检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Yingge Dai, Dawei Zhou, Kenan Tan, Xiufang Wu, Yiqiao Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

In the context of fine-grained sketch-based image retrieval (FG-SBIR) framework, sketch drawing is a time-consuming and skill-intensive process that greatly restricts its practical application. Our study aims to enhance the early-stage retrieval efficiency by utilizing partial sketches with a minimum number of strokes in the on-the-fly FG-SBIR framework. Nevertheless, partial sketches with few strokes usually lack global information and consist only of sparse local details. This lack of detail results in ambiguous semantic content and indistinct differences among images, which consequently impairs early-stage retrieval. To acquire an efficient representation for these sketches, we propose a multi-granularity feature representation model that utilizes prior knowledge embedding to deal with the sketch drawing process. In the first stage,we design a triplet network to learn the joint a coarse representation embedding space that is common between the complete sketch and the image. In the second stage, We enhanced the semantic representation of sketches by utilizing prior knowledge, which aids in supplementing missing fine-grained features. This was achieved by formalizing the prior knowledge and integrating it into the feature vector obtained in the initial stage, thereby acquiring the final representation of a subset of sketches. Experiments conducted on two public datasets indicate that our method outperforms the state-of-the-art baseline during the early retrieval phase. In practical applications, our approach has also achieved good results. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Granular-ball Representation Learning for Deep CNN on Learning with Label Noise

arXiv

引用

arXiv 2024年

作者： Dai, Dawei Zhu, Hao Xia, Shuyin Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

In actual scenarios, whether manually or automatically annotated, label noise is inevitably generated in the training data, which can affect the effectiveness of deep CNN models. The popular solutions require data cleaning or designing additional optimizations to punish the data with mislabeled data, thereby enhancing the robustness of models. However, these methods come at the cost of weakening or even losing some data during the training process. As we know, content is the inherent attribute of an image that does not change with changes in annotations. In this study, we propose a general granular-ball computing (GBC) module that can be embedded into a CNN model, where the classifier finally predicts the label of granular-ball (gb) samples instead of each individual samples. Specifically, considering the classification task: (1) in forward process, we split the input samples as gb samples at feature-level, each of which can correspond to multiple samples with varying numbers and share one single label;(2) during the backpropagation process, we modify the gradient allocation strategy of the GBC module to enable it to propagate normally;and (3) we develop an experience replay policy to ensure the stability of the training process. Experiments demonstrate that the proposed method can improve the robustness of CNN models with no additional data or optimization. Copyright © 2024, The Authors. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 1177-1189页

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi'An Jiaotong School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi'an710049 China Xi'An Jiaotong School of Computer Science and Technology Shaanxi Xi'an710049 China BigKEJoint Innovation Center SHMEEA Shanghai China Xi'An Jiaotong University School of Mathematics and Statistics Xi'an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Leverage Learning Behaviour data for Students' Learning Performance Prediction and Influence Factor Analysis

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2422-2433页

作者： Ni, Qin Zhu, Yanjin Zhang, Lingying Lu, Xiaochen Zhang, Lei Shanghai International Studies University Key Laboratory of Multilingual Education with AI Shanghai201620 China Donghua University College of Information Science and Technology Shanghai201620 China Donghua University Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China Shanghai Normal University Shanghai Engineering Research Center of Intelligent Education and Bigdata and Lab for Educational Big Data and Policymaking Shanghai200234 China

Online education has become increasingly significant for university students and faculty, especially in the context of the modern remote education landscape. However, the inherent space-time separation in online education can create communication delays between teachers and students, making it challenging to monitor students' behaviors effectively. In an effort to understand the connection between students' online engagement and their learning performance, data annotation has been implemented to address the issue of accurately representing students' learning behaviors. Taking the online teaching data of Shanghai Normal University platform as the research object, the primary online education problem is explored through data mining, which includes correlation analysis, Gini importance ranking, and principal component analysis (PCA). Then, constructing the learning performance prediction model using random forest (RF) based on PCA by comparing various machine learning algorithms. As a consequence, the most influential online learning behaviors are course duration time, document learning time, test average score, and video completion rate. The overall classification accuracy of the learning performance prediction model is 87.45%, and the highest prediction accuracy for a single category is 96.52%. © 2020 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Federated Hybrid-Supervised Learning for Universal Medical Image Segmentation

Federated Hybrid-Supervised Learning for Universal Medical I...

引用

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

作者： Zheng, Shenhai Wen, Sian Li, Congyu Chen, Qing Li, Laquan College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China School of Science Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9798350368741

Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://***/TrivenDev/FedSLAG. © 2025 IEEE.

关键词： federated learning hybrid-supervised learning medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatial Consistency and Feature Diversity Regularization in Transfer Learning for Fine-Grained Visual Categorization

Spatial Consistency and Feature Diversity Regularization in ...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Dai, Zhigang Chen, Junying Mian, Ajmal South China University of Technology Key Laboratory of Big Data and Intelligent Robot Ministry of Education School of Software Engineering Guangzhou China The University of Western Australia Department of Computer Science Perth Australia

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Fine-grained visual categorization is challenged by limited training data by localizing discriminative regions and learning diverse features. We propose an effective regularization method that simultaneously imposes spatial consistency and feature diversity on CNN feature maps from a unified perspective. The former guides different feature map channels to concentrate collaboratively on the discriminative areas while the latter ensures that the feature maps are diverse. The proposed method does not require additional supervision, and leverages the covariance matrix of multi-channel feature maps to regularize the loss at the last convolutional layer where the semantic information is the richest. This allows the influence to be backpropagated to update all convolutional layers. We perform experiments using four network architectures for transfer learning from two source domains to three target domains, and demonstrate that our regularization method improves accuracy in all different settings. The proposed regularization method achieves state-of-the-art performance on CUB-200-2011, Stanford-Cars, and Stanford-Dogs datasets with 89.8%, 94.6%, and 88.5% accuracy, respectively. © 2022 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of fire alarm module for smart home

Design and implementation of fire alarm module for smart hom...

引用

2023 International Conference on Electronic Information Engineering and data Processing, EIEDP 2023

作者： Liu, Xiaohong Yan, Kai College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650224 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan430081 China

ISBN: (纸本)9781510666160

With the continuous development of information technology, artificial intelligence fire automatic alarm system is gradually developed. However, the current system is based on a single sensor for identification, when a fire still uses manual active fire extinguishing, low efficiency in handling fire, high failure rate, poor system scalability, poor anti-interference ability, high false alarm rate. At the same time, the recognition accuracy is low, the processing speed and intelligence are also insufficient. Therefore. To address the above problems, this study designs a multi-sensor artificial intelligence fire prevention system using smoke and temperature sensors. The fire prevention system can send alarm signals at the earliest stage of fire and can intelligently extinguish the fire, so that the disaster can be controlled and extinguished by taking measures in advance. Meanwhile, the system can continue to work even if one of the sensors is not working properly. © 2023 SPIE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation

arXiv

引用

arXiv 2024年

作者： Yuan, Li Cai, Yi Ren, Haopeng Wang, Jiexin School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

Generating coherent and credible explanations remains a significant challenge in the field of AI. In recent years, researchers have delved into the utilization of entailment trees to depict explanations, which exhibits a reasoning process of how a hypothesis is deduced from the supporting facts. However, existing models often overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees. To address this limitation, we propose the logical pattern memory pre-trained model (LMPM). LMPM incorporates an external memory structure to learn and store the latent representations of logical patterns, which aids in generating logically consistent conclusions. Furthermore, to mitigate the influence of logically irrelevant domain knowledge in the Wikipedia-based data, we introduce an entity abstraction approach to construct the dataset for pre-training LMPM. The experimental results highlight the effectiveness of our approach in improving the quality of entailment tree generation. By leveraging logical entailment patterns, our model produces more coherent and reasonable conclusions that closely align with the underlying premises. Code and data are released at https://***/YuanLi95/T5-LMPM. © 2024, CC BY-NC-ND.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation

KAN-Face: Efficient Resource Usage and Precision Lip-Sync in...

引用

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

作者： Feng, Guanwen Jin, Siyu Qian, Zhihao Li, Yunan Miao, Qiguang School of Computer Science and Technology Xidian University Shaanxi Xi'an710071 China Xi'an Key Laboratory of Big Data and Intelligent Vision Xidian University Shaanxi Xi'an710071 China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi'an710071 China

ISBN: (纸本)9798350368741

Despite significant progress in NeRF-based talking head generation, problems like poor lip synchronization and inefficient resource usage remain. To solve these, we propose KAN-Face, a lightweight framework. In preprocessing, we introduce a Lip-Sync Enhancement Module that uses Wav2Lip to extract high-resolution audio features and map them to an explicit intermediate representation, ensuring precise lip movement alignment with the speaker's identity. These predicted lip-sync features are combined with fundamental audio-extracted lip features and injected into the rendering module to improve synchronization. For rendering, we introduce FastKAN to map spatial points to color values. As a variant of KAN, FastKAN's sensitivity to 3D scenes and efficient structure enable precise, fast color prediction. Our framework reduces resource consumption while enhancing lip-sync accuracy and facial reconstruction, making it ideal for talking head generation tasks in resource-limited settings. Project: https://***/KAN-Face/. © 2025 IEEE.

关键词： Face Animation KAN Network Low Resource Neural Radiance Fields Talking Head Generation

来源：评论

学校读者我要写书评

暂无评论

Multi-Granular Genetic Algorithm Based Task Allocation for Heterogeneous UAVs

Multi-Granular Genetic Algorithm Based Task Allocation for H...

引用

International Conference on big data and Information Analytics (bigDIA)

作者： Jiajia Cao Guoyin Wang Qun Liu Haihuan Jiang Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

The unmanned aerial vehicles (UAVs) cooperative multi-task allocation systems have been widely used in recent years in areas such as land aerial photography, transportation of materials in disaster areas and so on. With the increase of the complex relationship between the mission and the UAV, it is difficult for genetic algorithm to find the global optimal solution in the search process. This paper proposes a new Multi-Granular Genetic Algorithm (MGGA) to solve the UAV cooperative multi-task allocation problem (CMTAP), accounting for multiple constraints in real scenarios. To enhance the quality of the initial population of genetic algorithm, a data preprocessing method via a typical clustering algorithm is proposed at first. Aiming to improve the solution speed of the standard genetic algorithm, MGGA incorporates the concept of Multi-Granular Cognition and combines granular-ball computing with the genetic algorithm to solve the CMTAP. Finally, through simulation experiments in different scenarios, the algorithm is proved to have better optimization ability and convergence effect.

关键词： Computational modeling data preprocessing Clustering algorithms Transportation System recovery Autonomous aerial vehicles Multitasking Resource management Standards Genetic algorithms

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：