检索结果-内蒙古大学图书馆

A Dynamic Transformer Network for Vehicle Detection

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2025年

作者： Tian, Chunwei Liu, Kai Zhang, Bob Huang, Zhixiang Lin, Chia-Wen Zhang, David Harbin Institute of Technology School of Computer Science and Technology Harbin15001 China Macao Special Administrative Region of China PAMI Research Group University of Macau 999078 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Key Laboratory of Electromagnetic Environmental Sensing Hefei230601 China National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu Taiwan School of Data Science Shenzhen518172 China

Stable consumer electronic systems can assist traffic better. Good traffic consumer electronic systems require collaborative work between traffic algorithms and hardware. However, performance of popular traffic algorithms containing vehicle detection methods based on deep networks via learning data relation rather than learning differences in different lighting and occlusions is limited. In this paper, we present a dynamic Transformer network for vehicle detection (DTNet). DTNet utilizes a dynamic convolution to guide a deep network to dynamically generate weights to enhance adaptability of an obtained detector. Taking into relations of different information account, a mixed attention mechanism based channel attention and Transformer is exploited to strengthen relations of channels and pixels to extract more salient information for vehicle detection. To overcome the drawback of difference in an image account, a translation-variant convolution relies on spatial location information to refine obtained structural information for vehicle detection. Experimental results illustrate that our DTNet is competitive for vehicle detection. Code of the proposed DTNet can be obtained at https://***/hellloxiaotian/DTNet. © 2025 IEEE.

关键词： Dynamic convolution Hybrid Attention Mechanism Transformer Vehicle Detection

Cross-Modality Person Re-Identification Based on Shared Feature Attention Aggregation Algorithm

学校读者我要写书评

暂无评论

Cross-Modality Person Re-Identification Based on Shared Feat...

International Conference on Information Science and Technology (ICIST)

作者： Jiong Wang Linjuan Xie Nian Zhang Jiang Xiong XiaoLing Song Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University Chongqing China Department of Electrical and Computer Engineering University of the District of Columbia Washington D.C. USA College of Mathematics and Statistics Chongqing Three Gorges University Chongqing China College of Computer Science and Engineerings Chongqing Three Gorges University Chongqing China

Person re-identification in the visible-infrared spectrum (VI-ReID) is a challenging task due to significant difference of modalities, making it difficult to extract salient features across modalities. To solve this problem, in this paper, we propose a novel Cross-Modality Shared Feature Attention Aggregation algorithm (cm-SFAA) for VI-ReID. In the cm-SFAA approach, we first design a Random Channel Alternation Erasure Network to better learn robust features against occlusions and noise, as well as diverse feature representations under different channel combinations. This enhances the generalization ability of the model. Furthermore, a Local Feature Aggregation module is introduced in cm-SFAA, which utilizes an adaptive weighting mechanism to aggregate features from different levels and domains, thereby improving the performance of the model. Extensive experiments on two mainstream datasets SYSU-MMOI and RegDB show that cm-SFAA outperforms several baseline methods and acquires state-of-the-art performance. The source code of our proposed cm-SFAA is available at https://***/wdqlndVcm-SFAA.

关键词：

Fundamental Limits of Multiple-Access Integrated Sensing and Communication Systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Yao Li, Min Liu, An Ong, Lawrence Yener, Aylin The College of Information Science and Electronic Engineering The Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Zhejiang University Hangzhou310027 China The School of Engineering University of Newcastle CallaghanNSW2308 Australia The Department of Electrical and Computer Engineering The Ohio State University ColumbusOH43210 United States

A memoryless state-dependent multiple access channel is considered to model an integrated sensing and communication system, where two transmitters wish to convey messages to a receiver while simultaneously estimating the sensing state sequences through echo signals. In particular, the sensing states are assumed to be correlated with the channel state, and the receiver has imperfect channel state information. In this setup, improved inner and outer bounds for capacity-distortion region are derived. The inner bound is based on an achievable scheme that combines message cooperation and joint compression via distributed Wyner-Ziv coding at each transmitter, resulting in unified cooperative communication and sensing. The outer bound is based on the ideas of dependence balance for communication rate and rate-limited constraints on sensing distortion. The proposed inner and outer bounds are proved to improve the state-of-the-art bounds. Finally, numerical examples are provided to demonstrate that our new inner and outer bounds strictly improve the existing results. © 2022, CC BY.

关键词： Transmitters

Boosting Scalability for Large-Scale Multiobjective Optimization Via Transfer Weights

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Hong, Haokai Jiang, Min Yen, Gary G. Department of Artificial Intelligence Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism School of Informatics Xiamen University 422 South Siming Road Siming District Fujian Xiamen361005 China The School of Electrical and Computer Engineering Oklahoma State University StillwaterOK74074 United States

Large-scale multiobjective optimization problems (LSMOPs), which optimize multiple conflicting objectives with hundreds or even thousands of decision variables, demand increasing computational resources to assure satisfactory performance as the decision variables increase. Multiobjective evolutionary algorithms are naturally scalable, but as the dimension increases, the conflict between analyzing enough solutions and the limited number of function evaluations has hindered further improvements in scalability. In this paper, we first define the scalability of multiobjective evolutionary algorithms and design an indicator to quantitatively measure the scalability. Second, to boost scalability when solving LSMOPs, we propose a scalable multiobjective optimization algorithm by transferring weights between solutions to reduce dependency on ever-increasing computational resources as the problem dimension increases. The proposed framework constructs a latent decision space to calculate evolutionary weights for a small subset of representative solutions, and then transfers the calculated weights to the remaining solutions for evolutionary optimization without additional evaluation. By transferring knowledge learned from source solutions in the latent decision space, each solution is provided with an evolutionary weight scheme that saves computational resources and improves optimization performance. We have conducted experiments on LSMOPs to verify the effectiveness and scalability of the proposed algorithm. © 2023, The Authors. All rights reserved.

关键词： Scalability

Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qiu, Yangyang Xu, Guoan Gao, Guangwei Guo, Zhenhua Yu, Yi Lin, Chia-Wen The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia The Tianyijiaotong Technology Ltd. Suzhou215100 China The Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima739-8511 Japan The Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, the integration of the local modeling capabilities of Convolutional Neural Networks (CNNs) with the global dependency strengths of Transformers has created a sensation in the semantic segmentation community. However, substantial computational workloads and high hardware memory demands remain major obstacles to their further application in real-time scenarios. In this work, we propose a lightweight multiple-information interaction network for real-time semantic segmentation, called LMIINet, which effectively combines CNNs and Transformers while reducing redundant computations and memory footprint. It features Lightweight Feature Interaction Bottleneck (LFIB) modules comprising efficient convolutions that enhance context integration. Additionally, improvements are made to the Flatten Transformer by enhancing local and global feature interaction to capture detailed semantic information. The incorporation of a combination coefficient learning scheme in both LFIB and Transformer blocks facilitates improved feature interaction. Extensive experiments demonstrate that LMIINet excels in balancing accuracy and efficiency. With only 0.72M parameters and 11.74G FLOPs, LMIINet achieves 72.0% mIoU at 100 FPS on the Cityscapes test set and 69.94% mIoU at 160 FPS on the CamVid test dataset using a single RTX2080Ti GPU. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Data Fusion for Multipath-Based SLAM: Combining Information from Multiple Propagation Paths

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Leitinger, Erik Venus, Alexander Teague, Bryan Meyer, Florian The Signal Processing and Speech Communication Laboratory Graz University of Technology Graz Austria The Christian Doppler Laboratory for Location-aware Electronic Systems Austria The MIT Lincoln Laboratory LexingtonMA United States The Department of Electrical and Computer Engineering and Scripps Institution of Oceanography University of California San Diego San DiegoCA United States

Multipath-based simultaneous localization and mapping (SLAM) is an emerging paradigm for accurate indoor localization constrained by limited navigation resources. The goal of multipath-based SLAM is to support the estimation of time-varying positions of mobile agents by detecting and localizing radio-reflective surfaces in the environment. In existing Bayesian methods, a propagation surface is represented by the mirror image of each physical anchor (PA) across that surface – known as the corresponding "virtual anchor" (VA). Due to this VAs representation, each propagation path is mapped individually. Existing methods thus neglect inherent geometrical constraints across different paths that interact with the same surface, which limits accuracy and speed. In this paper, we introduce an improved statistical model and estimation method that enables data fusion in multipath-based SLAM. By directly representing each surface with a master virtual anchor (MVA), geometrical constraints across propagation paths are also modeled statistically. A key aspect of the proposed method based on MVAs is to check the availability of single-bounce and double-bounce propagation paths at potential agent positions by means of ray-tracing (RT). This availability check is directly integrated into the statistical model as detection probabilities for propagation paths. Estimation is performed by a sum-product algorithm (SPA) derived based on the factor graph that represents the new statistical model. Numerical results based on simulated and real data demonstrate significant improvements in estimation accuracy compared to state-of-the-art multipath-based SLAM methods. © 2022, CC BY.

关键词： Mobile agents

Attention-Guided Multi-scale Interaction Network for Face Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wan, Xujie Li, Wenjie Gao, Guangwei Lu, Huimin Yang, Jian Lin, Chia-Wen The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100080 China The School of Automation Southeast University Nanjing210096 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, CNN and Transformer hybrid networks demonstrated excellent performance in face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid networks, how to fuse these multi-scale features and promote their complementarity is crucial for enhancing FSR. However, existing hybrid network-based FSR methods ignore this, only simply combining the Transformer and CNN. To address this issue, we propose an attention-guided Multi-scale interaction network (AMINet), which contains local and global feature interactions as well as encoder-decoder phases feature interactions. Specifically, we propose a Local and Global Feature Interaction Module (LGFI) to promote fusions of global features and different receptive fields' local features extracted by our Residual Depth Feature Extraction Module (RDFE). Additionally, we propose a Selective Kernel Attention Fusion Module (SKAF) to adaptively select fusions of different features within LGFI and encoder-decoder phases. Our above design allows the free flow of multi-scale features from within modules and between encoder and decoder, which can promote the complementarity of different scale features to enhance FSR. Comprehensive experiments confirm that our method consistently performs well with less computational consumption and faster inference. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

Pre-Chirp-Domain Index Modulation for Full-Diversity Affine Frequency Division Multiplexing towards 6G

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Guangyao Mao, Tianqi Xiao, Zhenyu Wen, Miaowen Liu, Ruiqi Zhao, Jingjing Basar, Ertugrul Wang, Zhaocheng Chen, Sheng The School of Electronic and Information Engineering The State Key Laboratory of CNS/ATM Beihang University Beijing100191 China State Key Laboratory of CNS/ATM Beijing Institute of Technology Beijing100081 China Zhuhai519088 China The Wireless and Computing Research Institute ZTE Corporation Beijing100029 China The State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen518055 China The School of Electronic and Information Engineering South China University of Technology Guangzhou510640 China Department of Electrical and Electronics Engineering Koç University Sariyer Istanbul34450 Turkey The Department of Electronic Engineering Tsinghua University Beijing100084 China The School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

As a superior multicarrier technique utilizing chirp signals for high-mobility communications, affine frequency division multiplexing (AFDM) is envisioned to be a promising candidate for sixth-generation (6G) wireless networks. AFDM is based on the discrete affine Fourier transform (DAFT) with two adjustable parameters of the chirp signals, termed the pre-chirp and post-chirp parameters, respectively. Whilst the post-chirp parameter complies with stringent constraints to combat the time-frequency doubly selective channel fading, we show that the pre-chirp counterpart can be flexibly manipulated for an additional degree of freedom. Therefore, this paper proposes a novel AFDM scheme with the pre-chirp index modulation (PIM) philosophy (AFDM-PIM), which can implicitly convey extra information bits through dynamic pre-chirp parameter assignment, thus enhancing both spectral and energy efficiency. Specifically, we first demonstrate that the subcarrier orthogonality is still maintained by applying distinct pre-chirp parameters to various subcarriers in the AFDM modulation process. Inspired by this property, we allow each AFDM subcarrier to carry a unique pre-chirp signal according to the incoming bits. By such an arrangement, extra bits can be embedded into the index patterns of pre-chirp parameter assignment without additional energy consumption. We derive asymptotically tight upper bounds on the average bit error probability (BEP) of the proposed schemes with the maximum-likelihood detection, and validate that the proposed AFDM-PIM can achieve full diversity under doubly dispersive channels. Based on the derived result, we further propose an optimal pre-chirp alphabet design to enhance the bit error rate (BER) performance via intelligent optimization algorithms. Simulation results demonstrate that the proposed AFDM-PIM outperforms the classical benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Chirp modulation

Graph Convolutional Networks Based Muti-Label Deep Cross-Modal Hashing

学校读者我要写书评

暂无评论

Graph Convolutional Networks Based Muti-Label Deep Cross-Mod...

International Conference on Information Science and Technology (ICIST)

作者： Yi Peng Xin Jiang Nian Zhang Jiang Xiong School of Electronic and Information Engineering Chongqing Three Gorges University Chongqing China Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University Chongqing China Department of Electrical and Computer Engineering University of the District of Columbia Washington D.C. USA College of Mathematics and Statistics Chongqing Three Gorges University Chongqing China

Recently, multi-label deep cross-modal hashing (MDCH), which incorporates deep neural networks, hashing and multi-label learning for cross-modal retrieval tasks, has achieved excellent cross-modal retrieval results and thus became a highly popular area of research. Nevertheless, many existing MDCH methods concentrate on extracting information from multi-modal data, while neglecting the abundant semantic information in multiple labels. Few MDCH methods incorporate multi-label information, but they often treat labels as independent entities, ignoring the relationships between categories, which hinders the establishment of semantic connections among multi-modal data. In order to tackle the aforementioned challenges, we propose a graph convolutional networks based multi-label deep cross-modal hashing method (GMCH) in this paper. GMCH leverages two deep neural networks to generate hash representations from the original image-text pairs, during this process, a graph convolutional network is introduced to capture the category correlations of multi-labels and supervise the training of hash mapping. Experimental results on two commonly employed datasets validate the efficacy of the proposed GMCH method. You can find the code for our proposed GCMH at https://***/licher12/***.

关键词：