检索结果-内蒙古大学图书馆

Consistent Learning of Sparse Background Features for Infrared Small-Target Labeling

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Xu, Hai Zhou, Hui Zhong, Sheng Yan, Luxin Zou, Xu Huazhong University of Science and Technology National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Wuhan430074 China China Aerospace Science and Technology Innovation Institute Beijing100088 China

Recent years have witnessed many remarkable achievements in infrared small-target (IST) detection based on deep learning (DL). To achieve high performance in real-world applications, DL methods require a substantial number of accurate labels. However, IST annotating is labor-intensive as they are very small. Determining and annotating edge pixels demands considerable time and effort, which slows down data expansion and further research in IST detection. To mitigate the issue, we propose a pseudo-label (PL) generation method named consistent learning of sparse background feature (CLSBF). This approach models the generation of IST PLs as a domain transformation from local target maps to background ones. It can relax the supervision requirements of DL methods, transitioning from absolute pixel-level supervision to point supervision. This method employs an unsupervised approach primarily, supplemented by semi-simulated supervision, to achieve mutual conversion of local images from different domains and obtain the final target PLs through the differences between target images and transformed background ones. Experiments show that equipped with our method, models trained with the input of a coarsely accurate center label can achieve performance up to 99.94% compared to models trained with official accurate labels. Furthermore, when the official labels are not accurate enough, models trained with PLs generated by CLSBF consistently show a performance improvement of 1.11%-4.09% when they are evaluated based on re-labeled bounding boxes. Extensive experiments demonstrate the reliability of CLSBF in generating PLs and its potential to alleviate the labor-intensive process of manual labeling significantly. We have released an IST labeling tool with CLSBF as an assistant at https://***/SeaHifly/***. © 1980-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Editing Memories Through Few Targeted Neurons 39

Editing Memories Through Few Targeted Neurons

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Wei Wei, Wei Cao, Guibang Wang, Fei Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory School of Computer Science and Technology Huazhong University of Science and Technology China Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL) China Ping An Property & Casualty Insurance Company of China Ltd China Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)157735897X

Model editing is a novel research topic in large language models (LLMs), aimed at efficiently handling various knowledge editing tasks. Since irrelevant knowledge is difficult to measure, existing editing methods often lack explicit ways to preserve it, especially for editing methods based on the fine-tuning paradigm. They generally control the locality performance of model editing by constraining the range of changes in model parameters. However, their performance improvements are not always ideal, and may even lead to a decrease in the editing reliability. In this paper, we try to explore effective editing locality control methods based on the relationship between the stored knowledge and the strongly associated model components. Based on the discovery of “knowledge neurons” and enough experimental results, we further explore the potential characteristics between knowledge and model components, confirm and point out: (1) only 1% neurons have significant contributions to specific knowledge storage, and (2) these targeted neurons often have a high overlap for knowledge with similar relational descriptions, which means that knowledge with similar relationships may be severely affected when these targeted neurons are modified. Based on these findings, we propose Targeted Neurons Fine-tuning with Data Augmentation (TNF-DA), which performs data augmentation based on the relational representation of edited knowledge to improve editing locality. By freezing most of the model parameters and only fine-tuning the highly contributing neurons corresponding to the edited knowledge, we obtain desirable results in terms of generalization and specificity compared with previous fine-tuning-based methods. Extensive experiments have demonstrated the superior editing performance achieved by our proposed method. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Circular Decomposition and Cross-Modal Recombination for Multimodal Sentiment Analysis

Circular Decomposition and Cross-Modal Recombination for Mul...

引用

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

作者： Haijian Liang Weicheng Xie Xilin He Siyang Song Linlin Shen School of Computer Science & Software Engineering Computer Vision Institue Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University School of Computing and Mathematical Sciences University of Leicester National Engineering Laboratory for Big Data System Computing Technology Shenzhen University

Multimodal Sentiment Analysis is a burgeoning research area, leveraging various modalities to predict the sentiment score. Nevertheless, previous studies have disregarded the impact of noise interference on specific modal sentiments during video recording, thereby compromising the accuracy of sentiment prediction. In this paper, we propose the Guided Circular Decomposition and Cross-Modal Recombination (GCD-CMR) model, which aims to eliminate contaminated sentiment features in a fine-grained way. To achieve this, we utilize tailored global information specific to each modality to guide the circular decomposing process in the GCD module, to produce a set of sentiment prototypes. Subsequently, in the CMR module, we align cross-modal sentiment prototypes and remove the contaminated prototypes for recombination. Experimental results on two publicly available datasets demonstrate that our model surpasses state-of-the-art models, confirming the effectiveness of our proposed method. We release the code at: https://***/nianhua20/GCD-CMR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regression-Guided Positive Sample Refocusing Paradigm for Tiny Object Detection in Aerial Images

Regression-Guided Positive Sample Refocusing Paradigm for Ti...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Lihui Ge He Chen Guanqun Wang Tong Zhang Yin Zhuang Fukun Bi Liang Chen National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China School of Computer Science Peking University Beijing China College of Information North China University of Technology Beijing China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Tiny object detection represents a pivotal challenge in remote sensing intelligent interpretation, necessitating detectors to exhibit heightened precision in object localization. However, typical model optimization strategies cannot release the detector’s potential for precisely localizing objects. And the lack of interpretability in detection box filtering based on object classification scores serves as a constraint on further performance improvement. Therefore, this paper proposed a novel model optimization strategy to thoroughly unleash the potential of the detector for precise localization. Then, the utilization of object comprehensive confidence score enhances the interpretability of the post-processing step for detection boxes. Rigorous experiments on the AI-TOD dataset have demonstrated the effectiveness of our method, achieving state-of-the-art performance.

关键词： Location awareness Filtering Detectors Object detection Optimization Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A 220-GHz Wireless Communication System Using a Quasi-Optical Cryogenic Receiver of High Sensitivity

A 220-GHz Wireless Communication System Using a Quasi-Optica...

引用

IEEE International Workshop on Radio-Frequency Integration technology (RFIT)

作者： Huanxin Li Dan Qiao Xindi Yu Liangbin Zhao Ziru Chen Heng Liu Xiang Gao School of Information and Electronics Beijing Institute of Technology Beijing China Division of Electronics and Information Metrology National Institute of Metrology Beijing China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (数字)9798331541095

ISBN: (纸本)9798331541101

This paper presents the design and implementation of a 220-GHz wireless communication system by using a quasi-optical cryogenic receiver of high sensitivity. The presented terahertz (THz) communication system utilizes a quasi-optical cryogenic receiver with a noise factor much lower than that of conventional room-temperature counterpart, thus helping to increase the transmission distance in long-range communication scenarios. In the scaled wireless link experiment, the communication data rate achieves 10 Gbit/s for a 16-quadrature amplitude modulation. According to the link budget, the communication distance can be around 5 km provided using appropriate transmitter power and antenna gains for practical scenarios. Considering the small volume, light weight and high sensitivity of the cryogenic receiver, the proposed system should be very useful for long-range THz communication applications.

关键词： Wireless communication Radio frequency Wireless sensor networks Sensitivity Transmitting antennas Radio transmitters Noise Receivers Cryogenics Terahertz communications

来源：评论

学校读者我要写书评

暂无评论

Long Video Micro-expression Spotting Based On OCC Theory

Long Video Micro-expression Spotting Based On OCC Theory

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： BingTong Liu ZheYuan Zhang Ju Zhou HanPu Wang Tong Chen Institute of Legal Psychology and Intelligent Computing Southwest University Chongqing China Chongqing Key Laboratory of Non-Linear Circuit and Intelligent Information Processing Chongqing China School of Electronic and Information Engineering Southwest University Chongqing China

The generation of micro-expression (ME) is unconscious and unaffected by human subjective consciousness. It can reveal hidden emotions in humans, which has important applications in the domains of psychological diagnosis, lie detection, and so on. ME detection, which aims to locate ME apex frames in long videos, is the foundation of ME recognition. In this paper, we propose a ME detection method based on One-Class Classification (OCC) theory for long videos. The method is the first to use neutral expression frames to detect MEs, which addresses the problem of insufficient training samples in ME detection. We design a geometric motion feature based on the prior knowledge from the FACS and utilize it in conjunction with the features extracted by CNN to train separate one-class classifiers for ME detection. Finally, we evaluate the proposed method on publicly available datasets CASME I, CASME II, SAMM, and a mixed database comprising data from the three datasets, to verify the feasibility of the proposed method in both single-database and cross-database ME detection. The experimental results show that our method outperforms three other ME detection methods, demonstrating its ability to more accurately locate ME apex frames in long videos.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Wideband Circularly Polarized Folded Transmitarray Antenna With Linearly Polarized Feed 7

A Wideband Circularly Polarized Folded Transmitarray Antenna...

引用

7th IEEE International Conference on Electronic information and Communication technology, ICEICT 2024

作者： Sun, Xiangdong Guo, Xulong Li, Yin Zhang, Yongliang Li, Yingsong Inner Mongolia University School of Electronic Information Engineering Hohhot010021 China Inner Mongolia University Inner Mongolia Branch of National Computer Network Emergency Response Technical Team Coordination Center of China Hohhot010020 China Peng Cheng Laboratory Shenzhen518000 China Inner Mongolia University School of Transportation Institute Hohhot010021 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing China

ISBN: (纸本)9798350384437

A low-profile, high-gain, wideband circularly polarized folded transmitarray antenna (CPFTA) is proposed, and a polarization-selective linear-to-circular polarization (LP-CP) conversion element is introduced. The CPFTA consists of a linearly polarized (LP) magnetoelectric dipole antenna and a circularly polarized (CP) helical patch antenna. The CPFTA demonstrates excellent performance with a 3dB gain bandwidth of 29.5% and a 3dB axial ratio (AR) bandwidth of 40.9%. © 2024 IEEE.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Joint Beamforming and Offloading Design for Integrated Sensing, Communication and Computation System

arXiv

引用

arXiv 2024年

作者： Liu, Peng Fei, Zesong Wang, Xinyi Zhou, Yiqing Zhang, Yan Liu, Fan The School of Information and Electronics Beijing Institute of Technology Beijing100081 China The State Key Laboratory of Processors The Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China

Mobile edge computing (MEC) is powerful to alleviate the heavy computing tasks in integrated sensing and communication (ISAC) systems. In this paper, we investigate joint beamforming and offloading design in a three-tier integrated sensing, communication and computation (ISCC) framework comprising one cloud server, multiple mobile edge servers, and multiple terminals. While executing sensing tasks, the user terminals can optionally offload sensing data to either MEC server or cloud servers. To minimize the execution latency, we jointly optimize the transmit beamforming matrices and offloading decision variables under the constraint of sensing performance. An alternating optimization algorithm based on multidimensional fractional programming is proposed to tackle the non-convex problem. Simulation results demonstrates the superiority of the proposed mechanism in terms of convergence and task execution latency reduction, compared with the state-of-the-art two-tier ISCC framework. Copyright © 2024, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

VAction: A Lightweight and Integrated VR Training System for Authentic Film-Shooting Experience 25

VAction: A Lightweight and Integrated VR Training System for...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI 2025

作者： Wang, Shaocong Qu, Che Yu, Minjing Zhou, Chao Wang, Yuntao Wen, Yu-Hui Shi, Yuanchun Liu, Yong-Jin Department of Computer Science and Technology Tsinghua University Beijing China Film & TV Technology Department Beijing Film Academy Beijing China College of Intelligence and Computing Tianjin University Tianjin China Human Computer Interaction Technology Intelligent Information Processing Laboratory Institute of Software Chinese Acadamy of Sciences Beijing China School of Computer Science and Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798400713941

The film industry exerts significant economic and cultural influence, and its rapid development is contingent upon the expertise of industry professionals, underscoring the critical importance of film-shooting education. However, this process typically necessitates multiple practice in complex professional venues using expensive equipment, presenting a significant obstacle for ordinary learners who struggle to access such training environments. Despite VR technology has already shown its potential in education, existing research has not addressed the crucial learning component of replicating the shooting process. Moreover, the limited functionality of traditional controllers hinder the fulfillment of the educational requirements. Therefore, we developed VAction VR system, combining high-fidelity virtual environments with a custom-designed controller to simulate the real-world camera operation experience. The system's lightweight design ensures cost-effective and efficient deployment. Experiment results demonstrated that VAction significantly outperforms traditional methods in both practice effectiveness and user experience, indicating its potential and usefulness in film-shooting education. © 2025 Copyright held by the owner/author(s).

关键词： Film Production Education Interaction Design Training System Virtual Reality

来源：评论

学校读者我要写书评

暂无评论

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

引用

Frontiers of information technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

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：