检索结果-内蒙古大学图书馆

CPAL: Cross-prompting Adapter with LoRAs for RGB+X Semantic Segmentation

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Liu, Ye Wu, Pengfei Wang, Miaohui Liu, Jun Nanjing University of Posts and Telecommunications School of Automation and Artificial Intelligence Nanjing China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Lancaster University School of Computing and Communications Lancaster United Kingdom

As sensor technology evolves, RGB+X systems combine traditional RGB cameras with another type of auxiliary sensor, which enhances perception capabilities and provides richer information for important tasks such as semantic segmentation. However, acquiring massive RGB+X data is difficult due to the need for specific acquisition equipment. Therefore, traditional RGB+X segmentation methods often perform pretraining on relatively abundant RGB data. However, these methods lack corresponding mechanisms to fully exploit the pretrained model, and the scope of the pretraining RGB dataset remains limited. Recent works have employed prompt learning to tap into the potential of pretrained foundation models, but these methods adopt a unidirectional prompting approach i.e., using X or RGB+X modality to prompt pretrained foundation models in RGB modality, neglecting the potential in non-RGB modalities. In this paper, we are dedicated to developing the potential of pretrained foundation models in both RGB and non-RGB modalities simultaneously, which is non-trivial due to the semantic gap between modalities. Specifically, we present the CPAL (Cross-prompting Adapter with LoRAs), a framework that features a novel bi-directional adapter to simultaneously fully exploit the complementarity and bridging the semantic gap between modalities. Additionally, CPAL introduces low-rank adaption (LoRA) to fine-tune the foundation model of each modal. With the support of these elements, we have successfully unleashed the potential of RGB foundation models in both RGB and non-RGB modalities simultaneously. Our method achieves state-of-the-art (SOTA) performance on five multi-modal benchmarks, including RGB+Depth, RGB+Thermal, RGB+Event, and a multi-modal video object segmentation benchmark, as well as four multi-modal salient object detection benchmarks. The code and results are available at: https://***/abelny56/CPAL. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Human-like conceptual representations emerge from language prediction

arXiv

引用

arXiv 2025年

作者： Xu, Ningyu Zhang, Qi Du, Chao Luo, Qiang Qiu, Xipeng Huang, Xuanjing Zhang, Menghan School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China Ministry of Education Key Laboratory of Contemporary Anthropology Fudan University Shanghai China

People acquire concepts through rich physical and social experiences and use them to understand the world. In contrast, large language models (LLMs), trained exclusively through next-token prediction over language data, exhibit remarkably human-like behaviors. Are these models developing concepts akin to humans, and if so, how are such concepts represented and organized? To address these questions, we reframed the classic reverse dictionary task to simulate human concept inference in context and investigated the emergence of human-like conceptual representations within LLMs. Our results demonstrate that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts. The derived representations converged towards a shared, context-independent structure that effectively predicted human behavior across key psychological phenomena, including computation of similarities, categories and semantic scales. Moreover, these representations aligned well with neural activity patterns in the human brain, even in response to visual rather than linguistic stimuli, providing evidence for biological plausibility. These findings establish that structured, human-like conceptual representations can naturally emerge from language prediction without real-world grounding. More broadly, our work positions LLMs as promising computational tools for understanding complex human cognition and paves the way for better alignment between artificial and human intelligence. 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

A Miniaturized Bandwidth Reconfigurable Bandpass Chip Filter with Semi-lumped Topology and GaAs pHEMT Technology

引用

Chinese Journal of Electronics 2021年第1期30卷 192-198页

作者： LI Linqing ZHU Haoran NING Xingyu LI Zunwen WU Xianliang Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui University

A miniaturized reconfigurable bandpass chip filter with semi-lumped topology and Gallium Arsenide pseudomorphic High electron mobility transistor（GaAs pHEMT） technology is proposed. Semi-lumped topology is employed to instead the traditional lumped inductor with microstrip transmission line, which can reduced the size of the tunable filter significantly. Three-order series and shunt resonated bandpass filter is implemented with shorted stubs and metal-insulator-metal capacitors. Two transmission zeros are introduced with the series resonator and the shunted GaAs FET. By tuning the gate bias circuit of the FET, the capacitance of the series resonator is changed and the bandwidth of the filter is adjusted correspondingly. An equivalent circuit model is developed to interpret the mechanism of the proposed filter circuit. A reconfigurable on chip filter sample operated at 10 GHz is fabricated to validate the design. Two fractional bandwidth of 14.3% and 23.5% are tuned with bias voltage of the FET, while insertion loss of 2.4 d B and 2.2 d B are observed with the filter, respectively. The area of the chip filter is 0.86 × 0.96 mm2and is equivalent to an electrical length of 0.08 × 0.09λg2at center frequency. Measurement results agree well with the simulation ones.

关键词： gallium arsenide tunable filter transmission zeros equivalent circuit model resonator filters shunted FET III-V semiconductors miniaturized bandwidth reconfigurable bandpass chip filter MIM devices microstrip transmission line chip filter sample shunt resonated bandpass filter metal-insulator-metal capacitors semilumped topology loss 2.4 dB Gallium Arsenide pseudomorphic High electron mobility transistor technology insertion loss filter circuit integrated circuit design GaAs integrated circuit manufacture frequency 10.0 GHz pHEMT technology microwave filters loss 2.2 dB HEMT integrated circuits series resonator miniaturized reconfigurable bandpass chip filter band-pass filters

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Malicious Web Request Detection based on Transformer and Contrastive Learning

引用

IEEE Transactions on Network and Service Management 2025年

作者： He, Shiming Zhang, Ying Liang, Diqing Sharma, Pradip Kumar Changsha University of Science and Technology School of Computer Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha410114 China University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom

The World Wide Web (Web) is a crucial part of the Internet. Web attacks are becoming more and more serious and complex. Malicious Web request detection aims to rapidly and accurately identify abnormal attacks on the network. Deep learning is being applied to malicious Web request detection, resulting in high detection performance. However, most deep learning-based methods are supervised and ignore special characters, which are hard to detect unknown malicious Web requests. The labels of Web request are fewer and Web request data is insufficient. Therefore, we propose an unsupervised malicious Web request detection based on transformer and contrastive learning (UTCDetector). UTCDetector exploits preprocessing and 2-gram word segmentationto preserve special characters, extracts semantic feature by Transformer, and leverages hypersphere loss function and contrastive learning to handle insufficient Web data without abnormal label. Since the public Web request datasets (CSIC 2010, CSIC TORPEDA 2012, and ECML/PKDD 2007) were created before 2012, we collected Web requests from a university Web application server in 2023 to build a private dataset named School 2023. This dataset contains more modern and complex attacks. The experimental results on the four datasets demonstrate that our method achieves a higher F1-score than other existing methods and ablation variants. © 2004-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multivariate Time Series Anomaly Detection by Feature Decoupling in Federated Learning Scenarios

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： He, Yifan Ding, Xi Tang, Yateng Guan, Jihong Zhou, Shuigeng Fudan University School of Computer Science Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Tencent Weixin Group Guangzhou510308 China Tongji University Department of Computer Science and Technology Shanghai201804 China Ministry of Education Key Laboratory of Embedded System and Service Computing Tongji University Shanghai200092 China

Anomalies are usually regarded as data errors or novel patterns previously unseen, which are quite different from most observed data. Accurate detection of anomalies is crucial in various application scenarios. This paper focuses on unsupervised anomaly detection from Multivariate Time Series (MTS), as real-world data collected from sources such as wearable devices, medical equipment and industrial machines typically manifest as MTS and are often unlabeled. Anomaly detection in MTS represents a data-driven challenge that traditionally requires substantial centralized data for training models. However, in practice, data are frequently distributed among multiple institutions, with privacy concerns restricting unrestricted access. To address these issues, we introduce Feature Decoupling Federated Learning (FDFL), an approach designed to collaboratively train a representation learning network over multiple clients for unsupervised anomaly detection in MTS. Unlike previous methods that simply integrate MTS anomaly detection algorithms with federated learning strategies, FDFL specifically addresses heterogeneity among clients by decoupling the representation network into shared and private branches through a contrastive learning mechanism. This method aggregates shared parameters during each federated round while maintaining client-specific private parameters locally. Additionally, we develop a self-attention block that integrates the representations derived from both shared and private parameters to reconstruct MTS and identify anomalies based on reconstruction errors. Extensive experiments conducted on three publicly available datasets demonstrate that FDFL outperforms existing algorithms in most cases, highlighting the effectiveness and superiority of our proposed method in MTS anomaly detection. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

The structural analysis of protein sequences based on the quasi-amino acids code

引用

Chinese Physics B 2009年第1期18卷 363-369页

作者：朱平唐旭清徐振源 School of Science Jiangnan University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University

Proteomics is the study of proteins and their interactions in a cell. With the successful completion of the Human Cenome Project, it comes the postgenome era when the proteomics technology is emerging. This paper studies protein molecule from the algebraic point of view. The algebraic system （∑, ＋, ＊） is introduced, where ∑ is the set of 64 codons. According to the characteristics of （∑, ＋, ＊）, a novel quasi-amino acids code classification method is introduced and the corresponding algebraic operation table over the set ZU of the 16 kinds of quasi-amino acids is established. The internal relation is revealed about quasi-amino acids. The results show that there exist some very close correlations between the properties of the quasi-amino acids and the codon. All these correlation relationships may play an important part in establishing the logic relationship between codons and the quasi-amino acids during the course of life origination. According to Ma F et al （2003 J. Anhui Agricultural University 30 439）, the corresponding relation and the excellent properties about amino acids code are very difficult to observe. The present paper shows that （ZU, ＋,×） is a field. Furthermore, the operational results display that the eodon tga has different property from other stop codons. In fact, in the mitochondrion from human and ox genomic codon, tga is just tryptophane, is not the stop codon like in other genetic code, it is the case of the Chen W C et al （2002 Acta Biophysiea Siniea 18（1） 87）. The present theory avoids some inexplicable events of the 20 kinds of amino acids code, in other words it solves the problem of ＇the 64 codon assignments of mRNA to amino acids is probably completely wrong＇ proposed by Yang （2006 Progress in Modern Biomedicine 6 3）.

关键词： algebraic operation quasi-amino acids code protein sequences structural analysis

来源：评论

学校读者我要写书评

暂无评论

An Optimization Algorithm for Service Composition Based on an Improved FOA

引用

Tsinghua Science and Technology 2015年第1期20卷 90-99页

作者： Yiwen Zhang Guangming Cui Yan Wang Xing Guo Shu Zhao the School of Computer Science and Technology Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University

Large-scale service composition has become an important research topic in Service-Oriented computing（SOC）. Quality of Service（Qo S） has been mostly applied to represent nonfunctional properties of web services and to differentiate those with the same functionality. Many studies for measuring service composition in terms of Qo S have been completed. Among current popular optimization methods for service composition, the exhaustion method has some disadvantages such as requiring a large number of calculations and poor scalability. Similarly,the traditional evolutionary computation method has defects such as exhibiting slow convergence speed and falling easily into the local optimum. In order to solve these problems, an improved optimization algorithm, WS FOA（Web Service composition based on Fruit Fly Optimization Algorithm） for service composition, was proposed, on the basis of the modeling of service composition and the FOA. Simulated experiments demonstrated that the algorithm is effective, feasible, stable, and possesses good global searching ability.

关键词： service composition Fruit Fly Optimization Algorithm（FOA） Quality of Service（QoS） index

来源：评论

学校读者我要写书评

暂无评论

MR-IDPSO: A Novel Algorithm for Large-Scale Dynamic Service Composition

引用

Tsinghua Science and Technology 2015年第6期20卷 602-612页

作者： Yanping Zhang Zihui Jing Yiwen Zhang School of Computer Science and Technology Key Laboratory of Intelligent Computing and Signal ProcessingMinistry of EducationAnhui University

In the era of big data, data intensive applications have posed new challenges to the field of service composition. How to select the optimal composited service from thousands of functionally equivalent services but different Quality of Service(Qo S) attributes has become a hot research in service computing. As a consequence,in this paper, we propose a novel algorithm MR-IDPSO(Map Reduce based on Improved Discrete Particle Swarm Optimization), which makes use of the improved discrete Particle Swarm Optimization(PSO) with the Map Reduce to solve large-scale dynamic service composition. Experiments show that our algorithm outperforms the parallel genetic algorithm in terms of solution quality and is efficient for large-scale dynamic service composition. In addition,the experimental results also demonstrate that the performance of MR-IDPSO becomes more better with increasing number of candidate services.

关键词： Map Reduce service composition Quality of Service(

来源：评论

学校读者我要写书评

暂无评论

Vector Field-Guided Circumnavigation for an Unmanned Surface Vehicle With Boundary and Obstacle Constraints

引用

IEEE Transactions on Emerging Topics in computing 2025年

作者： Wu, Nailong Wang, Jigang Wang, Yueying He, Shuping Donghua University College of Information Science and Technology Shanghai201620 China Donghua University Engineering Research Center of Digitized Textile & Apparel Technology Ministry of Education Shanghai201620 China Shanghai University School of Mechatronic Engineering and Automation Shanghai200444 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electrical Engineering and Automation Hefei230601 China

This article aims to tackle the challenge of rapid target circumnavigation by unmanned surface vehicles (USVs) under boundary and obstacle constraints through leveraging an emerging computing architecture specifically tailored for unmanned systems. Owing to the underactuation of USV dynamic systems and the presence of various time-varying surface disturbances, attaining rapid and accurate position control along with maneuverability poses a significant challenge to USVs. Therefore, when an USV maneuvers around a target in a confined search area with obstacles, it is essential for the guidance law to consider collision risks and environmental disturbances. This paper proposes a modified Lyapunov vector field with heading deviation compensation to circle the target in complex search regions. The vector field is designed to increase the radial velocity of the USV and accelerate convergence towards the target circle during the pursuit phase. By combining the proposed Lyapunov vector field with a boundary vector field, the USV can swiftly avoid boundaries and dynamic obstacles and then continue circling the target. The proposed computing architecture extends the application scope of the target circumnavigation to practical water surface environments, which is validated by extensive simulations and rigorous experiments. © 2025 IEEE.

关键词： Unmanned surface vehicles

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

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

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：