检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhou, Hanyu Wang, Haonan Liu, Haoyue Duan, Yuxing Chang, Yi Yan, Luxin National Key Lab of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China School of Computing National University of Singapore Singapore

High-dynamic scene optical flow is a challenging task, which suffers spatial blur and temporal discontinuous motion due to large displacement in frame imaging, thus deteriorating the spatiotemporal feature of optical flow. Typically, existing methods mainly introduce event camera to directly fuse the spatiotemporal features between the two modalities. However, this direct fusion is ineffective, since there exists a large gap due to the heterogeneous data representation between frame and event modalities. To address this issue, we explore a common-latent space as an intermediate bridge to mitigate the modality gap. In this work, we propose a novel common spatiotemporal fusion between frame and event modalities for high-dynamic scene optical flow, including visual boundary localization and motion correlation fusion. Specifically, in visual boundary localization, we figure out that frame and event share the similar spatiotemporal gradients, whose similarity distribution is consistent with the extracted boundary distribution. This motivates us to design the common spatiotemporal gradient to constrain the reference boundary localization. In motion correlation fusion, we discover that the frame-based motion possesses spatially dense but temporally discontinuous correlation, while the event-based motion has spatially sparse but temporally continuous correlation. This inspires us to use the reference boundary to guide the complementary motion knowledge fusion between the two modalities. Moreover, common spatiotemporal fusion can not only relieve the cross-modal feature discrepancy, but also make the fusion process interpretable for dense and continuous optical flow. Extensive experiments have been performed to verify the superiority of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

DD-Net: Dynamic Network Architecture for Optimized Curve Segmentation and Reduce Computational Redundancy 27th

DD-Net: Dynamic Network Architecture for Optimized Curve Seg...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Cao, Yunxiang Chen, Li Wang, Yubo Feng, Zhida Tian, Jing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China Institute of Systems Science National University of Singapore Singapore Singapore

ISBN: (纸本)9783031783821

Curvilinear Structure segmentation has numerous applications in various fields, including providing a better understanding of defects such as cracks on roads or walls, thereby assessing the structural safety of buildings. Numerous curve segmentation methods based on Convolutional Neural Networks(CNN) have been developed in recent years. However, preserving feature integrity remains a challenge. To address this issue, this paper introduces a double dynamic network, called DD-Net, which consists of a dynamic structure for training and dynamic masking for inference. Firstly, to enhance the nonlinearity of the model, a paradigm to auto-adjust the CNN structure via a trainable module is formed for better fine-grained feature extraction. This dynamic structure (DS) paradigm enables a trade-off to extract or discard the feature data in the model training. Due to the data heterogeneity between the training and inference data, models may contain some useless nodes that are less effective during inference. The dynamic masking (DM) is proposed to omit the useless nodes based on the score difference between the train and inference feature statistics, thereby reducing redundant computations. To further improve the model’s performance on thin-curve segmentation and to preserve feature integrity, we introduce a non-curve suppression (NCS) module. This module focuses on background information while considering foreground prediction to address noisy conditions. The experimental results show that our DD-Net achieves promising results on three benchmark datasets and outperforms state-of-the-art curve segmentation models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MASS FLOW DETECTION technology FOR SEED AND FERTILISER PARTICLES AND ITS APPLICATION IN UAV-BASED SPREADING

引用

INMATEH - Agricultural Engineering 2025年第1期75卷 584-599页

作者： Wang, Yanshuang Song, Cancan Gao, Yongqi Lan, Yubin Wang, Guobin Ming, Rui College of Agricultural Engineering and Food Science Shandong University of Technology Zibo China Shandong University of Technology Sub-center of National Center for International Collaboration Research on Precision Agricultural Aviation Pesticide Spraying Technology Zibo China Research of Institute of Ecological Unmanned Farm Shandong University of Technology Zibo China School of Computer and Big Data Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China

The processes of sowing and fertiliser application represent a significant aspect of agricultural production. In order to achieve efficient and precise seeding and fertiliser application, mass flow detection of seed and fertiliser particles can facilitate real-time monitoring and precise decision-making for intelligent seeding and fertiliser application. However, the diversity of seed and fertiliser particle types and particle flow modes presents a challenge for existing detection methods, particularly in meeting the varying operational requirements, especially for particle mass flow detection in low-altitude and high-speed sowing operations of agricultural drones. In such cases, the overlap and flow rate will have a significant impact on the detection results due to the large displacement and the continuous high-throughput dense phase of the particle flow. This paper provides a summary of the existing seed and fertiliser particle mass flow detection techniques and their underlying working principles. It compares the direct detection based on mass with the indirect detection methods based on velocity and concentration, and analyses their respective advantages, disadvantages and applicability. It also explores the possibility of optimising the existing detection methods for the specific needs of agricultural UAVs and considers the potential introduction of cutting-edge science and technology in order to develop an efficient, accurate and convenient detection system to meet the growing market demand. © (2025), (INMA Bucharest). All Rights Reserved.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

IsoVISoR: Towards 3D Mesoscale Brain Mapping of Large Mammals at Isotropic Sub-micron Resolution

引用

Neuroscience Bulletin 2025年第2期41卷 344-348页

作者： Chao-Yu Yang Yan Shen Xiaoyang Qi Lufeng Ding Yanyang Xiao Qingyuan Zhu Hao Wang Cheng Xu Pak-Ming Lau Pengcheng Zhou Fang Xu Guo-Qiang Bi Division of Life Sciences and Medicine CAS Key Laboratory of Brain Function and DiseaseUniversity of Science and Technology of ChinaHefei230026China Interdisciplinary Center for Brain Information Shenzhen-Hong Kong Institute of Brain ScienceShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518055China Center for Integrative Imaging Hefei National Research Center for Physical Sciences at the MicroscaleUniversity of Science and Technology of ChinaHefei230027China National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application MoE Key Laboratory of Brain-Inspired Intelligent Perception and CognitionSchool of Information Science and TechnologyUniversity of Science and Technology of ChinaHefei230026China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial IntelligenceHefei Comprehensive National Science CenterHefei230088China Faculty of Life and Health Sciences Shenzhen University of Advanced TechnologyShenzhen518107China CAS Key Laboratory of Brain Connectome and Manipulation The Brain Cognition and Brain Disease InstituteShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518055China

Dear Editor,The mammalian brain exhibits cross-scale complexity in neuronal morphology and connectivity,the study of which demands high-resolution morphological reconstruction of individual neurons across the entire brain[1-4].Current commonly used approaches for such mesoscale brain mapping include two main types of three-dimensional fluorescence microscopy:the block-face methods,and the lightsheet-based methods[5,6].In general,the high imaging speed and light efficiency of light-sheet microscopy make it a suitable tool for high-throughput volumetric imaging,especially when combined with tissue-clearing ***,large brain samples pose major challenges to this approach.

关键词： brain mapping three dimensional fluorescence microscopy mesoscale brain mapping lightsheet based methods block face methods high throughput volumetric imaging tissue clearing techniques

来源：评论

学校读者我要写书评

暂无评论

Semantic Data Augmentation for Few-Shot Biomedical Named Entity Recognition

Semantic Data Augmentation for Few-Shot Biomedical Named Ent...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Zhang, Ying Wang, Weihua College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (纸本)9798350368741

Biomedical Named Entity Recognition (BioNER) aims to identify and classify entities in biomedical text. This task struggles with data scarcity due to limited annotated data. Although data augmentation is effective, existing methods fail to handle the complex semantic mappings on biomedical terminology, which results in the generated samples lacking semantic diversity. In this paper, we propose a data augmentation method to create semantically diverse and coherent training samples for few-shot BioNER. The method utilizes the Unified Medical Language System (UMLS) for entity replacement and combines with a Masked Language Model (MLM) to generate contextually relevant words. Experimental results show that our method improves BioNER performance in few-shot scenarios. Compared to all baseline models, our method achieves an average F1 score improvement of 7.6% and 11.6% on the NCBI and JNLPBA datasets, respectively. Our source code and data are available at https://***/ABC8184/SDA. © 2025 IEEE.

关键词： BioNER data augmentation few-shot learning masked language model UMLS

来源：评论

学校读者我要写书评

暂无评论

Visual Language Model based Cross-modal Semantic Communication Systems

引用

IEEE Transactions on Wireless Communications 2025年第5期24卷 3937-3948页

作者： Jiang, Feibo Tang, Chuanguo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha410081 China Hunan Normal University School of Information Science and Engineering Changsha410081 China Hunan University of Technology and Business School of Computer Science Changsha410205 China Xiangjiang Laboratory Changsha410205 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Nanjing University School of Intelligent Software and Engineering Suzhou215163 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China

Semantic Communication (SC) has emerged as a novel communication paradigm in recent years. Nevertheless, extant Image Semantic Communication (ISC) systems face several challenges in dynamic environments, including low information density, catastrophic forgetting, and uncertain Signal-to-Noise Ratio (SNR). To address these challenges, we propose a novel Vision-Language Model-based Cross-modal Semantic Communication (VLM-CSC) system. The VLM-CSC comprises three novel components: (1) Cross-modal Knowledge Base (CKB) is used to extract high-density textual semantics from the semantically sparse image at the transmitter and reconstruct the original image based on textual semantics at the receiver. The transmission of high-density semantics contributes to alleviating bandwidth pressure. (2) Memory-assisted Encoder and Decoder (MED) employ a hybrid long/short-term memory mechanism, enabling the semantic encoder and decoder to overcome catastrophic forgetting in dynamic environments when there is a drift in the distribution of semantic features. (3) Noise Attention Module (NAM) employs attention mechanisms to adaptively adjust the semantic coding and the channel coding based on SNR, ensuring the robustness of the CSC system. The experimental simulations validate the effectiveness, adaptability, and robustness of the CSC system. © 2002-2012 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Bi-Temporal Feature Relational Distillation for On-Board Lightweight Change Detection in Remote Sensing Imagery

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Wang, Guoqing Chen, He Li, Jie Wang, Jue Liu, Wenchao Chen, Liang Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China Shanghai Aerospace Electronic Technology Institute Shanghai201109 China

Deep learning models for remote sensing change detection (CD) require significant resources, challenging real-time applications on spaceborne devices. Knowledge distillation (KD) technology is a potential solution that balances model size and CD performance. However, existing KD methods struggle to effectively transfer the teacher's ability to respond to changed landcovers, and also face challenges in assisting the student model in detecting changes in landcovers with subtle visual characteristics. To overcome these limitations, a bi-temporal feature relational distillation (FRD) framework is proposed. The FRD framework includes two designed distillation components: bi-temporal feature distance distillation (BFDD) and contrastive cluster representation distillation (CCRD). BFDD guides the student model to learn the relationship between bi-temporal feature categories from the teacher model and introduces the iteration-wise random selection and bilinear interpolation strategy to solve feature mismatch problem between the teacher and the student. CCRD describes the pixel-level and clusterlevel feature distributions through the designed contrastive cluster (CC) module, guiding the student model to align the change/nonchange features with the teacher model, so as to alleviate the confusion of change/non-change features. Extensive experiments and analyses have confirmed that the proposed FRD framework can develop lightweight models capable of achieving performance comparable to large models, thereby enhancing suitability for realtime CD. © 1965-2011 IEEE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech Synthesis

Anchored Monotonic Alignment and Representation Substitution...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Wu, Ning-Qian Hu, Ya-Jun Chen, Liping Ling, Zhen-Hua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China iFLYTEK Research iFLYTEK Co. Ltd. China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China

ISBN: (纸本)9798350368741

Spontaneous behaviors in speech pose significant challenges for speech synthesis. Existing research has not adequately addressed these behaviors, with most studies relying on specially recorded datasets. In contrast, real-world data more accurately reflects the natural, spontaneous speaking styles in everyday life and encompasses a wider range of spontaneous behaviors. However, such data is often of lower quality, and the distribution of spontaneous behaviors is highly imbalanced. In this study, we explore spontaneous speech synthesis using real-world data within the VITS2 framework. To overcome these challenges, we introduce two techniques: anchored monotonic alignment and spontaneous hidden representation substitution. Experimental results demonstrate that these methods enhance model alignment and improve the naturalness of the generated speech. Our proposed approach successfully addresses the challenge of synthesizing rare spontaneous behaviors and offers users flexible control over the synthesized speech. © 2025 IEEE.

关键词： real-world data speech synthesis spontaneous behaviors spontaneous speech synthesis VITS

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Entity Typing with Curriculum Contrastive Learning 31

Knowledge Graph Entity Typing with Curriculum Contrastive Le...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Hao Nuo, Minghua Jiang, Shan College of Computer Science Inner Mongolia University Inner Mongolia Hohhot010021 China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Hohhot010021 China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Inner Mongolia Hohhot010021 China

ISBN: (纸本)9798891761964

The Knowledge Graph Entity Typing (KGET) task aims to predict missing type annotations for entities in knowledge graphs. Most recent studies only focus on the structural information from an entity's neighborhood or semantic information from textual representations of entities or relations. In this paper, inspired by curriculum learning and contrastive learning, we propose the CCLET model using the Curriculum Contrastive Learning strategy for KGET, which uses the Pre-trained Language Model (PLM) and the graph model to fuse the entity related semantic and the structural information of the Knowledge Graph (KG) respectively. Our CCLET model consists of two main parts. In the Knowledge Fusion part, we design an Enhanced-MLP architecture to fuse the text of the entity's description, related triplet and tuples;In the Curriculum Contrastive Learning part, we define the difficulty of the training course by controlling the level of added noise, we aim to accurately learn with curriculum contrastive learning strategy from easy to difficult. Our extensive experiments demonstrate that the CCLET model outperforms recent state-of-the-art models, verifying its effectiveness in the KGET task. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Autoencoder-based Probabilistic Shaping Method for Optical Communication 7

An End-to-End Autoencoder-based Probabilistic Shaping Method...

引用

7th Optics Young Scientist Summit, OYSS 2024

作者： Teng, Ziqiang Guo, Dong Gao, Ran Kong, Leyi Han, Wentao Chang, Huan Li, Zhipei Xin, Xiangjun School of Information and Electronics Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China Institute of Science and Technology Research Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China

ISBN: (数字)9781510688377

ISBN: (纸本)9781510688360

The advent of services such as big data and cloud computing has driven a continuous increase in the required transmission rate and capacity of optical fiber communication systems, which now support over 90% of global data traffic. Probability shaping (PS), which adjusts the probability distribution of constellation points, enhances both data transmission rates and the resilience of signals to channel nonlinearity. However, traditional PS methods, such as those using constant composition distribution matching (CCDM), cannot dynamically adjust the probability distribution of constellation points based on channel conditions. To address this limitation, we propose an end-to-end Autoencoder (AE)-based PS technique for optical communication. Simulation results show that compared to traditional 16/64/256QAM, this scheme achieves a maximum improvement of 0.356 bit/symbol in mutual information over the AWGN channel. In the optical fiber channel, under varying signal power and fiber length conditions, the mutual information is improved in different degrees and the influence of channel nonlinearity on the signal is reduced. Innovatively, residual connections are added to the decoder to enhance the model's generalization performance, enabling a deeper network structure and improving its ability to handle complex optical fiber channels. © 2025 SPIE.

关键词： Optical fiber communication

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：