检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Xie, Shangjin Feng, Jiawei Chen, Zibo Liu, Zhixuan Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783031784552

Labeling every point in a scene is a laborious journey for 3D understanding. To achieve annotation-free training, existing works introduce Contrastive Language-Image Pre-training (CLIP) to transfer the pre-trained capability of visual-linguistic correspondence to 3D-linguistic matching. However, directly adopting this CLIP-driven strategy can inevitably introduce bias: The overrated roles of the color and texture from an RGB image could overshadow the geometric nature of the corresponding 3D scene, resulting in a sub-optimal alignment. We note that different from RGB images, a depth map contains rich geometric information. Inspired by this, we propose Depth-Enhanced Alignment (D-EA) for label-free 3D semantic segmentation. D-EA aims to explore the rich geometric cues in depth maps and mitigate the color and texture biases rooted in the original CLIP-driven strategy. Specifically, we first tune a geometry-enhanced CLIP by aligning its depth prediction to the paired RGB prediction given by the original CLIP. Next, the point cloud feature space is matched with the RGB-Depth aggregated CLIP space by aligning point prediction to RGB and depth predictions. Moreover, to mitigate the semantic ambiguity caused by view-specific noise, we propose a View-Integrated Pseudo Label Generation paradigm. Experiments demonstrate the effectiveness of the proposed D-EA on the ScanNet (indoor) and GraspNet-1Billion (desktop) datasets in the label-free setting. Our method is also competitive in limited annotation semantic segmentation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

iGrasp: An Interactive 2D-3D Framework for 6-DoF Grasp Detection 27th

iGrasp: An Interactive 2D-3D Framework for 6-DoF Grasp Detec...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Jiang, Jian-Jian Wu, Xiao-Ming Chen, Zibo Wei, Yi-Lin Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783031781124

For 6-DoF grasp detection, we aim at introducing a new interactive 2D-3D framework which filters out irrelevant information and makes both modalities collaborate effectively to generate robust grasps and accelerate inference speed greatly. This cannot be accomplished by existing works on learning to grasp that merely utilize 3D point clouds or leverage both 2D textures and 3D point clouds. Our framework is called iGrasp, a novel three-step design between 2D textures and 3D point clouds, where the interaction modelling enhances both modalities. Concretely, we propose the 2D-to-3D interaction to leverage objectness masks generated from 2D textures to filter out target-irrelevant information in 3D point clouds. Then, we introduce the 3D-to-2D interaction to leverage structural priors from 3D point cloud features with cross-attention and cylinder grouping to refine 2D texture features. Finally, we combine the refined 2D texture features and 3D point cloud features for generating high-quality 6-DoF grasp poses. Our experiments on the large-scale real-world dataset, namely GraspNet-1Billion, demonstrate that iGrasp surpasses state-of-the-art methods by 4.66/3.53 mAP on RealSense/Kinect and reduces the inference time by 28%. Real-world experiments further verify the effectiveness of iGrasp. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization 27th

Towards Completeness: A Generalizable Action Proposal Genera...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Du, Jia-Run Lin, Kun-Yu Meng, Jingke Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783031784439

To address the zero-shot temporal action localization (ZSTAL) task, existing works develop models that are generalizable to detect and classify actions from unseen categories. They typically develop a category-agnostic action detector and combine it with the Contrastive Language-Image Pre-training (CLIP) model to solve ZSTAL. However, these methods suffer from incomplete action proposals generated for unseen categories, since they follow a frame-level prediction paradigm and require hand-crafted post-processing to generate action proposals. To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way. Our GAP is built in a query-based architecture and trained with a proposal-level objective, enabling it to estimate proposal completeness and eliminate the hand-crafted post-processing. Based on this architecture, we propose an Action-aware Discrimination loss to enhance the category-agnostic dynamic information of actions. Besides, we introduce a Static-Dynamic Rectifying module that incorporates the generalizable static information from CLIP to refine the predicted proposals, which improves proposal completeness in a generalizable manner. Our experiments show that our GAP achieves state-of-the-art performance on two challenging ZSTAL benchmarks, i.e., Thumos14 and ActivityNet1.3. Specifically, our model obtains significant performance improvement over previous works on the two benchmarks, i.e., +3.2% and +3.4% average mAP, respectively. The code is available at https://***/Run542968/GAP. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Speech Emotion Recognition With Conditional Emotion Feature Diffusion and Progressive Interleaved Learning Strategy

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1787-1800页

作者： Yang Liu Xin Chen Zhichao Peng Yongwei Li Xingfeng Li Peng Song Masashi Unoki Zhen Zhao School of Information Science and Technology Qingdao University of Science and Technology Qingdao China School of Information Hunan University of Humanities Science and Technology Loudi China CAS Key Laboratory of Behavioral Science Institute of Psychology Chinese Academy of Sciences Beijing China Faculty of Data Science City University of Macau Macau China School of Computer and Control Engineering Yantai University Yantai China School of Information Science Japan Advanced Institute of Science and Technology Nomi Japan

Speech emotion recognition (SER) aims to identify the speaker's emotional states in specific utterances accurately. However, existing methods still face feature confusion when attempting to recognize certain emotions because traditional acoustic feature extraction methods fail to capture dynamic emotional changes, blurring emotional boundaries. Additionally, existing classification networks (CNs) are constrained by fixed learning strategies, hindering their ability to capture subtle emotional nuances and resulting in label confusion. To address these two issues, we introduce 3D multiresolution modulation filtered cochleogram (MMCG) features by computing the deltas and delta-deltas of MMCG features to enhance the dynamic emotional changes and produce distinct emotional boundaries. We then customize a conditional emotion feature diffusion (CEFD) module, which progressively diffuses features based on emotional context to retain emotional nuances effectively and reduce reliance on conditioned information. In addition, a confidence filtering module is used to filter diffused features based on confidence-based posterior probabilities to ensure enhanced feature discrimination. We design a flexible training strategy named the progressive interleaved learning strategy (PILS) to learn further complex emotional nuances, which consists of two alternating stages: fine-tuning the CN parameters and supervising the CEFD output. Testing on the IEMOCAP, CASIA, and EMODB corpora demonstrates significant performance improvements in SER.

关键词： Feature extraction Emotion recognition Training Three-dimensional displays Diffusion models Speech enhancement Electronic mail Speech recognition Semantics Face recognition

来源：评论

学校读者我要写书评

暂无评论

An Empirical Comparison of Machine and Deep Learning Algorithms for Predicting Maternal Health Risk 5th

An Empirical Comparison of Machine and Deep Learning Algorit...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： N, Srinivasa Gupta Valarmathi, B. Kavitha, A. Gopini, Sai Bhuvan Seela, Hari Kumar Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Mathematics School of Advanced of Sciences Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9783031770777

Maternal health is among the greatest challenges in the world, especially in rural areas as there lack medical practitioners, they do not have easily accessible publics clinics and transport is difficult. Therefore, high rates of maternal as well as infant morbidity and mortalities are recorded. This research utilizes Artificial Intelligence (AI) with machine learning algorithms to forecast and address maternal health hazards right at their onset stage. The current research utilizes the concept of AI along with many Machine Learning (ML) methods like the Ensemble Learning Model (ELM), Random Forest (RF), K-Nearest Neighbour (KNN), Decision-Tree (DT), XG-Boost (XGB), Cat Boost (CB), and Gradient Boosting (GB), along with Synthetic Minority Over-sampling Technique (SMOTE) algorithm used for dealing with the problem class imbalance within the data set. SMOTE algorithm is utilized for the dataset balancing process. The handling system involves refining data preprocessing with the help of feature engineering and robust data cleaning which makes sure that anomalies do not erode the reliability of the predictive model. The existing methods [1] used RF (90%), DT (87%), XGB (85%), CB (86%), and GB (81%) algorithms and were compared with the accuracies of the proposed models like Logistic Regression (LR), Ensemble Learning Bagging (ELB), Ensemble Learning Stacking (ELS), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The existing methods used only imbalance dataset. The accuracies of the proposed models with using SMOTE algorithm (balanced dataset) are LR (61.33%), KNN (81%), ELB (92.33%), ELS (90.66%) CNN (40.67%), RNN (59.67%), LSTM (54%), GRU (56%) respectively. Among these methods, ELB achieved 92.33% of accuracy with using SMOTE algorithm using imbalanced dataset. Whereas the accuracies of the proposed models without using SMOTE algorithm (imbalanced dataset) are LR (66.09%), KNN (68.47%)

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Technique for Image Captioning Based on Hierarchical Clustering and Deep Learning

引用

SN computer science 2025年第4期6卷 1-13页

作者： Rahman, Rizwan Ur Kumar, Pavan Mohan, Aditya Aziz, Rabia Musheer Tomar, Deepak Singh School of Computing Science and Engineering VIT Bhopal University Kothrikalan Sehore 466114 India School of Advanced Science and Languages VIT Bhopal University Kothrikalan Sehore 466114 India Department of CSE and IT Jay Pee University of Information Technology Solan 173234 India State Planning Institute (New Division) Lucknow 226001 India Department of CSE and IT Maulana Azad National Institute of Technology Bhopal 462003 India

The advent of deep learning has brought about significant progress in the field of computer vision, leading to its extensive application in various domains. One of the most important tasks in computer vision is image captioning, which is essential to enable machines to understand and describe visual content in natural language. Applications ranging from improving user experiences in digital media to assistive devices for the blind or visually challenged require this capability. In this paper, we introduce a novel method for accomplishing the image-captioning task with a focus on data reduction through clustering techniques. Our approach aims to maintain or surpass the accuracy achieved by prior studies. Our unique approach uses clustering algorithms to reduce data and addresses the issues of data and computing intensity. It is expected to improve the accuracy and efficiency of picture captioning models. Additionally, we investigate the outcomes of utilizing single long short-term memory (LSTM) as opposed to stacked LSTMs for generating captions. Finally, the MS-COCO benchmark image dataset is used to analyze the performance of proposed approaches, their contributions, and relevance are highlighted, emphasizing the significance of the proposed approach and shedding light on a potential research direction for the image captioning approaches. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks Deep learning Hierarchical clustering Image captioning Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Port-controllable routing of orbital angular momentum modes using a rotatable diffractive neural network

引用

science China(Physics,Mechanics & Astronomy) 2025年第06期Mechanics & Astronomy) .卷 158-167页

作者： Junmin Liu Jiafu Chen Qingji Zeng Zemin Liang Xinping Wu Xin Zhao Jiangnan Xiao Huapeng Ye Ze Dong Dianyuan Fan Shuqing Chen Institute of Microscale Optoelectronics Shenzhen University College of New Materials and New Energies Shenzhen Technology University Terahertz Technology Innovation Research Institute Shanghai Key Laboratory of Modern Optical System Terahertz Science Cooperative Innovation Center School of Optical-Electrical Computer Engineering University of Shanghai for Science and Technology Guangdong Provincial Key Laboratory of Optical Information Materials and Technology & Institute of Electronic Paper Displays South China Academy of Advanced Optoelectronics South China Normal University School of Information and Electronics Beijing Institute of Technology

Orbital angular momentum(OAM) modes provide an additional orthogonal physical dimension, offering transformative potential for enhancing optical communication capacity. Despite significant progress in mode multiplexing, the development of robust communication networks faces persistent challenges, particularly in effectively routing and controlling these multiplexed channels among network nodes. To tackle these dilemmas, we propose a rotatable diffractive neural network(R-DNN) strategy and demonstrate its capability for port-controllable OAM mode routing. By leveraging the correlation between the orthogonal evolution of OAM modes in free space and phase modulations during propagation, the R-DNN precisely shapes the spatial evolution of mode fields through multiple rotatable phase layers, enabling efficient routing to specific output ports. This approach exploits the interaction of secondary wavelets with the relative states of the rotatable layers, allowing on-demand control of mode evolution paths and enhancing routing flexibility. As a proof of concept, we developed a tri-functional router that successfully directs three OAM modes to individually controllable output ports. This router achieves an average intermode crosstalk of less than-16.4 dB across three functional states, one-dimensional, two-dimensional, and cross-connected switching, while supporting the routing of 5.85 Tbit/s quadrature phase-shift keying signals. These results highlight the R-DNN's effectiveness in achieving precise and controllable OAM mode manipulation, paving the way for advanced applications in mode-multiplexed communication networks and beyond.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing ECT Imaging: Residual UNet Deep Neural Network Approach 1st

Advancing ECT Imaging: Residual UNet Deep Neural Network App...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Deabes, Wael Khalifa, Fahmi Abdel-Hakim, Alaa E. Bouazza, Kheir Eddine Computational Engineering Mathematical Sciences Department Texas A&M University SA San AntonioTX78224 United States Electrical and Computer Engineering Department Morgan State University BaltimoreMD21251 United States Computer Science Department in Jamoum Umm Al-Qura University Makkah Saudi Arabia Computer and Information Science Division Higher Colleges of Technology Abu Dhabi United Arab Emirates

ISBN: (纸本)9783031823763

Recently, there has been significant progress in Electrical Capacitance Tomography (ECT) image reconstruction, yet there remains room for enhancing both speed and quality in these reconstructions. Deep Learning (DL) offers a promising avenue due to its capacity to handle intricate nonlinear functions. This study introduces DL-based ECT image reconstruction model based on Residual UNet and termed as ECT_ResUNet. A sizable dataset containing permittivity distribution and corresponding capacitance measurements was created to train and evaluate the proposed model. The ECT_ResUNet processes modulated capacitance vectors, representing them as 66×66 images. The model’s effectiveness and practicality were assessed using unseen samples, demonstrating precise image reconstruction with an average Image Error (IE) of 0.0918 and Correlation Coefficient (CC) of 0.9527. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

CATD: Unified Representation Learning for EEG-To-fMRI Cross-Modal Generation

引用

IEEE Transactions on Medical Imaging 2025年第5期44卷 2283-2294页

作者： Yao, Weiheng Lyu, Zhihan Mahmud, Mufti Zhong, Ning Lei, Baiying Wang, Shuqiang Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China Faculty of Arts Uppsala University Department of Game Design Sweden King Fahd University of Petroleum and Minerals Interdisciplinary Research Center for Biosystems and Machines Department of Information and Computer Science SDAIA-KFUPM Joint Research Center for AI Dhahran Saudi Arabia Maebashi Institute of Technology Faculty of Engineering Maebashi371-0816 Japan Shenzhen University School of Biomedical Engineering Shenzhen518060 China

Multi-modal neuroimaging analysis is crucial for a comprehensive understanding of brain function and pathology, as it allows for the integration of different imaging techniques, thus overcoming the limitations of individual modalities. However, the high costs and limited availability of certain modalities pose significant challenges. To address these issues, this paper proposed the Condition-Aligned Temporal Diffusion (CATD) framework for end-To-end cross-modal synthesis of neuroimaging, enabling the generation of functional magnetic resonance imaging (fMRI)-detected Blood Oxygen Level Dependent (BOLD) signals from more accessible Electroencephalography (EEG) signals. By constructing Conditionally Aligned Block (CAB), heterogeneous neuroimages are aligned into a potential space, achieving a unified representation that provides the foundation for cross-modal transformation in neuroimaging. The combination with the constructed Dynamic Time-Frequency Segmentation (DTFS) module also enables the use of EEG signals to improve the temporal resolution of BOLD signals, thus augmenting the capture of the dynamic details of the brain. Experimental validation demonstrated that the framework improves the accuracy of brain activity state prediction by 9.13% (reaching 69.8%), enhances the diagnostic accuracy of brain disorders by 4.10% (reaching 99.55%), effectively identifies abnormal brain regions, enhancing the temporal resolution of BOLD signals. The proposed framework establishes a new paradigm for cross-modal synthesis of neuroimaging by unifying heterogeneous neuroimaging data into a potential representation space, showing promise in medical applications such as improving Parkinson's disease prediction and identifying abnormal brain regions. © 2025 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Multi-Adulterant Detection in Milk Using an In-house Developed Multiplexed Microfluidic Paper-Based Analytical Device (M-µPAD)

引用

Sensing and Imaging 2025年第1期26卷 1-20页

作者： Ahsan, Jannat Riaz, Kashif Samad, Hudair Mehmood, Muhammad Qasim Khelif, Abdelkrim Department of Electrical Engineering Information Technology University of the Punjab (ITU) Lahore Pakistan Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Advanced Manufacturing Research Centre University of Sheffield Rotherham UK

Milk adulteration poses a significant challenge in developing countries, impacting food safety and public health. This study introduces a multiplexed microfluidic paper-based analytical device (M-µPAD) for rapid and simultaneous detection of multiple milk adulterants. The M-µPAD, fabricated using readily available materials like filter paper and wax crayons, eliminates the need for specialized equipment. The device demonstrates linear relationships between colorimetric response and adulterant concentration for urea (10–200 mg/dL), starch (20-1000 mg/dL), and detergent (100–3000 mg/dL), with detection limits of 11.1, 22.4, and 120.8 mg/dL, respectively. Requiring only 40 µL of reagents and 80 µL of milk sample, the M-µPAD achieves over 95% accuracy and reproducibility with RSD values below 4%. This affordable, in-house fabricated platform offers a promising solution for milk quality assessment in resource-limited settings, addressing the need for accessible and efficient adulterant detection methods.

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：