检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Zhonglin Chen Cuili Yang Junfei Qiao Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China

ISBN: (纸本)9781665426480

As an improved recurrent neural network, Long short-term memory (LSTM) neural network have been widely applied in many areas. However, redundant resources of calculation and memory are often required in the dense LSTM neural network and the over-fitting problem can even be caused. It hinders the practical application of network. To enhance the sparsity and generalization ability, the sparse LSTM neural network with hybrid particle swarm optimization algorithm (SLSTM-HPSO) is proposed. Firstly, based on LSTM, the hybrid coding method is established to directly denote the state and value of network weights. Secondly, the fitness function which is composed of the network training error and ℓ 1 norm term is introduced to control the accuracy and sparsity of network, simultaneously. Thirdly, the update strategy is designed according to the coding method and fitness function to search for optimal solution. Finally, the proposed method is respectively 47.72% and 47.02% better than traditional LSTM neural network in terms of prediction accuracy and sparsity.

关键词： Training Recurrent neural networks Neural networks Memory management Prediction algorithms Numerical simulation Encoding

来源：评论

学校读者我要写书评

暂无评论

An Efficient Lightweight Spatio-temporal Attention Module for Action Recognition 22

An Efficient Lightweight Spatio-temporal Attention Module fo...

引用

Proceedings of the 2022 11th International Conference on computing and Pattern Recognition

作者： Zhonghua Sun Meng Dai Ziwen Yi Tianyi Wang Jinchao Feng Kebin Jia Faculty of Information Technology Beijing University of Technology China and Beijing Laboratory of Advanced Information Networks Beijing University of Technology China Faculty of Information Technology Beijing University of Technology China Faculty of Information Technology Beijing University of Technology China and Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information Technology China

ISBN: (纸本)9781450397056

Effective feature learning is one of the prime components for human action recognition algorithm. Three-dimensional convolutional neural network (3D CNN) can directly extract spatio-temporal features, however it is insufficient to capture the most discriminative part of the action video. The redundant spatial regions within and between temporal frames would weak the descriptive ability of the 3D CNN model. To address this problem, we propose a lightweight spatio-temporal attention module (ST-AM), composed of spatial attention module (SAM) and temporal attention module (TAM). SAM and TAM can effectively encode the semantic spatial areas and suppress the redundant temporal frames to reduce misclassification. The proposed SAM and TAM have complementary effects and can be easily embedded into the existing 3D CNN action recognition model. Experiment on UCF-101 and HMDB-51 datasets shows that the ST-AM embedded model achieves impressive performance on action recognition task.

关键词： 3D CNN Attention module Action recognition Spatio-temporal features

来源：评论

学校读者我要写书评

暂无评论

Base Station Network Traffic Prediction Approach Based on LMA -DeepAR 6

Base Station Network Traffic Prediction Approach Based on LM...

引用

6th IEEE International Conference on Computer and Communication systems, ICCCS 2021

作者： Zhang, Jiachen Zuo, Xingquan Xu, Mingying Han, Jing Zhang, Baisheng Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing Uinversity of Posts and Telecommunications Beijing China Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing Uinversity of Posts and Telecommunications Beijing China Network Interface Virtualization Shanghai System Design Deptment Zhongxing Telecommunication Equipment Corporation Shanghai China

ISBN: (纸本)9780738126043

Accurate network traffic prediction of base station cell is very vital for the expansion and reduction of wireless devices in base station cell. The burst and uncertainty of base station cell network traffic makes the network traffic nonlinear and nonstationary, which brings challenges to the long-term prediction of network traffic. In this paper, the traffic model LMA-DeepAR for base station network is established based on DeepAR. Acordding to the distribution characteristics of network traffic, this paper proposes an artificial feature sequence calculation method based on local moving average (LMA). The feature sequence is input into DeepAR as covariant, which makes the statistical characteristics of network traffic near a period of time in the past be considered when updating parameters, and the interference of non-stationary network traffic on model training will be reduced. Experimental results show that the proposed prediction approach (LMA-DeepAR) outperforms other methods in the overall long-term prediction performance and stability of multi cell network traffic. © 2021 IEEE.

关键词： Base stations

来源：评论

学校读者我要写书评

暂无评论

Event-based Video Reconstruction via Spatial-Temporal Heterogeneous Spiking Neural Network

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Yu, Jiajie Lu, Xing Guo, Lijun Wang, Chong Li, Guoqi Qian, Jiangbo Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China University of Nottingham Ningbo China Ningbo315100 China Ningbo University Merchants’ Guild Economics and Cultural Intelligent Computing Laboratory Ningbo315211 China Chinese Academy of Sciences Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Institute of Automation Beijing100045 China

Event cameras detect per-pixel brightness changes and output asynchronous event streams with high temporal resolution, high dynamic range, and low latency. However, the unstructured nature of event streams means that humans cannot analyze and interpret them in the same way as natural images. Event-based video reconstruction is a widely used method aimed at reconstructing intuitive videos from event streams. Most reconstruction methods based on traditional artificial neural networks (ANNs) have high energy consumption, which counteracts the low-power advantage of event cameras. Spiking neural networks (SNNs) are a new generation of event-driven neural networks that encode information via discrete spikes, which leads to greater computational efficiency. Previous methods based on SNNs overlooked the asynchronous nature of event streams, leading to reconstructions that suffer from artifacts, flickering, low contrast, etc. In this work, we analyze event streams and spiking neurons and explain poor reconstruction quality. We specifically propose a novel spatial-temporal heterogeneous (STH) spiking neuron suitable for reconstructing asynchronous event streams. The STH neuron adjusts the membrane decay coefficient adaptively and has better spatiotemporal perception. In addition, we propose a temporal-frequency calibration module (TFCM) based on the Fourier transform to improve the contrast of the reconstructions. On the basis of the above proposed neuron and module, we construct two SNN-based models, referred to as the STHSNN and TFCSNN. The goal of the former is to reduce the artifacts and flickering in reconstructions, whereas the latter focuses on enhancing the contrast. The experimental results demonstrate that our models can yield reconstructions in various scenarios, achieving better quality and lower energy consumption than previous SNNs. Specifically, the TFCSNN and STHSNN achieve top-2 performance among the SNN-based models, with energy consumption reductions of 3.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Lane Detection Method for Advancing Sustainable Energy Internet

A Lane Detection Method for Advancing Sustainable Energy Int...

引用

IEEE Conference on Energy Internet and Energy system Integration (EI2)

作者： Xiting Peng Yang Yang Xiaoyu Zhang Xiaoling Zhang School of Information Science and Engineering Shenyang University of Technology Liaoning Liaohe Laboratory Shenyang Key Laboratory of Advanced Computing and Application Innovation Shenyang China School of Information Science and Engineering Shenyang University of Technology Shenyang China School of Artificial Intelligence Shenyang University of Technology Shenyang Key Laboratory of Industrial Intelligent Chip and Network System Innovation Application Shenyang China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

Artificial intelligence (AI) technology plays a key role in driving the development of a green and smart Energy Internet. As one of the application areas of the Energy Internet, lane detection in intelligent transportation systems can provide accurate real-time traffic data, thus supporting intelligent scheduling and resource optimization, reducing congestion, energy consumption, and emissions, and improving overall energy efficiency. Therefore, deep learning-based lane detection methods can further enhance the intelligence level of the Energy Internet and promote its efficient operation. However, current methods often rely on Convolutional Neural Networks (CNNs), which excel at local feature extraction but struggle to capture global information in complex conditions. In varying light, shadows, and obstacles, CNNs struggle to integrate information, leading to inaccuracies, particularly in dense traffic or complex road structures, where diverse local features result in identification errors and hinder lane continuity. This reduces decision-making efficiency and increases energy consumption. Consequently, we present LFKNet, a lane detection framework designed for the fusion of the Lane Focus Mechanism (LFM) and Kolmogorov-Arnold Network (KAN) to enhance accuracy and robustness. It consists of two key components: the Lane Focus Mechanism , which utilizes the geometrical topology of lanes for improved global fea ture extraction in complex scenarios, and the Kolmogorov-Arnold Network, which employs a learnable nonlinear activation function to optimize performance on complex and nonlinear features. The experiments demonstrate that LFKNet achieves 97.00% accuracy with a 97.76% F1-score on the Tusimple dataset. It also achieves a 79.43% F1-score on the CULane dataset. Overall, LFKNet’s performance validates its effectiveness in lane detection, enabling accurate traffic monitoring and analysis while providing reliable data support for the Energy Internet.

关键词： Energy consumption Accuracy Lane detection Decision making Energy Internet system integration Feature extraction Robustness Topology Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Visual Transformation Telling

arXiv

引用

arXiv 2023年

作者： Cui, Wanqing Hong, Xin Lan, Yanyan Pang, Liang Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Data Intelligence System Research Center Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China

Humans can naturally reason from superficial state differences (e.g. ground wetness) to transformations descriptions (e.g. raining) according to their life experience. In this paper, we propose a new visual reasoning task to test this transformation reasoning ability in real-world scenarios, called Visual Transformation Telling (VTT). Given a series of states (i.e. images), VTT requires to describe the transformation occurring between every two adjacent states. Different from existing visual reasoning tasks that focus on surface state reasoning, the advantage of VTT is that it captures the underlying causes, e.g. actions or events, behind the differences among states. We collect a novel dataset to support the study of transformation reasoning from two existing instructional video datasets, CrossTask and COIN, comprising 13,547 samples. Each sample involves the key state images along with their transformation descriptions. Our dataset covers diverse real-world activities, providing a rich resource for training and evaluation. To construct an initial benchmark for VTT, we test several models, including traditional visual storytelling methods (CST, GLACNet, Densecap) and advanced multimodal large language models (LLaVA v1.5-7B, Qwen-VL-chat, Gemini Pro Vision, GPT-4o, and GPT-4). Experimental results reveal that even state-of-the-art models still face challenges in VTT, highlighting substantial areas for improvement. © 2023, CC BY-NC-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Tbd-Y: Automatic Tea Bud Detection with Synergistic Object-Spatial Attention and Global-Local Attention Guided Feature Fusion

SSRN

引用

SSRN 2025年

作者： Liu, Zhongyuan Zhuo, Li Dong, Chunwang Li, Jiafeng Li, Yang Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China Faculty of Information Technology Beijing University of Technology Beijing100124 China Tea Research Institute Shandong Academy of Agricultural Sciences Jinan250100 China Key Laboratory of Tea Quality and Safety Control Ministry of Agriculture and Rural Affairs Tea Research Institute Chinese Academy of Agricultural Sciences Hangzhou China Shandong Academy of Agricultural Sciences China

Automatic Tea Bud Detection (TBD) is a critical technology in intelligent tea-picking systems. Nevertheless, challenges, such as complex environments and the high visual similarity between tea buds and backgrounds, frequently result in false detection and missed detection, especially for small tea buds. To address these issues, in this paper, an automatic TBD method is proposed, which is built upon the YOLOv11 object detection framework, named TBD-Y. Firstly, a Synergistic Object-Spatial Attention (SOSA) mechanism is proposed, which incorporates the proposed Local Context Attention (LCA) mechanism o enhance the features in both spatial and regional dimensions. It enables the network to focus more on the tea bud regions, and suppress the interference from background noise. Secondly, a Global-local Attention Guided Feature Fusion (GAGFF) strategy is designed. It consists of two branches: one branch enhances low-resolution, high-level features containing rich global semantic information, while the other branch strengthens high-resolution features that preserve low-level visual details. The fusion of these two branches improves the representation capability of the features. The SOSA and GAGFF are integrated into the YOLOv11 framework, constructing three variants of the TBD model with different parameter scales, named TBD-Y-L, TBD-Y-M, and TBD-Y-S. Experimental results on the self-built TBD dataset and the publicly available Global Wheat Head Dataset 2021 (GWHD_2021) demonstrate that the proposed TBD-Y-L outperforms the existing methods, achieving a superior detection accuracy. Furthermore, the TBD-Y-S model exhibits improved detection accuracy compared to YOLOv11-L, while maintaining lower model parameters and computational complexity. © 2025, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Network Architecture Search Framework with Adaptive Multimodal Fusion for Hand Gesture Recognition

arXiv

引用

arXiv 2024年

作者： Xia, Yizhang Song, Shihao Hou, Zhanglu Xu, Junwen Zou, Juan Liu, Yuan Yang, Shengxiang Hunan Engineering Research Center of Intelligent System Optimization and Security Key Laboratory of Intelligent Computing and Information Processing Ministry of Education of China Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Hunan Province Xiangtan411105 China The Centre for Computational Intelligence School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Hand gesture recognition (HGR) based on multimodal data has attracted considerable attention owing to its great potential in applications. Various manually designed multimodal deep networks have performed well in multimodal HGR (MHGR), but most of existing algorithms require a lot of expert experience and time-consuming manual trials. To address these issues, we propose an evolutionary network architecture search framework with the adaptive multimodel fusion (AMF-ENAS). Specifically, we design an encoding space that simultaneously considers fusion positions and ratios of the multimodal data, allowing for the automatic construction of multimodal networks with different architectures through decoding. Additionally, we consider three input streams corresponding to intra-modal surface electromyography (sEMG), intra-modal accelerometer (ACC), and inter-modal sEMG-ACC. To automatically adapt to various datasets, the ENAS framework is designed to automatically search a MHGR network with appropriate fusion positions and ratios. To the best of our knowledge, this is the first time that ENAS has been utilized in MHGR to tackle issues related to the fusion position and ratio of multimodal data. Experimental results demonstrate that AMF-ENAS achieves state-of-the-art performance on the Ninapro DB2, DB3, and DB7 datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

GM-DF: Generalized Multi-Scenario Deepfake Detection

arXiv

引用

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Learning domain-aware detection head with prompt tuning 23

Learning domain-aware detection head with prompt tuning

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Haochen Li Rui Zhang Hantao Yao Xinkai Song Yifan Hao Yongwei Zhao Ling Li Yunji Chen Intelligent Software Research Center Institute of Software CAS Beijing China and University of Chinese Academy of Sciences Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China and University of Chinese Academy of Sciences Beijing China

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a discriminative visual encoder, while ignoring the domain bias in the detection head. Inspired by the high generalization of vision-language models (VLMs), applying a VLM as the robust detection backbone following a domain-aware detection head is a reasonable way to learn the discriminative detector for each domain, rather than reducing the domain bias in traditional methods. To achieve the above issue, we thus propose a novel DAOD framework named Domain-Aware detection head with Prompt tuning (DA-Pro), which applies the learnable domain-adaptive prompt to generate the dynamic detection head for each domain. Formally, the domain-adaptive prompt consists of the domain-invariant tokens, domain-specific tokens, and the domain-related textual description along with the class label. Furthermore, two constraints between the source and target domains are applied to ensure that the domain-adaptive prompt can capture the domains-shared and domain-specific knowledge. A prompt ensemble strategy is also proposed to reduce the effect of prompt disturbance. Comprehensive experiments over multiple cross-domain adaptation tasks demonstrate that using the domain-adaptive prompt can produce an effectively domain-related detection head for boosting domain-adaptive object detection. Our code is available at https://***/Therock90421/DA-Pro.

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：