標(biāo)題: Titlebook: Advanced Intelligent Computing Technology and Applications; 20th International C De-Shuang Huang,Chuanlei Zhang,Wei Chen Conference proceed [打印本頁(yè)] 作者: 皺紋 時(shí)間: 2025-3-21 17:44
書目名稱Advanced Intelligent Computing Technology and Applications影響因子(影響力)
書目名稱Advanced Intelligent Computing Technology and Applications影響因子(影響力)學(xué)科排名
書目名稱Advanced Intelligent Computing Technology and Applications網(wǎng)絡(luò)公開度
書目名稱Advanced Intelligent Computing Technology and Applications網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Advanced Intelligent Computing Technology and Applications被引頻次
書目名稱Advanced Intelligent Computing Technology and Applications被引頻次學(xué)科排名
書目名稱Advanced Intelligent Computing Technology and Applications年度引用
書目名稱Advanced Intelligent Computing Technology and Applications年度引用學(xué)科排名
書目名稱Advanced Intelligent Computing Technology and Applications讀者反饋
書目名稱Advanced Intelligent Computing Technology and Applications讀者反饋學(xué)科排名
作者: 詞匯 時(shí)間: 2025-3-21 21:22 作者: Chauvinistic 時(shí)間: 2025-3-22 02:24
https://doi.org/10.1007/978-981-97-5591-2Swarm Intelligence and Optimization; Neural Networks; Signal Processing; Pattern Recognition; Evolutiona作者: 固執(zhí)點(diǎn)好 時(shí)間: 2025-3-22 08:36
978-981-97-5590-5The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapor作者: finale 時(shí)間: 2025-3-22 09:29
https://doi.org/10.1007/978-3-658-31829-1 detection methods encounter challenges in following aspects: capturing sparsity, nonlinearity, and ensuring the uniqueness of anomalies. To address these issues, this paper introduces an autoencoder framework built upon multi-mode graph attention networks, which models attribute networks using grap作者: defibrillator 時(shí)間: 2025-3-22 14:05 作者: 冒失 時(shí)間: 2025-3-22 20:06 作者: ALT 時(shí)間: 2025-3-23 00:29
,Analyse von Einschwingvorg?ngen,tructures. However, this task is costly and requires significant human effort due to the varying appearance of different concrete materials caused by changing weather conditions and lighting intensities, especially the various uncertain graffiti markings, and the random overlapping of defect types o作者: 輕快走過 時(shí)間: 2025-3-23 03:02
Grundlagen der Elektrotechnik 2h requires substantial computational and memory resources, limiting the deployment of the model on edge devices. In this paper, we analyze the challenges of channel compression in stereo matching models and adopt a straightforward and efficient compression method. Our method focuses on the channel c作者: nauseate 時(shí)間: 2025-3-23 08:47 作者: 性冷淡 時(shí)間: 2025-3-23 12:59
https://doi.org/10.1007/978-3-322-98523-1ng imaging devices struggle to address this issue in real-time. While most efforts leverage deep networks for image deraining and have made progress, their large parameter sizes hinder deployment on resource-constrained devices. Additionally, these data-driven models often produce deterministic resu作者: 全能 時(shí)間: 2025-3-23 15:30 作者: 責(zé)難 時(shí)間: 2025-3-23 21:28
https://doi.org/10.1007/978-3-322-98523-1sed. The purpose of this approach is to reduce the complexity of the hyperbox as well as to eliminate the hyperbox overlap problem. AFMNN consists of four stages, which are input layer, preprocessing layer, hyperbox generation layer and output layer. In preprocessing layer, important features are se作者: HUMP 時(shí)間: 2025-3-23 22:35
https://doi.org/10.1007/978-3-322-98523-1based building change detection method (BFFGNet). Initially, to capture the fine difference features at various scales, the Feature Difference Enhancement (FDE) module is proposed for enhancing interaction of information between the bi-temporal features. Then, for extracting accurate boundary inform作者: 優(yōu)雅 時(shí)間: 2025-3-24 03:45 作者: dendrites 時(shí)間: 2025-3-24 09:16
https://doi.org/10.1007/978-3-322-98523-1t and grassland environments—such as a wide variety of species, color similarity to the background, small inter-class variability, and large intra-class variability—an improved lightweight target detection model, Pest-YOLO, is proposed. This model addresses the deficiencies of traditional models in 作者: 催眠藥 時(shí)間: 2025-3-24 10:40 作者: MOAT 時(shí)間: 2025-3-24 17:44 作者: 變形 時(shí)間: 2025-3-24 21:27
Elektrischer Leitungsmechanismus,speech enhancement. However, there remain considerable difficulties for neural networks to improve speech quality. Firstly, existing methods have the problem of speech over-suppression. Because they have not yet taken into account that neural networks influence not only background noise but also cle作者: Alcove 時(shí)間: 2025-3-25 01:29
Elektrischer Leitungsmechanismus,irs of events within a sentence. Existing models for extracting temporal relations treat it as a supervised classification task with Generative Pre-trained Transformer (GPT). However, due to the complexity of annotation, most models face the challenge of insufficient labeled data. Furthermore, the c作者: inundate 時(shí)間: 2025-3-25 06:17
https://doi.org/10.1007/978-3-662-00854-6d on aligning the global distributions of the source and target domains. In this paper, we introduce a subclass domain adaptive network (CASAN) that integrates the Large Margin Cosine Loss and Additive Angular Margin Loss to enhance domain-adaptive classification in scenarios where image quality var作者: PATHY 時(shí)間: 2025-3-25 08:02 作者: PHONE 時(shí)間: 2025-3-25 14:43
https://doi.org/10.1007/978-3-658-31829-1quired node embeddings to rebuild both the topology and node attributes of the attribute network. Finally, anomaly detection is conducted by evaluating the reconstruction errors of attributes and structures. The experimental results on three attribute network datasets demonstrate the framework’s effectiveness.作者: –scent 時(shí)間: 2025-3-25 17:09
https://doi.org/10.1007/978-3-322-98523-1gression tasks. By integrating these components, our model effectively reduces feature loss in tiny object detection, achieving outstanding results on three aerial datasets: AI-TOD, VisDrone2019, and RSOD. Comparative evaluations against baselines and other detection models demonstrate the superior performance of our approach.作者: Incisor 時(shí)間: 2025-3-25 22:35
Grundlagen der Elektrotechnik Iwo parallel convolutional neural network branches. Then, it employs an attention mechanism to weigh the local features of a person, emphasizing regions which are more critical for identification. Finally, the global and weighted local features are fused to obtain the final representation of the person.作者: 返老還童 時(shí)間: 2025-3-26 02:13 作者: 妨礙 時(shí)間: 2025-3-26 04:27 作者: filicide 時(shí)間: 2025-3-26 10:22 作者: textile 時(shí)間: 2025-3-26 14:05 作者: ARCH 時(shí)間: 2025-3-26 19:21 作者: Insubordinate 時(shí)間: 2025-3-26 23:30 作者: cogent 時(shí)間: 2025-3-27 02:48
0302-9743 4882 - the refereed proceedings of the 20th International Conference on Intelligent Computing, ICIC 2024, held in Tianjin, China, during August 5-8, 2024...The total of 863 regular papers were carefully reviewed and selected from 2189 submissions...This year, the conference concentrated mainly on th作者: HIKE 時(shí)間: 2025-3-27 06:09
https://doi.org/10.1007/978-3-662-00854-6lass domain distribution matching loss, is proposed to better align the features of different domains in the high-dimensional space. Experiments are conducted on three benchmark datasets to compare our model with other mainstream models, and the results achieve higher accuracy.作者: 令人作嘔 時(shí)間: 2025-3-27 11:13 作者: 空氣 時(shí)間: 2025-3-27 15:47 作者: grotto 時(shí)間: 2025-3-27 19:01
Multi-mode Graph Attention-Based Anomaly Detection on Attributed Networks detection methods encounter challenges in following aspects: capturing sparsity, nonlinearity, and ensuring the uniqueness of anomalies. To address these issues, this paper introduces an autoencoder framework built upon multi-mode graph attention networks, which models attribute networks using grap作者: Annotate 時(shí)間: 2025-3-27 22:12
A Hierarchical Multi-scale Cortical Learning Algorithm for Time Series Forecastingct temporal dependencies of time series, it ignores the characteristics of the data and can’t deal with the intricate temporal patterns within the sequence. Multi-scale information is crucial for modeling time series, but is not fully studied in the CLA. To this end, we propose a Hierarchical Multi-作者: nerve-sparing 時(shí)間: 2025-3-28 05:44 作者: 厚顏 時(shí)間: 2025-3-28 07:22 作者: 行為 時(shí)間: 2025-3-28 10:37 作者: 破布 時(shí)間: 2025-3-28 18:28
Designing Real-Time Neural Networks by Efficient Neural Architecture Searchhe critical nature of these systems, the ability of CNNs to meet stringent timing constraints is as crucial as their accuracy. However, variability in CNN execution times can lead to time constraint violations, affecting system reliability. To address this, we introduce RetNAS, an efficient neural a作者: 類人猿 時(shí)間: 2025-3-28 20:08
Uncertainty-Driven Multi-scale Feature Fusion Network for Real-Time Image Derainingng imaging devices struggle to address this issue in real-time. While most efforts leverage deep networks for image deraining and have made progress, their large parameter sizes hinder deployment on resource-constrained devices. Additionally, these data-driven models often produce deterministic resu作者: Assignment 時(shí)間: 2025-3-29 00:53
RAY-Net: A Motorcycle Helmet Detection Method Integrated Auxiliary Correctionsignificant task. However, this field currently faces two major challenges. Firstly, there is a lack of a comprehensive open-source dataset that encompasses challenging scenarios such as nighttime and rainy days. Secondly, the detection of motorcycles in motion is often disrupted by pedestrians and 作者: Rankle 時(shí)間: 2025-3-29 03:16
Augmented Fuzzy Min-Max Neural Network Driven to Preprocessing Techniques and Space Search Optimizatsed. The purpose of this approach is to reduce the complexity of the hyperbox as well as to eliminate the hyperbox overlap problem. AFMNN consists of four stages, which are input layer, preprocessing layer, hyperbox generation layer and output layer. In preprocessing layer, important features are se作者: 永久 時(shí)間: 2025-3-29 10:42
Building Change Detection Based on Fully Convolutional Network in High-Resolution Remote Sensing Imabased building change detection method (BFFGNet). Initially, to capture the fine difference features at various scales, the Feature Difference Enhancement (FDE) module is proposed for enhancing interaction of information between the bi-temporal features. Then, for extracting accurate boundary inform作者: Foment 時(shí)間: 2025-3-29 11:36
Optimization of NUMA Aware DNN Computing Systemltaneous memory accesses facilitated by independent multiple processors. However, the efficacy of extensive computational tasks, including those in the realm of AI, hinges on the implementation of intricate memory allocation strategies within this framework. Consider the Linux operating system, wher作者: 強(qiáng)有力 時(shí)間: 2025-3-29 16:35 作者: 得意牛 時(shí)間: 2025-3-29 21:03 作者: 蛙鳴聲 時(shí)間: 2025-3-30 03:56 作者: Comedienne 時(shí)間: 2025-3-30 04:59 作者: Conscientious 時(shí)間: 2025-3-30 11:23
Prompt-Based Event Temporal Relation Extraction with Contrastive Learningirs of events within a sentence. Existing models for extracting temporal relations treat it as a supervised classification task with Generative Pre-trained Transformer (GPT). However, due to the complexity of annotation, most models face the challenge of insufficient labeled data. Furthermore, the c作者: 言行自由 時(shí)間: 2025-3-30 14:14 作者: Mhc-Molecule 時(shí)間: 2025-3-30 17:05 作者: Assemble 時(shí)間: 2025-3-30 22:09 作者: EXULT 時(shí)間: 2025-3-31 01:26 作者: CESS 時(shí)間: 2025-3-31 07:54 作者: Contend 時(shí)間: 2025-3-31 09:47
Multi-label Classification for Concrete Defects Based on EfficientNetV2Spatial Pyramid Pooling Fast (SPPF), to extract defect-representative features from concrete defect images based on EfficientNetV2. Among them, SCARM contributes to assisting the network focus on crucial features and suppressing unnecessary ones and SPPF used to aggregate multi-scale features to add作者: relieve 時(shí)間: 2025-3-31 14:24 作者: 宣稱 時(shí)間: 2025-3-31 19:23
Designing Real-Time Neural Networks by Efficient Neural Architecture Searchch efficiency and achieves a success rate of approximately 99.2% in meeting time constraints, outperforming other methods. Our experiments also show that CNNs designed by RetNAS surpass the accuracy of manually designed CNNs and visual transformers by 0.4% to 5%.作者: Spina-Bifida 時(shí)間: 2025-4-1 00:53 作者: 先鋒派 時(shí)間: 2025-4-1 03:18 作者: 過渡時(shí)期 時(shí)間: 2025-4-1 06:40 作者: 指令 時(shí)間: 2025-4-1 13:39
Building Change Detection Based on Fully Convolutional Network in High-Resolution Remote Sensing Imainformation for directing the distinct level feature integration using the Change Guide Module (CGM), which enhances model‘s capacity to identify complete buildings and small targets. To demonstrate the model‘s effectiveness, it was tested on two large remote sensing building change detection datase作者: 嬰兒 時(shí)間: 2025-4-1 15:10
