检索结果-内蒙古大学图书馆

Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Adaptation Learning

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wu, Ruiqi Jiao, Bingliang Liu, Meng Wang, Shining Wang, Wenxuan Wang, Peng Northwestern Polytechnical University School of Computer Science Xi'an710072 China Ningbo Institute Northwestern Polytechnical University Ningbo315000 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China Northwestern Polytechnical University School of Electronics and Information Xi'an710072 China Shenzhen Research Institute of Northwestern Polytechnical University Shenzhen518057 China

The Visible-Infrared Person Re-identification (VI ReID) aims to achieve cross-modality re-identification by matching pedestrian images from visible and infrared illumination. A crucial challenge in this task is mitigating the impact of modality divergence to enable the VI ReID model to learn cross-modality correspondence. Regarding this challenge, existing methods primarily focus on eliminating the information gap between different modalities by extracting modality-invariant information or supplementing inputs with specific information from another modality. However, these methods may overly focus on bridging the information gap, a challenging issue that could potentially overshadow the inherent complexities of cross-modality ReID itself. Based on this insight, we propose a straightforward yet effective strategy to empower the VI ReID model with sufficient flexibility to adapt diverse modality inputs to achieve cross-modality ReID effectively. Specifically, we introduce a Modality-aware and Instance-aware Visual Prompts (MIP) network, leveraging transformer architecture with customized visual prompts. In our MIP, a set of modality-aware prompts is designed to enable our model to dynamically adapt diverse modality inputs and effectively extract information for identification, thereby alleviating the interference of modality divergence. Besides, we also propose the instance-aware prompts, which are responsible for guiding the model to adapt individual pedestrians and capture discriminative clues for accurate identification. Through extensive experiments on four mainstream VI ReID datasets, the effectiveness of our designed modules is evaluated. Furthermore, our proposed MIP network outperforms most current state-of-the-art methods. © 1991-2012 IEEE.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Dynamic Origin-Destination Demand Prediction with Improved LSTM Model

Dynamic Origin-Destination Demand Prediction with Improved L...

引用

IEEE International Conference on Intelligent Transportation engineering (ICITE)

作者： Wei Tan Yang Yang Pengfa Song Yanning Huang Jing Liu Fangfang Zheng Southwest municipal engineering design & research institute of China Chengdu China School of Transportation and Logistics Southwest Jiaotong University Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China

As the basis of dynamic traffic distribution, traffic demand prediction needs to address the complicated coupling correlations within the road network structure and the spatial and seasonal variation of traffic demand. Dynamic origin-destination (OD) demand prediction can present the correlation between nodes in the road network pattern and the time-varying and periodicity of traffic data. In this paper, we propose a dynamic OD prediction model considering the spatial-temporal and environmental aspects (STE) of the network (STE-CNN-LSTM) based on the Long-Short-Term-Memory (LSTM) algorithm. The proposed model consists of three modules including the spatial, temporal and external environment modules. The spatial module extracts the spatial correlation information of OD data. The temporal module extracts the time correlation information of OD data, and the external environment module deals with the impact of the external factors (e.g., weather, accidents) on OD demand. To verify the effectiveness of the proposed model, we conducted experiments using the OD dataset collected by the Caltrans Performance Measurement System (PeMS) of California in the United States, and the results show that the proposed STE-CNN-LSTM model performs better than the ARIMA, general LSTM and CNN-LSTM models in most respect in most respects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Versatile hydrogel based on polyvinyl alcohol/chitosan/regenerated silk fibroin 5

Versatile hydrogel based on polyvinyl alcohol/chitosan/regen...

引用

2021 5th International Conference on Green Composite Materials and Nanotechnology, GCMN 2021

作者： Sun, Qinyue Fu, Jizhu Zhang, Heng Yang, Huihui Wang, Yumin Xiong, Yi Zeng, Wei Wang, Faniu Xu, Chao National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Electronics and Information Engineering Anhui University Anhui Hefei230601 China Science and Technology Institute Key Laboratory of Textile Fiber and Products Ministry of Education Laboratory for Electron Microscopy Wuhan Textile University Hubei Wuhan430073 China School of Physics and Technology Moe Key Laboratory of Artificial Micro- and Nano-Structures and Center for Electron Microscopy Wuhan University Hubei Wuhan430072 China

Versatile sensors have broad application prospects in human motion detection, health monitoring, wearable electronic devices and flexible electronic skin and other emerging fields. In this work, the enhanced hydrogel was prepared by freezing and thawing process with calcium ion crosslinking. This composite material shows excellent flexibility and elasticity, and after being cut in half, it can automatically heal well in a short time without external force. It shows great potential in flexible and wearable devices. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Hydrogels

来源：评论

学校读者我要写书评

暂无评论

An aggregate flow based scheduler in multi-task cooperated UAVs network

引用

Chinese Journal of Aeronautics 2020年第11期33卷 2989-2998页

作者： Xiaohuan LI Ziqi XIE Jin YE Xin TANG Chunhai LI Fengzhu TANG Rong YU School of Information and Communication Guilin University of Electronic TechnologyGuilin 541004China Guangxi Key Laboratory of Multimedia Communications and Network Technology School of ComputerElectronics and InformationGuangxi UniversityNanning 530004China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology(Guangxi) Nanning 530001China School of Automation Guangdong University of TechnologyGuangzhou 510006China

Unmanned Aerial Vehicles(UAVs)cooperative multi-task system has become the research focus in recent ***,the existing network frameworks of UAVs are not flexible and efficient enough to deal with the complex multi-task scheduling,because they are not able to perceive the different *** this paper,a novel cooperated UAVs network framework for multi-task scheduling is *** is a three-layer network including a core layer,an aggregation layer and an execution layer,which enhances the efficiency of multi-task distribution,aggregation and ***,an Aggre Gate Flow(AGFlow)based scheduler is dedicatedly designed to maximize the task completion rate,whose key point is to aggregate flows belonging to one task during the multi-task transmission of UAVs network and to allocate priority by calculating the urgency-level of each *** results demonstrate that,compared with that of state-of-the-art scheduler,the average task completion rate of AGFlow based scheduler is raised by 0.278.

关键词： Mixed-flow scheduling Multi-task Task completion rate Unmanned Aerial Vehicles(UAVs) Urgency-level

来源：评论

学校读者我要写书评

暂无评论

PseudoSC: A Binary Approximation to Stochastic Computing within Latent Operation-Space for Ultra-Lightweight on-Edge DNNs

PseudoSC: A Binary Approximation to Stochastic Computing wit...

引用

Design Automation Conference

作者： Jihe Wang Zhaoqing Wang Danghui Wang School of Computer Science Northwestern Polytechnical University Xi’an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi’an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi’an China

Recently, stochastic computing (SC) is increasingly popular in constructing MAC for on-edge DNNs benefiting from its outstanding energy-efficiency, including its adequate precision and gate-level operation. However, current SC-DNN systems always include a lot of costly SNGs/APCs for inevitably switches between binary and stochastic domains, which mortgages incongruous resources to pay the "bill" of the domain-switches and impedes highly-concurrent deployments. In this work, PseudoSC, a binary approximation to low-discrepancy SC, is proposed to totally remove the domain-switch for SNG/APC-free SC-DNNs. Its basic idea is to virtually re-arrange a couple of stochastic operands into a 2-D latent op-space, in which, original Monte Carlo sampling can be partitioned into three sub-ops, i.e., two fixed binary-ops and a fractal recursion. In theory, the recursion forms an isomorphic partition of the sampling repeated in smaller scales until the binary base-case achieved, as a result, a SC-op is well approximated only with binary-ops. Based on above theory, a multi-lane micro-architecture is designed to unroll the recursion within a few cycles and its advantages on hardware saving is verified under popular DNNs. The evaluation shows that the DNN-models with our schemes achieve 98.7% accuracy of the fixed-point implementations, which significantly outperform other SOTA methods. In addition, its reduced structure improves the power efficiency by 3.67 times on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation on Pedestrian-Bicycle Mixed Merging Flow in T-Junction

SSRN

引用

SSRN 2022年

作者： Luo, Lin Luo, Yangqi Feng, Yujing Li, Tao Fu, Zhijian School of Transportation and Logistics Southwest Jiaotong University Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu China

We experimentally investigated the pedestrian-bicycle mixed merging flow in a T-junction in both symmetric and asymmetric merging situations. Based on trajectories, we analyzed the spatial and temporal features of the flow in front of and behind the merging area. The flow priority was also discussed. The main findings include: 1) Congestions are concentrated nearly right in front of the merging area, where the interference between individuals is the most severe. There is little congestion after two flows join;2) The time finishing merging increases almost linearly with the cyclist ratio, and the merging efficiency under the asymmetric merging condition is higher than under the symmetric merging condition. The left-turning cyclists have an advantage in competing conflicts over the right-turning cyclists. Even though the number of participants behind merging might be higher, the speed is remarkably higher than in front of merging. It is even more noticeable as the ratio of cyclists increases;3) In the symmetric merging situation, the pedestrian flow in one branch is notably higher than in another branch. Under the asymmetric merging condition, the bicycle flow in the straight branch is significantly higher than in the bent branch, indicating the priority of flow in the straight branch. The study supports the design of mixed-traffic facilities and the management of the pedestrian-bicycle flow. It also gives insights for the modeling of pedestrian-bicycle flow. © 2022, The Authors. All rights reserved.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Training of Spiking Neural Network joint Curriculum Learning Strategy

arXiv

引用

arXiv 2023年

作者： Tang, Lingling Chu, Jielei Gong, Zhiguo Li, Tianrui The School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China

Starting with small and simple concepts, and gradually introducing complex and difficult concepts is the natural process of human learning. Spiking Neural Networks (SNNs) aim to mimic the way humans process information, but current SNNs models treat all samples equally, which does not align with the principles of human learning and overlooks the biological plausibility of SNNs. To address this, we propose a CL-SNN model that introduces Curriculum Learning(CL) into SNNs, making SNNs learn more like humans and providing higher biological interpretability. CL is a training strategy that advocates presenting easier data to models before gradually introducing more challenging data, mimicking the human learning process. We use a confidence-aware loss to measure and process the samples with different difficulty levels. By learning the confidence of different samples, the model reduces the contribution of difficult samples to parameter optimization automatically. We conducted experiments on static image datasets MNIST, Fashion-MNIST, CIFAR10, and neuromorphic datasets N-MNIST, CIFAR10-DVS, DVS-Gesture. The results are promising. To our best knowledge, this is the first proposal to enhance the biologically plausibility of SNNs by introducing CL. Copyright © 2023, The Authors. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Relationship between Logistics Firm Size and Business Diversification: An Empirical Study of Chongqing, Area in China

引用

Open Journal of Statistics 2021年第1期11卷 1-18页

作者： Nannan He Wanshan Wu Sijing Liu School of Transportation and Logistics Southwest Jiaotong University Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China National United Engineering Laboratory of Integrated and Intelligent Transportation Chengdu China

This paper aims to explore the relationship between logistics firm size and business diversification, especially in micro- and small-sized enterprises, and assess the diversification process of Chongqing logistics enterprises using new data source. It is intended to contribute to theoretical research on diversification in the emerging logistics industry based on resource-based view (RBV) and factor production theory. We innovatively establish the logistics business classification system, then measure the degree and direction of diversification of logistics enterprises based on mean narrow-spectrum diversification-based product count methods. The empirically shows that there are a growing number of highly-diversified logistics enterprises in general, with an average annual increase of 14.23%. Especially after 2008, small and medium-sized enterprises developed towards related diversification while micro-sized enterprises came to the opposite conclusion. For them, creating unrelated diversified business is a crucial way to generate a competitive advantage. Unlike the conclusions derived from other industries, small-sized logistics enterprises are prone to try a new business, both related and unrelated, for better survival and performance. And changes in the firm size of medium and large-sized enterprises have little impact on the development of the business diversification.

关键词： Business Diversification Logistics Firm Size RBV Logistics Business Classification System

来源：评论

学校读者我要写书评

暂无评论

Encoding Global Semantic and Localized Geographic Spatial-Temporal Relations for Traffic Accident Risk Prediction

SSRN

引用

SSRN 2024年

作者： Alhaek, Fares Li, Tianrui Rajeh, Taha M. Javed, Muhammad Hafeez Liang, Weichao School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China

The proliferation of vehicles and the intricate layout of road systems have contributed to a significant rise in traffic accidents, posing a pressing concern globally. Despite the advancements facilitated by deep learning, several challenges persist in the domain of traffic accident prediction. Firstly, the sparsity of accident data in certain city regions presents a significant obstacle, particularly when attempting fine-grained predictions at a local level. Secondly, the intricate spatial-temporal relations inherent in traffic accident data pose a challenge for existing prediction models. In response to these formidable challenges, this paper presents GLST-TARP, a novel model for predicting traffic accident risk in urban environments by leveraging both global semantic and localized geographic spatial-temporal relations. Specifically, we construct multi-graphs to encode global static and dynamic spatial relations, incorporating attention mechanisms to adaptively focus on relevant information and temporal relations. Additionally, we employ channel-wise convolutional neural network blocks to extract localized geographic features and enhance predictive accuracy. The proposed model is trained using a Huber loss function tailored for regression tasks, relieving the impact of zero values during optimization. Experimental results demonstrate that GLST-TARP outperforms state-of-the-art methods in predicting traffic accident risks, showcasing its potential for enhancing urban safety and transportation management. © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models

HSR-Diff: Hyperspectral Image Super-Resolution via Condition...

引用

International Conference on Computer Vision (ICCV)

作者： Chanyue Wu Dong Wang Yunpeng Bai Hanyu Mao Ying Li Qiang Shen National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing School of Computer Science Northwestern Polytechnical University China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University U.K.

Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors. Inspired by recent advancements in deep generative models, we propose an HSI Super-resolution (SR) approach with Conditional Diffusion Models (HSR-Diff) that merges a high-resolution (HR) multispectral image (MSI) with the corresponding LR-HSI. HSR-Diff generates an HR-HSI via repeated refinement, in which the HR-HSI is initialized with pure Gaussian noise and iteratively refined. At each iteration, the noise is removed with a Conditional Denoising Transformer (CDFormer) that is trained on denoising at different noise levels, conditioned on the hierarchical feature maps of HR-MSI and LR-HSI. In addition, a progressive learning strategy is employed to exploit the global information of full-resolution images. Systematic experiments have been conducted on four public datasets, demonstrating that HSR-Diff outperforms state-of-the-art methods.

关键词：

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：