检索结果-内蒙古大学图书馆

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

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Deployment and Trajectory in UAV and IRS-Assisted IoT Data Collection System

arXiv

引用

arXiv 2022年

作者： Dong, Li Liu, Zhibin Jiang, Feibo Wang, Kezhi Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China The Department of Computer and Information Sciences Northumbria University United Kingdom

Unmanned aerial vehicles (UAV) can be applied in many Internet of Things (IoT) systems, e.g., smart farms, as a data collection platform. However, the UAV-IoT wireless channels may be occasionally blocked by trees or high-rise buildings. Intelligent reflecting surface (IRS) can be applied to improve the wireless channel quality by smartly reflecting the signal via a large number of low-cost passive reflective elements. This paper aims to minimize the energy consumption of the system by jointly optimizing the deployment and trajectory of the UAV. The problem can be formulated as a mixed-integer- and-nonlinear-programming (MINLP), which is difficult to be addressed by the traditional solution, which may be easily fall into the local optimal. To address this issue, we propose a Joint Optimization framework of depLoyment and Trajectory (JOLT), where an adaptive whale optimization algorithm (AWOA) is applied to optimize the deployment of the UAV, and an elastic ring self-organizing map (ERSOM) is introduced to optimize the trajectory of the UAV. Specifically, in AWOA, a variable-length population strategy is applied to find the optimal number of stop points, and a nonlinear parameter a and a partial mutation rule are introduced to balance the exploration and exploitation. In ERSOM, a competitive neural network is also introduced to learn the trajectory of the UAV by competitive learning, and a ring structure is presented to avoid the trajectory intersection. Extensive experiments are carried out to show the effectiveness of the proposed JOLT framework. Copyright © 2022, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

FULL-LENGTH-BODY CBCT IMAGING IN UPRIGHT POSITION WITH ROBOTIC-ARM SYSTEM: A SIMULATION STUDY

arXiv

引用

arXiv 2023年

作者： Lin, Tong Lyu, Tianling Wu, Zhan Xi, Yan Zhu, Wentao Chen, Yang Laboratory of Image Science and Technology Southeast University Nanjing China Research Center of Augmented Intelligence Zhejiang Lab Hangzhou China Shanghai First-Imaging Tech Shanghai China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University Nanjing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

Upright position CT scans make it possible for full-length-body imaging at conditions more relevant to daily situations, but the substantial weight of the upright CT scanners increases the risks to floor’s stability and patients’ safety. Robotic-arm CBCT systems are supposed to be a better solution for this task, but such systems still face challenges including long scanning time and low reconstruction quality. To address the above challenges, this paper proposes a novel method to calculate optimal scanning pitch based on data completeness analysis, which can complete the whole-body scan in the shortest time without a significant decline in image quality. Besides, an FDK-style reconstruction method based on normalized projections is proposed to obtain fast image reconstruction. Extensive experiments prove the effectiveness of the proposed optimal scanning trajectory. Qualitative and quantitative comparisons with FDK and iterative algorithms show that the proposed reconstruction method can obtain high imaging quality with reasonable computation costs. The method proposed in this paper is expected to promote the application of robotic-arm CBCT systems in orthopedic functional analysis. © 2023, CC BY-NC-SA.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection 39

Provable Discriminative Hyperspherical Embedding for Out-of-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zou, Zhipeng Wan, Sheng Li, Guangyu Han, Bo Liu, Tongliang Zhao, Lin Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Hong Kong Baptist University China Sydney AI Centre The University of Sydney Sydney Australia Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Out-of-distribution (OOD) detection aims to identify the test examples that do not belong to the distribution of training data. The distance-based methods, which identify OOD examples based on their distances from the centroids of in-distribution (ID) examples, have demonstrated promising OOD detection performance. However, the objectives utilized in prior approaches are typically designed for classification and thus might not yield sufficient discriminative power to distinguish between ID and OOD examples. Therefore, this paper proposes a prototype-based contrastive learning framework for OOD detection, which is termed provable Discriminative Hyperspherical Embedding (DHE). The proposed framework provides a theoretical analysis of inter-class dispersion, which is proved to be fundamental in reducing the false positive rate (FPR) on OOD examples. Based on this, we devise an angular spread loss to achieve the maximal dispersion of the prototypes of different classes prior to training. Subsequently, a prototype-enhanced contrastive loss is introduced to align embeddings of ID examples closely with their corresponding prototypes. In our proposed DHE, the maximal prototype dispersion is theoretically proved, thereby avoiding the pitfalls of local optima commonly encountered by most existing methods. Experimental results demonstrate the effectiveness of our proposed DHE, which showcases a remarkable reduction in FPR95 (i.e., 5.37% on CIFAR-100) and more than doubling the computational efficiency when compared with the state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition

arXiv

引用

arXiv 2023年

作者： Wang, Xiao Rong, Yao Wang, Shiao Chen, Yuan Wu, Zhe Jiang, Bo Tian, Yonghong Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China School of Computer Science and Technology Anhui University Hefei230601 China The School of Internet Anhui University Hefei230601 China The Peng Cheng Laboratory Shenzhen China The Peng Cheng Laboratory China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China

Pattern recognition based on RGB-Event data is a newly arising research topic and previous works usually learn their features using CNN or Transformer. As we know, CNN captures the local features well and the cascaded self-attention mechanisms are good at extracting the long-range global relations. It is intuitive to combine them for high-performance RGB-Event based video recognition, however, existing works fail to achieve a good balance between the accuracy and model parameters, as shown in Fig. 1. In this work, we propose a novel RGB-Event based recognition framework termed TSCFormer, which is a relatively lightweight CNN-Transformer model. Specifically, we mainly adopt the CNN as the backbone network to first encode both RGB and Event data. Meanwhile, we initialize global tokens as the input and fuse them with RGB and Event features using the BridgeFormer module. It captures the global long-range relations well between both modalities and maintains the simplicity of the whole model architecture at the same time. The enhanced features will be projected and fused into the RGB and Event CNN blocks, respectively, in an interactive manner using F2E and F2V modules. Similar operations are conducted for other CNN blocks to achieve adaptive fusion and local-global feature enhancement under different resolutions. Finally, we concatenate these three features and feed them into the classification head for pattern recognition. Extensive experiments on two large-scale RGB-Event benchmark datasets (PokerEvent and HARDVS) fully validated the effectiveness of our proposed TSCFormer. The source code and pre-trained models will be released at https://***/Event-AHU/TSCFormer Copyright © 2023, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

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

作者： Xin Li Feng Xu Feifei Tao Yao Tong Xin Lyu Jianyi Zhong André Kaup College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Chair of Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study.

关键词： Semantic segmentation Frequency-domain analysis Urban planning Semantics Speech enhancement Signal processing Transformers Sensors Remote sensing Standards

来源：评论

学校读者我要写书评

暂无评论

The Effect of Mn Doping on the Electrical and Magnetic Properties of Cr2te3 Thin Films

SSRN

引用

SSRN 2024年

作者： Luo, Fu-Sheng Zhang, Jie-Rui Wang, Zhao-Cai Tang, Fang Fang, Yong Zhou, Wei-Ping School of Physics and Electronic Information Gannan Normal University Ganzhou341000 China School of Materials and Mechanic & Electrical Engineering Jiangxi Science and Technology Normal University Nanchang330038 China Jiangsu Laboratory of Advanced Functional Materials Department of Physics Changshu Institute of Technology Changshu215500 China School of Physics and Materials Science Nanchang University Nanchang330031 China Fujian Provincial Key Laboratory of Advanced Materials Processing and Application China

Mn doped Cr2-xMnxTe3 thin films were prepared by molecular beam epitaxy technology. The effect of Mn doping concentration on the structural, morphological, electrical and magnetic performance of Cr2Te3 thin films were detailed analyzed. By varying the beam current of the Mn source, it is found that Mn can be doped into the Cr2Te3 thin film when the Mn source temperature is lower than 700 ℃, while the Mn tends to bind with Te as MnTe crystals for Mn source temperature higher than 700 ℃. Cr2-xMnxTe3 films all exhibt strong ferromagnetism with a Curie temperature of around 175 K. The magnetization of the films decreases with increasing Mn doping concentration. A notable negative magnetoresistance effect is observed with the highest MR ratio about -60% in the vicinity of the Curie temperature. A clear topological Hall signal was observed in the sample with a Mn source temperature of 700 ℃ at low temperature (2 K). These results imply that the electrical and magnetic properties of Cr2Te3 materials can be effectively controlled by doping to meet the practical needs of different fields. © 2024, The Authors. All rights reserved.

关键词： Thin films

来源：评论

学校读者我要写书评

暂无评论

Fast Algorithm for Parallel Solving Inversion of Large Scale Small Matrices Based on Gpu

SSRN

引用

SSRN 2022年

作者： Jin, Xuebin Chen, Yewang Fan, Wentao Zhang, Yong Du, Jixiang The College of Computer Science and Technology Huaqiao University Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China College of Mechanical Engineering and Automation Huaqiao University Xiamen China

Inverting a matrix is time-consuming, and many works focus on accelerating inverting a single large matrix by GPU. However, the problem of inverting large-scale small matrices has little attention. In this paper, we propose a Revised In-Place Inversion algorithm for inverting large-scale small matrices, which runs on the CUDA platform and utilizes multicore GPUs. The proposed algorithm is well-suited for large-scale-small matrices (dimension $n \leq 32$), which can invert millions of small matrices within tens of milliseconds. In addition, we find there is an upper bound of input data size for each GPU device, the performance will degrade if the input data size is too large. Hence, we improve the proposed method by dividing matrices into batches according to this finding. Experimental results show that this strategy can effectively alleviate the performance degradation for inverting large scale small matrices, and maintain the high-performance execution of the algorithm. © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs

arXiv

引用

arXiv 2025年

作者： Wang, Xiaoqin Ma, Xusen Hou, Xianxu Ding, Meidan Li, Yudong Chen, Junliang Chen, Wenting Peng, Xiaoyang Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China AIAC Xi’an Jiaotong-Liverpool University China Tsinghua University China The Hong Kong Polytechnic University Hong Kong City University of Hong Kong Hong Kong Sun Yat-sen University China

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the structure, the proposed FaceBench consists of 49,919 visual question-answering (VQA) pairs for evaluation and 23,841 pairs for fine-tuning. Moreover, we further develop a robust face perception MLLM baseline, Face-LLaVA, by training with our proposed face VQA data. Extensive experiments on various mainstream MLLMs and Face-LLaVA are conducted to test their face perception ability, with results also compared against human performance. The results reveal that, the existing MLLMs are far from satisfactory in understanding the fine-grained facial attributes, while our Face-LLaVA significantly outperforms existing open-source models with a small amount of training data and is comparable to commercial ones like GPT-4o and Gemini. The dataset will be released at https://***/CVI-SZU/FaceBench. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AdvFAS: a robust face anti-spoofing framework against adversarial examples

arXiv

引用

arXiv 2023年

作者： Chen, Jiawei Yang, Xiao Yin, Heng Ma, Mingzhi Chen, Bihui Peng, Jianteng Guo, Yandong Yin, Zhaoxia Su, Hang Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China Department of Computer Science and Technology Institute for AI THBI Lab Tsinghua University Beijing100084 China Zhongguancun Laboratory Beijing100080 China OPPO Research Institute Beijing China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai200241 China

Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the most state-of-the-art methods to defend against adversarial examples remains elusive. While several adversarial defense strategies have been proposed, they typically suffer from constrained practicability due to inevitable trade-offs between universality, effectiveness, and efficiency. To overcome these challenges, we thoroughly delve into the coupled relationship between adversarial detection and face anti-spoofing. Based on this, we propose a robust face anti-spoofing framework, namely AdvFAS, that leverages two coupled scores to accurately distinguish between correctly detected and wrongly detected face images. Extensive experiments demonstrate the effectiveness of our framework in a variety of settings, including different attacks, datasets, and backbones, meanwhile enjoying high accuracy on clean examples. Moreover, we successfully apply the proposed method to detect real-world adversarial examples. © 2023, CC BY.

关键词： Face recognition

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：