相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Cristiano Patricio et al.
Summary: This paper introduces an attention-based strategy for feature extraction in zero-shot learning, which improves the performance by incorporating the most salient attributes of the image. Experimental results show that this strategy significantly improves performance on face datasets but degrades performance on classical ZSL datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yuqing Zhang et al.
Summary: In this paper, a novel dual-pathway-fusion-based sequence-to-sequence learning model (DPF-S2S) is proposed for text recognition in the wild. It focuses on enriching spatial information and extracting high-dimensional representation features to aid decoding. The model incorporates a double alignment module to tackle text misalignment and a global fusion module to enhance recognition accuracy in complicated scenes. Benchmark evaluations on seven datasets demonstrate the superiority of DPF-S2S over other state-of-the-art text recognition methods, showcasing its competitiveness in identifying texts in regular and irregular scenes. Ablation studies further validate the effectiveness of the strategies employed in DPF-S2S.
Article
Computer Science, Artificial Intelligence
Haonan Yang et al.
Summary: In this paper, a pyramid structure network combining a convolutional neural network and Swin Transformer is proposed for automatic segmentation of breast tumors. The network improves the performance of breast lesion segmentation by using interactive channel attention and supplementary feature fusion modules, and introduces a boundary detection module to enhance the boundary quality of segmentation results. Experimental results demonstrate the superiority of the network in breast ultrasound lesion segmentation.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jianping Gou et al.
Summary: Knowledge distillation is an effective technique for compressing deep models by transferring knowledge from a large teacher model to a small student model. Existing methods mainly focus on unidirectional knowledge transfer, overlooking the effectiveness of students' self-reflection in real-world education scenarios. To address this, we propose a new framework called MTKD-SSR that enhances the teacher's ability to transfer knowledge and improves the student's capacity to absorb knowledge through self-reflection.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2023)
Article
Biology
Peishu Wu et al.
Summary: In this paper, a novel attention-based glioma grading network (AGGN) oriented towards magnetic resonance imaging (MRI) is proposed. The AGGN utilizes a dual-domain attention mechanism to consider both channel and spatial information for weight assignment. It also incorporates multi-branch convolution, pooling, and multi-modal information fusion modules to extract and merge features from different modalities. Experimental results demonstrate the effectiveness, superiority, high generalization ability, and strong robustness of the proposed AGGN compared to other models, even without manually labeled tumor masks, alleviating the reliance on supervised information.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Yuwen Liu et al.
Summary: The article introduces an attention-based bidirectional gated recurrent unit model for POI category prediction. This method regards users' POI categories as interest preferences, improving the interpretability and prediction accuracy of the model, while simply reflecting user interests.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2022)
Article
Automation & Control Systems
Fanrong Qu et al.
Summary: This paper investigates distributed fusion over sensor networks with probabilistic constraints and stochastic perturbations. A new event-triggering mechanism called TETM is utilized to save bandwidth resources, and a time-varying distributed fusion filter is designed. Global fusion is obtained through recursive linear matrix inequality technique, and local filter parameters are computed by solving an optimization problem. A numerical simulation is used to illustrate the effectiveness of the proposed distributed fusion strategy.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2022)
Article
Automation & Control Systems
Huimin Tao et al.
Summary: This study addresses the problem of H-infinity state estimation for discrete-time memristive neural networks with time-varying delays and randomly occurring denial-of-service attacks. The proposed state estimation method ensures the stability of the error system and meets the desired disturbance attenuation level. Sufficient conditions for solving this problem are established using Lyapunov function and stochastic analysis techniques. The effectiveness of the proposed method is demonstrated through a numerical example.
SYSTEMS SCIENCE & CONTROL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Han Li et al.
Summary: In the context of the global COVID-19 pandemic, a computer aided diagnosis model called Cov-Net is proposed for accurate recognition of COVID-19 from chest X-ray images. Experimental results demonstrate the high feasibility and accuracy of the model in identifying COVID-19. Compared to other algorithms, Cov-Net exhibits superior performance and competitiveness in this task.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Junyi Wu et al.
Summary: This paper proposes an inter attribute aware network via vector-neuron capsule for pedestrian attribute recognition (PAR). By considering the relations between attributes and replacing traditional one-dimensional scalar neurons with two-dimensional vector-neuron capsules, the proposed method achieves better performance and demonstrates its generalization ability on different backbones.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Jun-Jie Hew et al.
Summary: Investment in science and technology is crucial for a country's growth, with computer science research playing a vital role. Despite being geographically close, ASEAN countries exhibit a digital divide in ICT development due to varying research focuses. This study aims to analyze and compare computer science research output among ASEAN countries over the past decade to understand the implications of these differences.
JOURNAL OF COMPUTER INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Shang-Hua Gao et al.
Summary: This paper introduces a novel building block for CNNs, Res2Net, which represents multiscale features within one single residual block by constructing hierarchical residual-like connections. The Res2Net enhances the representation of multiscale features in various vision tasks and consistently outperforms baseline models in performance gains.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Automation & Control Systems
Jun Hu et al.
Summary: This paper discusses the challenges brought by the insertion of communication networks in networked control systems and the role and application of sliding mode control in NCSs. The article summarizes new sliding mode control schemes for issues such as time delays, packet losses, quantization, and uncertainty/disturbance in NCSs, and discusses the introduction of communication protocols for energy saving purposes under scheduling protocols.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Jianping Gou et al.
Summary: This paper provides a comprehensive survey of knowledge distillation, covering knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison, and applications. It also briefly reviews challenges in knowledge distillation and discusses future research directions.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Yang Yang et al.
Summary: The paper introduces a cascaded Split-and-Aggregate Learning (SAL) approach and Feature Recombination (FR) method to enhance the performance of multi-label pedestrian attribute recognition in surveillance tasks.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Review
Automation & Control Systems
Daan Ji et al.
Summary: This paper provides an up-to-date overview of data driven-based fault diagnosis and remaining useful life prediction in the petroleum machinery and equipment (PME) field. It discusses the FD and RUL prediction of five key components using mathematical statistics and shallow learning, as well as surveys four widely-used DL models and their applications in PME. Possible challenges and future research directions are also presented.
SYSTEMS SCIENCE & CONTROL ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Jie Hu et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Computer Science, Information Systems
Lai-Ying Leong et al.
JOURNAL OF COMPUTER INFORMATION SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Dangwei Li et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Artificial Intelligence
Joao Victor Bruneti Severino et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Computer Science, Artificial Intelligence
Zichang Tan et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Artificial Intelligence
Nikolaos Sarafianos et al.
PATTERN RECOGNITION
(2018)
Article
Computer Science, Information Systems
Abrar H. Abdulnabi et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2015)