Article
Computer Science, Artificial Intelligence
Ammar Ul Hassan, Hammad Ahmed, Jaeyoung Choi
Summary: This study introduces a novel method that can synthesize an entire font family instead of just a single font style, addressing the font family synthesis problem. By conditioning on various styles during training, the method can synthesize different styles like regular, bold, italic, and bold-italic.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Gijs van Tulder, Marleen de Bruijne
Summary: Unsupervised domain adaptation is a challenging task in medical image analysis, as it requires matching domains without labeled data. This paper examines the problems and conditions for successful unsupervised domain adaptation. Using experiments with synthetic data, MNIST digits, and medical images, the authors show that the practical success of domain adaptation relies on the existing similarities in the data. Understanding these implicit assumptions is crucial for identifying potential problems and improving the reliability of the results.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Ran Yi, Yong-Jin Liu, Yu-Kun Lai, Paul L. Rosin
Summary: This paper introduces a unique and expressive style of art called face portrait line drawing. To automatically transform face photos into portrait drawings, the authors propose a novel method using unpaired training data and the ability to generate drawings in multiple styles and unseen styles. Through the introduction of a new quality metric and quality loss, the authors address the problem of missing important facial features in existing methods due to information imbalance. Experimental results demonstrate that their method outperforms state-of-the-art methods in portrait drawing generation.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Biochemistry & Molecular Biology
Xihao Chen, Jingya Yu, Shenghua Cheng, Xiebo Geng, Sibo Liu, Wei Han, Junbo Hu, Li Chen, Xiuli Liu, Shaoqun Zeng
Summary: This article proposes an unsupervised method to normalize cytopathology image styles through a two-stage style normalization framework, achieving superior results on six cervical cell datasets from different hospitals and scanners. The method greatly improves the recognition accuracy of lesion cells on unseen cytopathology images, meaningful for model generalization.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2021)
Article
Computer Science, Information Systems
Ziqiang Zheng, Yi Bin, Xiaoou Lv, Yang Wu, Yang Yang, Heng Tao Shen
Summary: The study proposes an asynchronous generative adversarial network called Async-GAN, which addresses the problem of asymmetric unpaired image-to-image translation. It iteratively builds gradually improving intermediate domains to generate pseudo paired training samples, providing stronger full supervision to assist in the translation from the information-poor domain to the information-rich domain.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
Lan Yan, Wenbo Zheng, Chao Gou, Fei-Yue Wang
Summary: This study focuses on the translation from photos to caricatures and proposes an Identity-Preservation Generative Adversarial Network (IPGAN) for unsupervised translation. The model introduces an identity preservation loss to retain the identity information of original photos and improve the quality of generated caricatures. It also uses a style differentiation loss to capture realistic caricature styles that differ from photos. The model utilizes a warp controller to achieve diverse exaggerations without supervision. Experimental results show that IPGAN achieves state-of-the-art performance on the WebCaricature dataset and can generate realistic caricatures while preserving identity.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jin Zhao, Feifei Lee, Chunyan Hu, Hongliu Yu, Qiu Chen
Summary: In this paper, a lightweight domain-attention generative adversarial network (LDA-GAN) is proposed for unpaired image-to-image translation. By introducing an improved domain-attention module and a novel separable-residual block, the generator can focus more on important object regions and retain depth and spatial information, resulting in more realistic images.
Article
Computer Science, Artificial Intelligence
Che-Tsung Lin, Jie-Long Kew, Chee Seng Chan, Shang -Hong Lai, Christopher Zach
Summary: Recent advances in GANs have shown promising results in domain adaptation for object detectors through data augmentation. However, existing methods that preserve objects well in image-to-image translation often require pixel-level annotations or object detectors at test time. This work proposes AugGAN-Det, which utilizes Cycle-object Consistency (CoCo) loss to generate instance-aware translated images across complex domains. The model outperforms previous models in terms of object preservation, instance-level translation, detection accuracy, and visual perceptual quality, without the need for explicit feature alignment or a detector at test time.
PATTERN RECOGNITION
(2023)
Article
Automation & Control Systems
Xiaoqin Zhang, Chenxiang Fan, Zhiheng Xiao, Li Zhao, Huiling Chen, Xiaojun Chang
Summary: The goal of unpaired image-to-image translation is to learn a mapping from a source domain to a target domain without using labeled examples of paired images. Existing algorithms suffer from producing untruthful and lacking detail images. In this article, we propose a random reconstructed unpaired image-to-image translation (RRUIT) framework that incorporates random reconstruction and an adversarial strategy to preserve high-level features and learn the target distribution respectively. Experimental results demonstrate the superiority of RRUIT in photorealistic and artistic stylization.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Physiology
Xindi Wu, Chengkun Li, Xiangrui Zeng, Haocheng Wei, Hong-Wen Deng, Jing Zhang, Min Xu
Summary: Cryo-electron tomography is a revolutionary tool in structural biology for visualizing cellular organelles and macromolecular complexes. The proposed CryoETGAN generative model provides efficient and reliable simulation of Cryo-ET images, outperforming previous methods and maintaining stability.
FRONTIERS IN PHYSIOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Xianfang Zeng, Yusu Pan, Hao Zhang, Mengmeng Wang, Guanzhong Tian, Yong Liu
Summary: The study introduces a novel image translation method, SAAGAN, to address the challenges of unpaired image translation, such as discovering correct semantic-level correspondences between two domains. By jointly learning salient object discovery and translation, the approach achieves a more stable training process and more realistic mapping results.
Article
Biology
Alaa Abu-Srhan, Israa Almallahi, Mohammad A. M. Abushariah, Waleed Mahafza, Omar S. Al-Kadi
Summary: This study introduces a uagGAN model for MR to CT image translation, trained on paired and unpaired datasets with a combination of loss functions to generate fine structure images. The model utilizes attention masks for producing accurate and sharp images, and incorporates knowledge from a non-medical pre-trained model, leading to better performance compared to rival models in quantitative evaluation and qualitative perceptual analysis by radiologists.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Jianxin Lin, Zhibo Chen, Yingce Xia, Sen Liu, Tao Qin, Jiebo Luo
Summary: This article introduces a new image-to-image translation method DosGAN, which utilizes domain supervision information in unpaired data to design a generative adversarial network. Experimental results demonstrate the effectiveness of this method in multiple tasks such as facial attribute, identity, and season translation, and it is able to achieve conditional translation in the CelebA dataset.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Physics, Multidisciplinary
Yuanbin Fu, Jiayi Ma, Xiaojie Guo
Summary: The paper presents a novel deep image-to-image translator EDIT that achieves feature extraction and style transfer through exemplar domain-aware parameter network. Experimental results demonstrate the superiority of EDIT over other state-of-the-art methods both quantitatively and qualitatively.
Article
Computer Science, Artificial Intelligence
Yalan Ye, Ziwei Huang, Tongjie Pan, Jingjing Li, Heng Tao Shen
Summary: The study introduces a new unsupervised domain adaptation method that addresses the current issues by matching the distribution of two domains and reducing the classifier's bias towards source samples. Experimental results demonstrate the effectiveness of the method in unsupervised domain adaptation scenarios.
Article
Computer Science, Information Systems
Hao Tang, Lei Ding, Songsong Wu, Bin Ren, Nicu Sebe, Paolo Rota
Summary: This paper proposes an unsupervised method for key frame extraction by combining convolutional neural network and temporal segment density peaks clustering. The proposed method addresses the issue of imbalance between performance and efficiency in large-scale video classification. Experimental results demonstrate that the proposed strategy achieves competitive performance and efficiency compared with the state-of-the-art approaches.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Mengyi Zhao, Hao Tang, Pan Xie, Shuling Dai, Nicu Sebe, Wei Wang
Summary: Conventional motion prediction methods tend to focus on short-term prediction, leading to freezing forecasting problem where predicted long-term motions become average poses. To address this, we propose a novel Bidirectional Transformer-based Generative Adversarial Network (BiTGAN) for long-term human motion prediction. By utilizing both forward and backward directions, our bidirectional setup ensures consistent and smooth generation. To make full use of history motions, we split them into two parts and use them as encoder and decoder inputs respectively. Additionally, we introduce the soft dynamic time warping (Soft-DTW) loss for better maintaining local and global similarities, and employ a dual-discriminator to distinguish predicted sequences. Experimental results on Human3.6M dataset show that our BiTGAN achieves state-of-the-art performance with a 4% average error reduction for all actions.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Guanglei Yang, Zhun Zhong, Mingli Ding, Nicu Sebe, Elisa Ricci
Summary: In this paper, the authors study source-free domain adaptation and propose the TransDA framework based on Transformer to address the issue of unavailable source data. The framework utilizes attention modules and self-supervised knowledge distillation to improve the model's generalization ability and accuracy.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Hong Liu, Zhun Zhong, Nicu Sebe, Shin'ichi Satoh
Summary: The issue of overfitting in adversarial training has gained attention in the AI and machine learning community. This paper evaluates the performance of several calibration methods on robust models and proposes a regularization method called Self-Residual-Calibration (SRC), which effectively mitigates overfitting while improving robustness. The results show that SRC is complementary to other regularization methods and achieves top performance on the benchmark leaderboard.
ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Interdisciplinary Applications
Cristian Felipe Blanco-Diaz, Cristian David Guerrero-Mendez, Denis Delisle-Rodriguez, Alberto Ferreira de Souza, Claudine Badue, Teodiano Freire Bastos-Filho
Summary: This study proposes a nonlinear neural decoder using an Unscented Kalman Filter (UKF) to infer lower-limb kinematics from EEG signals during pedaling. The results demonstrated maximum decoding accuracy using slow cortical potentials in the delta band (0.1-4 Hz) of 0.33 for Pearson's r-value and 8 for the signal-to-noise ratio (SNR). This opens the door to the development of closed-loop EEG-based BCI systems for kinematic monitoring during pedaling rehabilitation tasks.
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yue Song, Nicu Sebe, Wei Wang
Summary: This paper proposes two more efficient variants, Matrix Taylor Polynomial (MTP) and Matrix Pade Approximants (MPA), to compute the differentiable matrix square root and inverse square root. Numerical tests and real-world applications demonstrate the superior performance and competitive speed of both methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Cristian D. Guerrero-Mendez, Cristian F. Blanco-Diaz, Andres F. Ruiz-Olaya, Alberto Lopez-Delis, Sebastian Jaramillo-Isaza, Rafhael Milanezi Andrade, Alberto Ferreira De Souza, Denis Delisle-Rodriguez, Anselmo Frizera-Neto, Teodiano F. Bastos-Filho
Summary: This study compares the performance of naive BCI users using three different deep learning (DL) methods. The results show that the LSTM-BiLSTM-based approach performs the best, with a 32% improvement compared to baseline methods. It is expected that this study will increase the controllability, usability, and reliability of robotic devices for naive BCI users.
BIOMEDICAL PHYSICS & ENGINEERING EXPRESS
(2023)
Article
Computer Science, Artificial Intelligence
Elia Peruzzo, Willi Menapace, Vidit Goel, Federica Arrigoni, Hao Tang, Xingqian Xu, Arman Chopikyan, Nikita Orlov, Yuxiao Hu, Humphrey Shi, Nicu Sebe, Elisa Ricci
Summary: This paper proposes a novel approach for Interactive Neural Painting, which assists users in creating realistic artworks by suggesting next strokes. The proposed I-Paint method, based on a conditional transformer Variational AutoEncoder (VAE) architecture, shows promising results compared to existing techniques. Additionally, two new datasets are introduced to evaluate and foster further research in this area.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2023)
Article
Engineering, Civil
Jing Wang, Wenjing Li, Fang Li, Jun Zhang, Zhongcheng Wu, Zhun Zhong, Nicu Sebe
Summary: This paper introduces a large-scale and diverse posture-based distracted driver dataset, which includes over 470K images captured by 4 cameras observing 100 drivers from 5 vehicles over 79 hours. The researchers provide a detailed data analysis and present 4 different settings to investigate practical problems of distracted driving, including traditional setting and 3 challenging settings with domain shifts. Through comprehensive experiments, the importance of this dataset is demonstrated, offering new opportunities for further development of distracted driving research.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Nan Pu, Zhun Zhong, Nicu Sebe, Michael S. Lew
Summary: This paper introduces the lifelong person re-identification (LReID) task and proposes a new MEmorizing and GEneralizing (MEGE) framework to prevent forgetting and improve generalization ability. The framework consists of Adaptive Knowledge Accumulation (AKA) and differentiable Ranking Consistency Distillation (RCD) modules. Experimental results demonstrate that the MEGE framework significantly improves performance on both seen and unseen domains.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Yahui Liu, Yajing Chen, Linchao Bao, Nicu Sebe, Bruno Lepri, Marco De Nadai
Summary: Recently, there has been a growing interest in utilizing pre-trained unconditional image generators for image editing, but translating images to multiple visual domains using these methods is still challenging. Existing approaches often fail to preserve the domain-invariant part of the image or handle multiple domains and multi-modal translations. This work proposes an implicit style function (ISF) that enables straightforward multi-modal and multi-domain image-to-image translation using pre-trained unconditional generators. The experiments demonstrate significant improvements over the baselines in manipulating human faces and animal images. The model allows for cost-effective, high-resolution, multi-modal unsupervised image-to-image translations using pre-trained unconditional GANs. The code and data are available at: https://github.com/yhlleo/stylegan-mmuit.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Guofeng Mei, Fabio Poiesi, Cristiano Saltori, Jian Zhang, Elisa Ricci, Nicu Sebe
Summary: This paper proposes a novel overlap-guided probabilistic registration approach that computes the optimal transformation from matched Gaussian Mixture Model (GMM) parameters. The method introduces a Transformer-based detection module to detect overlapping regions and uses GMMs to represent the input point clouds. Experimental results demonstrate that the method outperforms state-of-the-art methods in terms of registration accuracy and efficiency when dealing with point clouds with partial overlap and different densities.
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV)
(2023)
Article
Computer Science, Artificial Intelligence
Yue Song, Nicu Sebe, Wei Wang
Summary: This article investigates how to improve the covariance conditioning by enforcing orthogonality to the Pre-SVD layer, and proposes the Nearest Orthogonal Gradient (NOG) and Optimal Learning Rate (OLR) as methods. Experimental results demonstrate that these methods can simultaneously improve covariance conditioning and generalization, and combining them with orthogonal weight can further boost performance. Additionally, a series of experiments show the benefits of orthogonality techniques for better latent disentanglement in generative models.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Theory & Methods
Juanjuan Weng, Zhiming Luo, Shaozi Li, Nicu Sebe, Zhun Zhong
Summary: This paper investigates the transferability of targeted adversarial examples and finds that the traditional Cross-Entropy (CE) loss function is insufficient. To address this issue, two simple and effective logit calibration methods are proposed to increase transferability.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Review
Computer Science, Artificial Intelligence
Wei Gao, Shuangshuang Ge
Summary: This study provides a comprehensive review of slope stability research based on artificial intelligence methods, focusing on slope stability computation and evaluation. The review covers studies using quasi-physical intelligence methods, simulated evolutionary methods, swarm intelligence methods, hybrid intelligence methods, artificial neural network methods, vector machine methods, and other intelligence methods. The merits, demerits, and state-of-the-art research advancement of these studies are analyzed, and possible research directions for slope stability investigation based on artificial intelligence methods are suggested.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Khuong Le Nguyen, Hoa Thi Trinh, Saeed Banihashemi, Thong M. Pham
Summary: This study investigated the influence of input parameters on the shear strength of RC squat walls and found that ensemble learning models, particularly XGBoost, can effectively predict the shear strength. The axial load had a greater influence than reinforcement ratio, and longitudinal reinforcement had a more significant impact compared to horizontal and vertical reinforcement. The performance of XGBoost model outperforms traditional design models and reducing input features still yields reliable predictions.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Bo Hu, Huiyan Zhang, Xiaoyi Wang, Li Wang, Jiping Xu, Qian Sun, Zhiyao Zhao, Lei Zhang
Summary: A deep hierarchical echo state network (DHESN) is proposed to address the limitations of shallow coupled structures. By using transfer entropy, candidate variables with strong causal relationships are selected and a hierarchical reservoir structure is established to improve prediction accuracy. Simulation results demonstrate that DHESN performs well in predicting algal bloom.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Limin Wang, Lingling Li, Qilong Li, Kuo Li
Summary: This paper discusses the urgency of learning complex multivariate probability distributions due to the increase in data variability and quantity. It introduces a highly scalable classifier called TAN, which utilizes maximum weighted spanning tree (MWST) for graphical modeling. The paper theoretically proves the feasibility of extending one-dependence MWST to model high-dependence relationships and proposes a heuristic search strategy to improve the fitness of the extended topology to data. Experimental results demonstrate that this algorithm achieves a good bias-variance tradeoff and competitive classification performance compared to other high-dependence or ensemble learning algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Zhejing Hu, Gong Chen, Yan Liu, Xiao Ma, Nianhong Guan, Xiaoying Wang
Summary: Anxiety is a prevalent issue and music therapy has been found effective in reducing anxiety. To meet the diverse needs of individuals, a novel model called the spatio-temporal therapeutic music transfer model (StTMTM) is proposed.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Nur Ezlin Zamri, Mohd. Asyraf Mansor, Mohd Shareduwan Mohd Kasihmuddin, Siti Syatirah Sidik, Alyaa Alway, Nurul Atiqah Romli, Yueling Guo, Siti Zulaikha Mohd Jamaludin
Summary: In this study, a hybrid logic mining model was proposed by combining the logic mining approach with the Modified Niche Genetic Algorithm. This model improves the generalizability and storage capacity of the retrieved induced logic. Various modifications were made to address other issues. Experimental results demonstrate that the proposed model outperforms baseline methods in terms of accuracy, precision, specificity, and correlation coefficient.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
David Jacob Kedziora, Tien-Dung Nguyen, Katarzyna Musial, Bogdan Gabrys
Summary: The paper addresses the problem of efficiently optimizing machine learning solutions by reducing the configuration space of ML pipelines and leveraging historical performance. The experiments conducted show that opportunistic/systematic meta-knowledge can improve ML outcomes, and configuration-space culling is optimal when balanced. The utility and impact of meta-knowledge depend on various factors and are crucial for generating informative meta-knowledge bases.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
G. Sophia Jasmine, Rajasekaran Stanislaus, N. Manoj Kumar, Thangamuthu Logeswaran
Summary: In the context of a rapidly expanding electric vehicle market, this research investigates the ideal locations for EV charging stations and capacitors in power grids to enhance voltage stability and reduce power losses. A hybrid approach combining the Fire Hawk Optimizer and Spiking Neural Network is proposed, which shows promising results in improving system performance. The optimization approach has the potential to enhance the stability and efficiency of electric grids.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Zhijiang Wu, Guofeng Ma
Summary: This study proposes a natural language processing-based framework for requirement retrieval and document association, which can help to mine and retrieve documents related to project managers' requirements. The framework analyzes the ontology relevance and emotional preference of requirements. The results show that the framework performs well in terms of iterations and threshold, and there is a significant matching between the retrieved documents and the requirements, which has significant managerial implications for construction safety management.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Yung-Kuan Chan, Chuen-Horng Lin, Yuan-Rong Ben, Ching-Lin Wang, Shu-Chun Yang, Meng-Hsiun Tsai, Shyr-Shen Yu
Summary: This study proposes a novel method for dog identification using nose-print recognition, which can be applied to controlling stray dogs, locating lost pets, and pet insurance verification. The method achieves high recognition accuracy through two-stage segmentation and feature extraction using a genetic algorithm.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Shaohua Song, Elena Tappia, Guang Song, Xianliang Shi, T. C. E. Cheng
Summary: This study aims to optimize supplier selection and demand allocation decisions for omni-channel retailers in order to achieve supply chain resilience. It proposes a two-phase approach that takes into account various factors such as supplier evaluation and demand allocation.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Jinyan Hu, Yanping Jiang
Summary: This paper examines the allocation problem of shared parking spaces considering parking unpunctuality and no-shows. It proposes an effective approach using sample average approximation (SAA) combined with an accelerating Benders decomposition (ABD) algorithm to solve the problem. The numerical experiments demonstrate the significance of supply-demand balance for the operation and user satisfaction of the shared parking system.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Review
Computer Science, Artificial Intelligence
Soroor Motie, Bijan Raahemi
Summary: Financial fraud is a persistent problem in the finance industry, but Graph Neural Networks (GNNs) have emerged as a powerful tool for detecting fraudulent activities. This systematic review provides a comprehensive overview of the current state-of-the-art technologies in using GNNs for financial fraud detection, identifies gaps and limitations in existing research, and suggests potential directions for future research.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Review
Computer Science, Artificial Intelligence
Enhao Ning, Changshuo Wang, Huang Zhang, Xin Ning, Prayag Tiwari
Summary: This review provides a detailed overview of occluded person re-identification methods and conducts a systematic analysis and comparison of existing deep learning-based approaches. It offers important theoretical and practical references for future research in the field.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Jiajun Ma, Songyu Hu, Jianzhong Fu, Gui Chen
Summary: The article presents a novel visual hierarchical attention detector for multi-scale defect location and classification, utilizing texture, semantic, and instance features of defects through a hierarchical attention mechanism, achieving multi-scale defect detection in bearing images with complex backgrounds.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)