检索结果-内蒙古大学图书馆

Bi-Directional and Triangular Circulation Fusion Neural Networks for Small Object Detection

IEEE Transactions on Circuits and systems for Video Technology 2024年第6期35卷 5140-5152页

作者： Li, Fangyu Duan, Junzhu Zhang, Qiyu Shan, Caifeng Han, Honggui the School of Information Science and Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education Beijing Artificial Intelligence Institute Beijing University of Technology Beijing100124 China the State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China the School of Intelligence Science and Technology Nanjing University Suzhou215163 China

Deep learning-driven object detection models are capable of accurately identifying and localizing objects. However, small objects contain limited information relative to global features, resulting in the fact that detection models often do not learn small object features adequately. To enhance the precision in detecting small objects, we propose a bi-directional and triangular circulation fusion neural network (BTFN). First, to selectively strengthen the position features of small objects, we propose a feature circulation extraction module composed of a bi-directional triangular densely nested convolutional network (BTF), thus achieving repetitive multi-layer feature fusion. Second, to fill up the semantic gaps between different scales of features, we design a mixed dual attention module (MDA) in the bi-directional triangular densely nested network. Third, to mitigate the lost information in the neural networks with deep layers as well as improve the inference time, we design a re-parameterization bi-directional composite feature fusion module (Rep-BFM) that fuses the features of multiple scales. The proposed model is evaluated extensively on the MS COCO, Tsinghua-Tencent 100k, and Haier dismantled parts of used home appliances datasets. The experiment results show that the proposed model improves the AP on MS COCO by 4%, especially the APS of small objects is improved by 7.7% compared with SOTA models. © 2024 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Domestic appliances

来源：评论

学校读者我要写书评

暂无评论

Highly sensitive flexible heat flux sensor based on a microhole array for ultralow to high temperatures

引用

Microsystems & Nanoengineering 2023年第5期9卷 345-356页

作者： Le Li Bian Tian Zhongkai Zhang Meng Shi Jiangjiang Liu Zhaojun Liu Jiaming Lei Shuimin Li Qijing Lin Libo Zhao Zhuangde Jiang School of Mechanical Engineering Xi’an Jiaotong University710049 Xi’anChina State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement TechnologiesXi’an Jiaotong University(Yantai)Research Institute for Intelligent Sensing Technology and SystemXi’an Jiaotong UniversityXi’an 710049China Shandong Laboratory of Yantai Advanced Materials and Green Manufacturing Yantai 265503China

With the growing demand for thermal management of electronic devices,cooling of high-precision instruments,and biological cryopreservation,heat flux measurement of complex surfaces and at ultralow temperatures has become highly ***,current heat flux sensors(HFSs)are commonly used in high-temperature scenarios and have problems when applied in low-temperature conditions,such as low sensitivity and *** this study,we developed a flexible and highly sensitive HFS that can operate at ultralow to high temperatures,ranging from−196°C to 273°*** sensitivities of HFSs with thicknesses of 0.2 mm and 0.3 mm,which are efficiently manufactured by the screen-printing method,reach 11.21μV/(W/m2)and 13.43μV/(W/m2),*** experimental results show that there is a less than 3%resistance change from bending to ***,the HFS can measure heat flux in both exothermic and absorptive cases and can measure heat flux up to 25 kW/***,we demonstrate the application of the HFS to the measurement of minuscule heat flux,such as heat dissipation of human skin and cold *** technology is expected to be used in heat flux measurements at ultralow temperatures or on complex surfaces,which has great importance in the superconductor and cryobiology field.

关键词： high stretching superconductor

来源：评论

学校读者我要写书评

暂无评论

BAYESPROMPT: PROMPTING LARGE-SCALE PRETRAINED LANGUAGE MODELS ON FEW-SHOT INFERENCE VIA DEBIASED DOMAIN ABSTRACTION 12

BAYESPROMPT: PROMPTING LARGE-SCALE PRETRAINED LANGUAGE MODEL...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Li, Jiangmeng Song, Fei Jin, Yifan Qiang, Wenwen Zheng, Changwen Sun, Fuchun Xiong, Hui National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China State Key Laboratory of Intelligent Game Beijing China University of Chinese Academy of Sciences Beijing China Tsinghua University Beijing China Guangzhou China

As a novel and effective fine-tuning paradigm based on large-scale pre-trained language models (PLMs), prompt-tuning aims to reduce the gap between downstream tasks and pre-training objectives. While prompt-tuning has yielded continuous advancements in various tasks, such an approach still remains a persistent defect: prompt-tuning methods fail to generalize to specific few-shot patterns. From the perspective of distribution analyses, we disclose that the intrinsic issues behind the phenomenon are the over-multitudinous conceptual knowledge contained in PLMs and the incomplete knowledge for target downstream domains, which jointly result in that PLMs mis-locate the knowledge distributions corresponding to the target domains in the universal knowledge embedding space. To this end, we intuitively explore to approximate the complete target domains of downstream tasks in a debiased manner, and then abstract such domains to generate discriminative prompts, thereby providing the de-ambiguous guidance for PLMs. Guided by such an intuition, we propose a simple yet effective approach, namely BayesPrompt, to learn prompts that contain the domain discriminative information against the interference from domain-irrelevant knowledge. BayesPrompt primitively leverages known distributions to approximate the debiased factual distributions of target domains and further uniformly samples certain representative features from the approximated distributions to generate the ultimate prompts for PLMs. We provide theoretical insights with the connection to domain adaptation. Empirically, our method achieves state-of-the-art performance on benchmarks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Missing Data Imputation Method for Electricity Consumption Data Based on TCN-Attention with Mask Tokens 4

A Missing Data Imputation Method for Electricity Consumption...

引用

4th International Conference on Consumer Electronics and Computer Engineering, ICCECE 2024

作者： Mao, Yifeng Yang, Ming Li, Peng Ou, Zhujian Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Jinan China State Grid Nantong Power Supply Company State Grid Jiangsu Electric Power CO. LTD. Nantong China

ISBN: (纸本)9798350384062

With the popularization of smart meters, power companies can collect massive amounts of data from users for non-invasive load detection, electricity theft detection, etc. However, due to faults in smart meters and abnormal communication, the dataset often has missing values, making it difficult for data-driven methods to be widely applied. In this paper, we propose an unsupervised learning method based on TCN-Attention to fill in customers' electricity consumption data. Firstly, we extract electricity consumption features through TCN. In order to improve the feature extraction capability, we introduce a channel attention mechanism to TCN. The attention mechanism makes TCN focus on the effective features in the data by assigning weights. Meanwhile, we use mask tokens to cover a certain proportion of data, forcing the proposed model to learn potential feature representations of the data during the training process. Finally, the features are restored to data through feedforward neural networks. An example is given to verify the effectiveness of the proposed method. © 2024 IEEE.

关键词： Smart meters

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Method for Ship Collision Risk Detection in Heavy Traffic Waters 14

A Data-Driven Method for Ship Collision Risk Detection in He...

引用

14th International Conference on Information Science and Technology, ICIST 2024

作者： Lv, Haoran Mou, Junmin Zhang, Liang Li, Mengxia Chen, Pengfei School of Navigation Wuhan University of Technology Wuhan China State Key Laboratory of Maritime Technology and Safety Wuhan China Intelligent Transportation System Research Center Wuhan University of Technology Wuhan China

ISBN: (纸本)9798350353334

Intended to solve the problem of poor generalization of complex collision risk model, this paper proposes a novel collision risk model based on data-driven. Firstly, the main traffic pattern is clustered by Ordering Points to Identify the Clustering Structure algorithm. Afterwards, using probability statistics and mining the altering behaviors identify the abnormal behavior. And then, encounter situation and avoidance behaviors are identified by analyzing the relative motion characteristics of the two ships. Finally, by Kullback-Leibler dispersion and kernel density estimation methods, the key parameters are extracted from encounter data with avoidance behaviors. The collision risk model based on data-driven is constructed. To verify the effectiveness of the proposed method, the method is used in a heavy traffic area, the mouth of Yangtze River, China. The results show that the collision risk model based on data-driven can be more accurate. © 2024 IEEE.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Fast Transient Voltage Stability Assessment for Complex Receiving-End Power Grid 7

Fast Transient Voltage Stability Assessment for Complex Rece...

引用

7th International Conference on Power and Energy Applications, ICPEA 2024

作者： Liu, Xiyang Liu, Tianhao Liu, Yutian Li, Zhendong Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Jinan China Laiwu Power Supply Company State Grid Shandong Electric Power Company Laiwu China

ISBN: (纸本)9798350356113

The continuous increase of new energy generation and AC-DC interconnection make the transient voltage stability of the receiving-end power grid more and more complicated. In order to realize the rapid assessment of transient voltage stability, a one-dimensional Convolutional Neutral Network (CNN) for transient voltage stability assessment (TVSA) is constructed by selecting the features reasonably on the basis of using the Agglomerative Hierarchical Clustering (AHC) algorithm to partition the receiving-end grid. In order to enhance the assessment work, the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm is utilized to find out the concerns of the model to features, and the model knowledge of the neural network is analyzed on the basis of surveying on a large number of samples. Based on the transient voltage stability mechanism and the concerns of deep learning model, the factors that cause transient voltage instability are analyzed. The effectiveness of the proposed method is demonstrated by the case study of a provincial grid in eastern China. © 2024 IEEE.

关键词： Transient stability

来源：评论

学校读者我要写书评

暂无评论

Color liquid crystal grating based color holographic 3D display system with large viewing angle

引用

Light(Science & Applications) 2024年第1期13卷 103-112页

作者： Di Wang Yi-Long Li Fan Chu Nan-Nan Li Zhao-Song Li Sin-Doo Lee Zhong-Quan Nie Chao Liu Qiong-Hua Wang School of Instrumentation and Optoelectronic Engineering Beihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China Display Technology Research Center Seoul National UniversityGwanak-ro 1Gwanak-guSeoul 08826Republic of Korea Key Lab of Advanced Transducers and Intelligent Control System Ministry of EducationTaiyuan University of TechnologyTaiyuan 030024China

Holographic 3D display is highly desirable for numerous applications ranging from medical treatments to military ***,it is challenging to simultaneously achieve large viewing angle and high-fidelity color reconstruction due to the intractable constraints of existing ***,we conceptually propose and experimentally demonstrate a simple and feasible pathway of using a well-designed color liquid crystal grating to overcome the inevitable chromatic aberration and enlarge the holographic viewing angle,thus enabling large-viewing-angle and color holographic 3D *** use of color liquid crystal grating allows performing secondary diffraction modulation on red,green and blue reproduced images simultaneously and extending the viewing angle in the holographic 3D display *** principle,a chromatic aberration-free hologram generation mechanism in combination with the color liquid crystal grating is proposed to pave the way for on such a superior holographic 3D *** proposed system shows a color viewing angle of~50.12°,which is about 7 times that of the traditional system with a single spatial light *** work presents a paradigm for achieving desirable holographic 3D display,and is expected to provide a new way for the wide application of holographic display.

关键词： holographic angle crystal

来源：评论

学校读者我要写书评

暂无评论

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Mo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Chang, Zhiyuan Li, Mingyang Wang, Junjie Liu, Yi Wang, Qing Liu, Yang State Key Laboratory of Intelligent Game Beijing China Science and Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences China Nanyang Technological University Singapore

ISBN: (纸本)9798891761681

Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies. The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt. We first conduct an empirical study on this issue, exploring the prevalence of catastrophic-neglect, potential mitigation strategies with feature enhancement, and the insights gained. Guided by the empirical findings, we propose an automated repair approach named Patcher to address catastrophic-neglect in T2I DMs. Specifically, Patcher first determines whether there are any neglected objects in the prompt, and then applies attention-guided feature enhancement to these neglected objects, resulting in a repaired prompt. Experimental results on three versions of Stable Diffusion demonstrate that Patcher effectively repairs the issue of catastrophic-neglect, achieving 10.1%-16.3% higher Correct Rate in image generation compared to baselines. © 2024 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

Machine Learning for Signal Demodulation in Underwater Wireless Optical Communications

引用

China Communications 2024年第5期21卷 297-313页

作者： Ma Shuai Yang Lei Ding Wanying Li Hang Zhang Zhongdan Xu Jing Li Zongyan Xu Gang Li Shiyin Department of Strategic and Advanced Interdisciplinary Research Peng Cheng LaboratoryShenzhen 518055China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China Data-driven Intelligent Information System Laboratory Shenzhen Research Institute of Big DataShenzhen 518172China Ocean College Zhejiang UniversityZhoushan 316021China State Key Laboratory of Millimeter Waves Southeast UniversityNanjing 210096China

The underwater wireless optical communication(UWOC)system has gradually become essential to underwater wireless communication *** other existing works on UWOC systems,this paper evaluates the proposed machine learningbased signal demodulation methods through the selfbuilt experimental *** on such a platform,we first construct a real signal dataset with ten modulation ***,we propose a deep belief network(DBN)-based demodulator for feature extraction and multi-class feature *** also design an adaptive boosting(Ada Boost)demodulator as an alternative scheme without feature filtering for multiple modulated ***,it is demonstrated by extensive experimental results that the Ada Boost demodulator significantly outperforms the other *** also reveals that the demodulator accuracy decreases as the modulation order increases for a fixed received optical power.A higher-order modulation may achieve a higher effective transmission rate when the signal-to-noise ratio(SNR)is higher.

关键词： AdaBoost DBN machine learning signal demodulation

来源：评论

学校读者我要写书评

暂无评论

Construction of the rat brain spatial cell firing model on a quadruped robot

引用

CAAI Transactions on Intelligence Technology 2022年第4期7卷 732-743页

作者： Naigong Yu Yishen Liao Hejie Yu Ouattara Sie Faculty of Information Technology Beijing University of TechnologyBeijingChina Beijing Key Laboratory of Computational Intelligence and Intelligent System BeijingChina Engineering Research Center of Digital Community Ministry of EducationBeijingChina College of Robotic UniversitéFélix Houphouet-BoignyAbidjanCote d'Ivoire

Physiological studies have shown that rats in a dark environment rely on the limbs and vestibule for their self-motion information,which can maintain the specific firing patterns of grid cells and hippocampal CA3 place *** the development stage of rats,grid cells are considered to come from place cells,and place cells can be encoded by hippocampal theta *** on these,the quadruped robot is used as a platform in this ***,the sensing information of the robot's limbs and inertial measurement unit is obtained to solve its position in the *** the position information is encoded by theta cells and mapped to place cells through a neural *** obtaining the place cells with singlepeak firing fields,Hebb learning is used to adjust the connection weight of the neural network between place cells and grid *** order to verify the model,3-D simulation experiments are designed in this *** experiment results show that with the robot exploring in space,the spatial cells firing effects obtained by the model are consistent with the physiological research facts,which lay the foundation for the bionic environmental cognition model.

关键词： robot neural firing

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：