the prediction model in DT is trained based on historical data, and the predicted values are used as input to the mechanism model in DT to generate simulated data. The networked structure of ICS guarantees real-time data collected from field sites for DT. Therefore, PLC-MDT detects attacks by monitoring the difference between the predicted and real-time data, revealing control channel corruption when the difference exceeds a threshold. The effectiveness of PLC-MDT is demonstrated through experiments on real-world systems, showing its potential for real-time detection of anomalies in ICS. © 2001-2012 IEEE.

关键词： SCADA systems

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition with DToF Sensing

Facial Expression Recognition with DToF Sensing

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Chengxiao Zhang, Xie Wu, Chenshu Department of Computer Science School of Computing and Data Science The University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Facial Expression Recognition (FER) is crucial for understanding human emotions, with applications spanning from mental health assessment to marketing recommendation systems. However, existing camera-based methods raise privacy concerns, while RF-based approaches suffer from limited environmental generalizability and high cost. In this work, we propose ToFace, a FER system leveraging a low-cost (4.8$) Direct Time-of-Flight (DToF) sensor that has been available on commodity smartphones. This sensor provides an extremely low-resolution 8 × 8 depth map and a clear Field of View (FoV), significantly mitigating privacy concerns while avoiding the impact of ambient objects. Despite the benefits, the low-resolution depth map introduces significant challenges for precise expression recognition due to limited facial structure information. We first develop a physical model to extract additional spatial information from the intermediate sensor output, i.e., the transient histograms. We then propose a physics-integrated neural network to reconstruct a facial structure map comprising both depth and orientation for accurate expression recognition. We conduct real-world experiments with 12 users and compare our model with several baselines. The results demonstrate that ToFace achieves the highest recognition accuracy of 75%. © 2025 IEEE.

关键词： direct time-of-flight sensor facial expression recognition internet of things sensing AI

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning a Biased Model for Improving Fairness

引用

IEEE Transactions on Big data 2025年第3期11卷 1397-1410页

作者： Chen, Huiqiang Zhu, Tianqing Liu, Bo Zhou, Wanlei Yu, Philip S. University of Technology Sydney Center for Cyber Security and Privacy School of Computer Science SydneyNSW2007 Australia City University of Macau Faculty of Data Science 999078 China University of Illinois at Chicago Department of Computer Science ChicagoIL60607 United States

Fairness has emerged as a crucial concern in machine learning since biased models would generate dissimilar predictions for different groups, perpetuating social inequalities. Although numerous techniques have been proposed to address the fairness issue in machine learning, most rely on incorporating fairness constraints during the training phase, rendering them ineffective once the model is deployed. This paper explores the potential of fine-tuning biased models to enhance fairness, particularly suitable for scenarios where retraining the model is not feasible. Our approach is rooted in an empirical analysis of the distribution of bias within a biased model, and we fine-tune the model parameter in a limited scope so that the performance of the original model can be maintained. We first observe that fine-tuning a biased model leads to deviations from its initial state, with deep layers undergoing the most significant changes. We then design and apply a bias-discovery algorithm, revealing that bias predominantly resides in the model’s deep layers. Based on these observations, we propose a straightforward yet highly effective method for debiasing the model: fine-tuning the classification head. We conduct a thorough theoretical analysis to justify the proposed method and provide guidance for fine-tuning. Furthermore, we experimentally validate our method on tabular and image datasets using four networks (CNN, AlexNet, VGG-11, and ResNet-18). © 2015 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Dynamic Flexible Job Shop Scheduling With Biased Objectives via Multitask Genetic Programming

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 169-183页

作者： Zhang, Fangfang Shi, Gaofeng Mei, Yi Zhang, Mengjie Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Emerson New Plymouth4310 New Zealand

Dynamic flexible job shop scheduling is an important combinatorial optimization problem that has rich real-world applications such as product processing in manufacturing. Genetic programming has been successfully used to learn scheduling heuristics for dynamic flexible job shop scheduling. Intuitively, users prefer small and effective scheduling heuristics that can not only generate promising schedules but also are computationally efficient and easy to be understood. However, a scheduling heuristic with better effectiveness tends to have a larger size, and the effectiveness of rules and rule size are potentially conflicting objectives. With the traditional dominance relation-based multiobjective algorithms, there is a search bias toward rule size, since rule size is much easier to optimized than effectiveness, and larger rules are easily abandoned, resulting in the loss of effectiveness. To address this issue, this article develops a novel multiobjective genetic programming algorithm that takes size and effectiveness of scheduling heuristics for optimization via multitask learning mechanism. Specifically, we construct two tasks for the multiobjective optimization with biased objectives using different search mechanisms for each task. The focus of the proposed algorithm is to improve the effectiveness of learned small rules by knowledge sharing between constructed tasks which is implemented with the crossover operator. The results show that our proposed algorithm performs significantly better, i.e., with smaller and more effective scheduling heuristics, than the state-of-the-art algorithms in the examined scenarios. By analyzing the population diversity, we find that the proposed algorithm has a good balance between exploration and exploitation during the evolutionary process. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Clinically Robust Polyp Segmentation: Enhanced Generalization and Perturbation Resistance

Clinically Robust Polyp Segmentation: Enhanced Generalizatio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Shanchuan Yuan, Fang Su, Jian-Nan Gan, Min College of Computer Science and Technology Qingdao University Qingdao China College of Computer and Data Science Fuzhou University Fuzhou China

ISBN: (纸本)9798350368741

Colonoscopy is vital for detecting colorectal polyps, which are closely linked to colorectal cancer. Accurate segmentation of polyps in colonoscopic images is essential for diagnosis and surgical planning but is challenging due to variability in polyp size, shape, and unclear boundaries. The Segment Anything Model (SAM) has shown promise in polyp segmentation but relies heavily on user-provided prompts and involves a large number of parameters, limiting its practicality in clinical settings. To address the limitations of SAM in clinical practice, we introduced Low Rank and Perturbation Segment Anything Model (LP-SAM) to improve segmentation accuracy and generalization ability while reducing the parameter count and complexity of user input. LP-SAM showed enhanced generalization and a lightweight design, making it more suitable for clinical applications where precise user input may not always be feasible. Comparative evaluations demonstrate that LP-SAM outperforms state-of-the-art methods on datasets such as CVC-ColonDB, CVC-300, and ETIS. © 2025 IEEE.

关键词： Low-rank Adaptation Perturbation Resistance polyp segmentation Segment Anything Model

来源：评论

学校读者我要写书评

暂无评论

Immersive video interaction system: a survey

引用

Visual Intelligence 2025年第1期3卷 1-14页

作者： Fang, Xiaohan Chen, Peilin Wang, Meng Wang, Shiqi Department of Computer Science City University of Hong Kong Hong Kong School of Data Science Lingnan University Hong Kong

As communication technologies undergo rapid evolution, human interaction technologies have become increasingly efficient and accessible. Videoconferencing, for example, facilitates real-time, face-to-face communication worldwide, providing unprecedented convenience. Nevertheless, traditional two-dimensional (2D) videoconferencing systems frequently fall short of delivering a fully immersive experience, as they lack the ability to convey physical presence, depth perception, and natural interaction—key elements that are of particular significance in replicating the subtleties inherent in in-person communication. This disconnection leaves users yearning for the rich, multi-sensory experiences that real-life interactions can offer. In response, significant research efforts have been dedicated to the development of immersive video interaction systems (IVISs). This paper introduces the concept of IVISs and reviews a spectrum of systems advanced by researchers and industry innovators, each of whom contributes unique insights into the evolution of this field. A comparative analysis of the characteristics of current IVISs is provided, offering insights across multiple dimensions. This survey concludes with a discussion of potential future research directions and the challenges that remain in enhancing the IVIS technology. Through a comprehensive analysis, this work aims to foster further exploration and innovation in immersive communication technologies. © The Author(s) 2025.

关键词： 3D vision Immersive video interaction systems Survey Video communication

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：