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
Mohammadreza Ghorvei et al.
Summary: Unsupervised domain adaptation has been successful in fault diagnosis under changing working conditions, but most methods neglect the geometric structure of the data and the relationship between subdomains. This paper proposes a novel deep subdomain adaptation graph convolution neural network that models the data structure and aligns subdomain distributions using adversarial domain adaptation and local maximum mean discrepancy methods to achieve accurate data-driven models.
Article
Computer Science, Interdisciplinary Applications
Alexandre Bailly et al.
Summary: This study compares the impact of training dataset size and interactions on the performance of machine learning and deep learning models. The results show that machine learning models are less influenced by dataset size but require interaction terms to achieve good performance, while deep learning models can achieve good performance even without interaction terms. Overall, well-specified machine learning models outperform deep learning models.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Harris Papadakis et al.
Summary: This paper provides a review of the research area of collaborative filtering recommender systems and offers a classification based on the tools and techniques employed, allowing readers to gain a quick and comprehensive understanding of this field.
KNOWLEDGE AND INFORMATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yu Chen et al.
Summary: This paper proposes two new strategies for cross-domain few-shot classification, including a precise metric function named FGNN and a hierarchical residual-like block based on multi-scale representation, which significantly improve the classification accuracy of lightweight ResNet structures.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Mohammadreza Kavianpour et al.
Summary: This paper introduces a novel semi-supervised method based on ARMA graph convolution, adversarial adaptation, and multi-layer multi-kernel local maximum mean discrepancy (MK-LMMD) to tackle the challenges in bearing fault diagnosis, such as insufficient labeled data, changing working conditions of the rotary machinery, and missing data.
Article
Computer Science, Artificial Intelligence
Dan Guo et al.
Summary: This paper introduces a context-aware graph (CAG) neural network for visual dialog, which utilizes object-level dialog-historical co-reference nodes for fine-grained relational reasoning. The graph structure is updated iteratively using an adaptive top-K message passing mechanism, and irrelevant relations are eliminated to improve inference efficiency. Additionally, a visual-aware knowledge distillation mechanism is proposed to address the issue of linguistic bias in history. Experimental results demonstrate that both CAG and CAG-Distill outperform comparative methods on the VisDial dataset, and visualization results validate the interpretability of the proposed graph inference solution.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Wenhao Yang et al.
Summary: Human-Object Interaction (HOI) detection aims to infer interactions between humans and related objects in images. Existing graph-based methods overlook the dominant role of humans in HOI and the contribution of object node representations. To tackle these issues, a novel graph-based HOI detection model (iCGPN) is proposed, which models one human node as a central node and enriches node representations through attention mechanism. HOI is inferred using a multi-relation graph convolutional network.
Article
Mathematics, Interdisciplinary Applications
Korab Rrmoku et al.
Summary: This paper presents the implementation of the Naive Bayes classifier to improve the accuracy and trustworthiness of recommendations. The feasibility of the approach is demonstrated by applying it to an online dataset in a social network.
Article
Computer Science, Artificial Intelligence
Kameni Florentin Flambeau Jiechieu et al.
Summary: Skills extraction is crucial for job recommender systems and building skills profiles and knowledge bases. A multi-label classification model based on convolutional neural networks is proposed to predict high-level skills from resumes. Experimental results show the method's effectiveness in extracting implicitly mentioned skills, with a recall rate of 98.79% and precision of 91.34%.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoke Hao et al.
Summary: This paper proposes a hypergraph neural network (Hyper-GNN) for skeleton-based action recognition, capturing spatial-temporal information and high-order dependencies. Local and global structure information is extracted via hyperedge constructions, with hypergraph attention mechanism and improved residual modules for discriminative feature representations. A three-stream Hyper-GNN fusion architecture is adopted for action recognition within the framework, achieving the best performance compared to state-of-the-art methods on benchmark datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Information Systems
Chuan Qin et al.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2020)
Article
Computer Science, Information Systems
Bushra Alhijawi et al.
INFORMATION PROCESSING & MANAGEMENT
(2020)
Article
Computer Science, Artificial Intelligence
Morteza Zihayat et al.
DECISION SUPPORT SYSTEMS
(2019)
Article
Multidisciplinary Sciences
Katy Boerner et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2018)
Review
Computer Science, Artificial Intelligence
John K. Tarus et al.
ARTIFICIAL INTELLIGENCE REVIEW
(2018)
Article
Computer Science, Artificial Intelligence
L Breiman