检索结果-内蒙古大学图书馆

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

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Curved Text Detection Based on Graph Convolution Context Enhancement

Curved Text Detection Based on Graph Convolution Context Enh...

引用

Chinese Automation Congress (CAC)

作者： Xinyue Mao Hongyang Zhou Jiapei Wang Yuan Zhang College of Big Data and Artificial Intelligence China Telecom Research Institute Shanghai China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China College of Big Data and Artificial Intelligence China Telecom Research Institute Hangzhou China

Text detection in industrial scenarios faces a major challenge: how to design smaller models while maintaining high detection accuracy. We propose a curved text detection model based on graph convolution context enhancement. By using the lightweight backbone MobileNetV2 to reduce the parameter count, and using the graph convolution context module to enhance context modeling ability. The target scene of this paper is the detection of painting characters on steel coils in the production process. Experiments on the Total-Text and the steel coil painting characters dataset show that the proposed method can maintain the optimal detection results with fewer parameters. Graph convolution context module makes the F-measure of this model on the Total-Text test set optimal among the methods based on lightweight networks such as ResNet18 and smaller networks. On the steel coil painting characters dataset, the F-measure of our method is also ahead of PAN and PSENet, and achieves real-time performance.

关键词： Coils Convolution Computational modeling Production Feature extraction Real-time systems Steel

来源：评论

学校读者我要写书评

暂无评论

End-to-End Remote Sensing Image Scene Classification with Vision Transformers 23

End-to-End Remote Sensing Image Scene Classification with Vi...

引用

6th International Conference on big data Technologies, ICBDT 2023

作者： Yuan, Hao Liu, Kun Shi, Jiechuan Wang, Can Wang, Weiwei School of Information Science and Engineering University of Jinan Jinan250022 China China High-resolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China QiLu Research Institute Jinan250200 China

ISBN: (纸本)9798400707667

In recent years, the development of deep learning technology has led to widespread attention on Vision Transformer (ViT) as an emerging image classification method. Remote sensing image classification is an important task in the field of remote sensing, with extensive application prospects. This paper aims to explore the remote sensing image classification method based on Vision Transformer, addressing the limitations of traditional convolutional neural networks in terms of global perception capability, context information retrieval, and positional encoding. The classification performance of the Vision Transformer model is evaluated and compared on remote sensing datasets. Vision Transformer is a deep neural network model based on self-attention mechanism that can capture the global context information in images and has achieved remarkable performance in various computer vision tasks. Furthermore, experimental results demonstrate that the remote sensing image classification method based on Vision Transformer exhibits outstanding accuracy and generalization ability. Compared to traditional convolutional neural networks, it can better capture the global features in remote sensing images and has better scalability when dealing with large-scale remote sensing image data. Experimental results on different remote sensing image datasets show that the model performs well compared to state-of-the-art methods. Specifically, Vision Transformer achieves average classification accuracies of 95.41%, 98.26%, 93.74% and 95.25% on the AID, UC-Merced, NWPU-RESISC45 and Optimal31 datasets, respectively. © 2023 ACM.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A study on gait analysis based on the pose estimation algorithm RTMPose using knee angle as a metric

A study on gait analysis based on the pose estimation algori...

引用

IEEE International Conference on Mechatronics and Automation

作者： Xin Guo Huimin Zhao School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Ministry of Education Engineering Research Center for Intelligent Rehabilitation Device and Detection Technology Tianjin China Qinhuangdao Research Institute of National Rehabilitation Aids Research Center Qinhuangdao China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Gait analysis can be used to assess a person's fall risk and evaluate the effectiveness of fall prevention training. The knee angle is a crucial metric for assessing gait. This study utilized the markerless lightweight pose estimation algorithm RTMPose to evaluate gait. Firstly, 2D human key point detection was performed based on the video. Then the knee angle change curves during walking and pedaling elliptical machine movement were calculated from the key points for gait analysis. This study analyzed knee angle data from individuals with varying body shapes. The results demonstrated that, compared to OpenPose and YOLOv8, RTMPose can quickly and accurately measure the knee angle and determine the abnormal gait condition. It does not need to wear sensors or rely on special testing environments, which is conducive to objective and effective gait analysis by professional rehabilitation workers.

关键词： Knee Training Power measurement Shape Prevention and mitigation Pose estimation Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for Speech Source Separation

EDSep: An Effective Diffusion-Based Method for Speech Source...

引用

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

作者： Jinwei Dong Xinsheng Wang Qirong Mao School of Computer Science and Communication Engineering Jiangsu University Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi’an China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Zhenjiang China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method’s superior performance over existing diffusion and discriminative models, validating its efficacy.

关键词： Training Adaptation models Technological innovation Source separation databases Stochastic processes Differential equations Speech enhancement Diffusion models Mathematical models

来源：评论

学校读者我要写书评

暂无评论

ICH-SCNet: Intracerebral Hemorrhage Segmentation and Prognosis Classification Network Using CLIP-guided SAM mechanism

arXiv

引用

arXiv 2024年

作者： Yu, Xinlei Jin, Hui Wu, Qing Elazab, Ahmed Jiang, Xinchen Shi, Qinglei Ge, Ruiquan Jia, Gangyong Wang, Changmiao School of Computer Science Hangzhou Dianzi University Hangzhou China School of Biomedical Engineering Shenzhen University Shenzhen China School of Management and Economics The Chinese University of Hong Kong Shenzhen Shenzhen China School of Medicine The Chinese University of Hong Kong Shenzhen Shenzhen China Medical Big Data Lab Shenzhen Research Institute of Big Data Shenzhen China

Intracerebral hemorrhage (ICH) is the most fatal subtype of stroke and is characterized by a high incidence of disability. Accurate segmentation of the ICH region and prognosis prediction are critically important for developing and refining treatment plans for post-ICH patients. However, existing approaches address these two tasks independently and predominantly focus on imaging data alone, thereby neglecting the intrinsic correlation between the tasks and modalities. This paper introduces a multi-task network, ICH-SCNet, designed for both ICH segmentation and prognosis classification. Specifically, we integrate a SAM-CLIP cross-modal interaction mechanism that combines medical text and segmentation auxiliary information with neuroimaging data to enhance cross-modal feature recognition. Additionally, we develop an effective feature fusion module and a multi-task loss function to improve performance further. Extensive experiments on an ICH dataset reveal that our approach surpasses other state-of-the-art methods. It excels in the overall performance of classification tasks and outperforms competing models in all segmentation task metrics. © 2024, CC BY.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

A method for detecting floating objects on water based on edge computing

A method for detecting floating objects on water based on ed...

引用

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Li, He Yang, Shuaipeng Liu, Jinjiang Fang, Honglin Fu, Zhumu Zhang, Rui Jia, Huimei Lv, Lianmeng Henan Costar Group Co. Ltd Henan Nanyang473003 China Henan University of Science and Technology College of Information Engineering Henan Luoyang471000 China Nanyang Normal University Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image School of Computer Science and Technology Nanyang473061 China Beijing University of Posts and Telecommunication State Key Laboratory of Networking and Switching Technology Beijing100876 China Xi'an Hengpin Electronic Technology Co. Ltd Xi'an710100 China

ISBN: (纸本)9798350321524

With the development and application of computer vision, many target detection networks are applied to the detection of floating objects in rivers. For the detection problems such as small targets easily missed and misdetected in water surface floating object detection tasks and difficult to deploy models. An edge computing-oriented approach to river floater detection is proposed. First, a four-fold down-sampling feature layer is added to the YOLOv5 network which enhances more target detail features and improves the detection capability of small objects. Second, CA (Coordinate Attention) is added to the Backbone to suppress background noise interference, and different pooling is used to accommodate different hierarchical features. Then, a bilinear interpolation method is adopted for up-sampling to avoid the loss of small object features. Design a data enhancement algorithm for small targets based on Mosaic to increase the number of small objects and enrich the training background. Finally, for the edge computing architecture platform, the channel pruning algorithm is used to prune and compress the model structure to adapt to the computing capability of edge devices. The experimental results show that the method can effectively improve the detection capability of the network for floating objects on the water surface. The detection accuracy can reach 93.6%, and the detection speed can be maintained at 36 frames per second, which can achieve high-precision real-time detection of floating objects on the water surface. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Combining Self-Supervised Learning and Adversarial Training Based Domain Adaptation for Speaker Verification

Combining Self-Supervised Learning and Adversarial Training ...

引用

International Symposium on Chinese Spoken Language Processing

作者： Zhengyang Chen Shuai Wang Bing Han Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai Shenzhen Research Institute of Big Data Shenzhen Chinese University of Hong Kong Shenzhen

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Adapting an existing well-trained system to a new domain using only unlabeled data is a highly sought-after yet challenging task for speaker verification in real-world scenarios. In this paper, we study two different domain adaptation methods, the adversarial domain adaptation (ADA) and the self-supervised learning-based domain adaptation (SSDA). To facilitate the deployment of unsupervised adaptation methods in applications, we conduct a detailed analysis of the characteristics of both the ADA and SSDA adaptation strategies. Our findings indicate that the SSDA strategy's performance is highly influenced by the amount of target domain data, whereas the ADA strategy is relatively insensitive to data quantity. Furthermore, augmenting target domain data enhances SSDA system performance but diminishes ADA performance. To further enhance system performance, we explore the complementarity between ADA and SSDA. Our results demonstrate that ADA and SSDA complement each other. When both strategies are applied jointly, the best system achieves over 20.0% relative Equal Error Rate (EER) improvement on the Cnceleb evaluation set and over 35.0% relative average EER improvement on the SRE16 Cantonese and Tagalog evaluation set under domain mismatched conditions.

关键词： Training Error analysis System performance Self-supervised learning Speech processing

来源：评论

学校读者我要写书评

暂无评论

Learning to Optimize Resource Allocation in Dynamic Wireless Environments: Embracing the New While Engaging the Old

引用

IEEE Transactions on Wireless Communications 2025年

作者： Liu, Zhenrong Li, Yang Wu, Yik-Chung Gong, Yi The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong Hong Kong Southern University of Science and Technology Department of Electrical and Electronic Engineering Shenzhen518055 China Shenzhen Research Institute of Big Data Shenzhen518172 China Great Bay University School of Computing and Information Technology Dongguan523000 China

Wireless resource allocation is a critical component in modern communication systems, and deep neural networks (DNNs) have shown great promise in addressing this challenge. However, the conventional DNNs assume that testing data follows the same distribution as that of the training data, which is incongruent with the dynamic nature of real-world wireless environments. This paper introduces a new training algorithm designed specifically for dynamic wireless environments where channel distribution exhibits variability. This method helps DNNs adapt to new environments while preserving previously learned information. The proposed approach distinguishes itself by updating the DNN parameters in the null space of the low-rank covariance of previous data, which reduces memory needs and boosts training efficiency. Additionally, to counter the problem of DNNs hitting their model capacity during continuous adaptation, a selective forgetting mechanism is proposed. This mechanism allows DNNs to discard the unimportant knowledge over time, freeing up model capacity for more effective adaptation. The effectiveness of the algorithm is validated by integrating it with graph neural networks and multilayer perceptrons for weighted sum-rate maximization. Through a comprehensive evaluation that includes synthetic and ray-tracing-based datasets, superior performance is demonstrated compared to existing methods. © 2002-2012 IEEE.

关键词： Deep learning dynamic environments low-rank null space wireless resource allocation

来源：评论

学校读者我要写书评

暂无评论

LLM Knows Geometry Better than Algebra: Numerical Understanding of LLM-Based Agents in A Trading Arena

arXiv

引用

arXiv 2025年

作者： Ma, Tianmi Du, Jiawei Huang, Wenxin Wang, Wenjie Xie, Liang Zhong, Xian Zhou, Joey Tianyi Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computing National University of Singapore Singapore School of Science Wuhan University of Technology China

Recent advancements in large language models (LLMs) have significantly improved performance in natural language processing tasks. However, their ability to generalize to dynamic, unseen tasks, particularly in numerical reasoning, remains a challenge. Existing benchmarks mainly evaluate LLMs on problems with predefined optimal solutions, which may not align with real-world scenarios where clear answers are absent. To bridge this gap, we design the Agent Trading Arena, a virtual numerical game simulating complex economic systems through zero-sum games, where agents invest in stock portfolios. Our experiments reveal that LLMs, including GPT-4o, struggle with algebraic reasoning when dealing with plain-text stock data, often focusing on local details rather than global trends. In contrast, LLMs perform significantly better with geometric reasoning when presented with visual data, such as scatter plots or K-line charts, suggesting that visual representations enhance numerical reasoning. This capability is further improved by incorporating the reflection module, which aids in the analysis and interpretation of complex data. We validate our findings on NASDAQ STOCK dataset, where LLMs demonstrate stronger reasoning with visual data compared to text. Our code and data are publicly available at https://***/wekjsdvnm/***. © 2025, CC BY.

关键词： Natural language processing systems

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：