Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Siyu Lu et al.
Summary: The Visual Question Answering (VQA) system aims to extract useful information from images related to a given question in order to answer the question accurately. It has a wide range of applications in visual assistance, automated security surveillance, and intelligent robotics-human interaction. However, the accuracy of VQA has been unsatisfactory, mainly due to the limitations in representing scene and object information in image features and fully utilizing text information. This paper proposes the use of multi-scale feature extraction and fusion methods to address these challenges and improve the accuracy of the VQA model. Experimental results demonstrate that the incorporation of multi-scale feature extraction and fusion techniques enhances the performance of the VQA model.
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS
(2023)
Article
Chemistry, Analytical
Shimaa Saber et al.
Summary: This paper presents a novel approach for person re-identification by introducing a multi-part feature network that combines the position attention module (PAM) and the efficient channel attention (ECA). The proposed method outperforms existing state-of-the-art methods on publicly available person re-ID datasets. The results demonstrate the effectiveness and potential of the suggested method in computer vision applications.
Article
Social Sciences, Interdisciplinary
Xuan Liu et al.
Summary: This study proposes three improved feature selection algorithms for Chinese texts and tests their performance on different types of corpora. The experimental results demonstrate that these algorithms can improve the accuracy of text classification.
Article
Computer Science, Information Systems
H. M. Shahzad et al.
Summary: Facial expression recognition (FER) is advancing with the help of multimodal approaches that incorporate data from various modalities, such as voice expressions. This paper proposes a novel multimodal methodology based on deep learning to effectively recognize facial expressions under masked conditions. Experimental evaluations demonstrate that the proposed approach outperforms conventional unimodal methods, achieving an accuracy of 79.81% compared to the unimodal technique's 68.81% accuracy.
Article
Computer Science, Information Systems
Teena Sharma et al.
Summary: This study presents a method for intelligent traffic monitoring using the YOLOv5 model, which allows real-time identification of vehicles, pedestrians, and traffic signals in different weather conditions. The results show that the proposed approach can accurately recognize and track objects on the road in various situations.
Article
Chemistry, Analytical
Hongjun Wu et al.
Summary: Multi-label aerial scene image classification is a challenging problem in remote sensing. We propose a semantic-driven masked attention transformer (S-MAT) method that accurately captures label dependencies and improves classification performance.
Article
Computer Science, Information Systems
Shimaa Saber et al.
Summary: Person re-identification is a method that uses multiple non-overlapping cameras for identification, and it has been successfully applied in computer vision applications. To address issues such as occlusion, illumination changes, and pose changes, a new graph convolutional network with attention modules is proposed. Experimental results demonstrate the high generalization ability and superior performance of the proposed method.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Software Engineering
Yongqi Zhang et al.
Summary: The study proposes an automatic approach to jointly design workspaces and workplans by optimizing performance and workload factors, generating Pareto-optimal design solutions for different work scenarios. Evaluation experiments validate the efficacy of the approach in synthesizing effective workspaces and workplans.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Environmental Sciences
Yakoub Bazi et al.
Summary: This paper proposes a remote-sensing scene-classification method based on vision transformers, which utilize multihead attention mechanisms to establish long-range contextual relationships between pixels in images. The approach involves dividing images into patches, converting them into sequences, and applying data augmentation techniques for improved classification performance. The study also demonstrates the efficacy of compressing the network by pruning half of the layers while maintaining competitive classification accuracies.
Article
Geography, Physical
Yuansheng Hua et al.
Summary: This paper proposes a method for recognizing multiple scenes in a single image by leveraging prototype learning, external memory, and multi-head attention mechanism. Experimental results demonstrate the effectiveness of this approach in aerial scene recognition.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Xinyu Wang et al.
Summary: This article proposes a channel-spatial attention mechanism based on a depthwise separable convolution (CSDS) network for aerial scene classification. Experimental results on three public datasets show that the CSDS network achieves comparable performance to other state-of-the-art methods. Visualization of feature extraction results and ablation experiments demonstrate the powerful feature learning and representation capabilities of the proposed CSDS network.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Nianchang Huang et al.
Summary: The study proposes a novel RGB-D salient object detection model that effectively combines cross-modal features from RGB-D images and unimodal features from RGB and depth images, achieving significant performance improvement on four benchmark datasets compared to state-of-the-art methods.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Sixian Wang et al.
Summary: This study proposes a real-time scene recognition model based on long short-term memory classifiers, utilizing lightweight sensors and a lower sampling rate, significantly reducing recognition latency through a two-stage setting and real-time processing techniques.
Article
Computer Science, Artificial Intelligence
Heng Wang et al.
NEURAL PROCESSING LETTERS
(2020)
Article
Environmental Sciences
Rafael Pires de Lima et al.
Article
Computer Science, Artificial Intelligence
Mouna Afif et al.
NEURAL PROCESSING LETTERS
(2020)
Article
Computer Science, Artificial Intelligence
Lin Xie et al.
PATTERN RECOGNITION
(2020)
Article
Environmental Sciences
Xiaolei Zhao et al.
Article
Chemistry, Multidisciplinary
Biserka Petrovska et al.
APPLIED SCIENCES-BASEL
(2020)
Proceedings Paper
Computer Science, Information Systems
Mayur Dhanaraj et al.
BIG DATA II: LEARNING, ANALYTICS, AND APPLICATIONS
(2020)
Article
Computer Science, Information Systems
Haijiao Xu et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Prajakta Ganesh Pawar et al.
2019 2ND INTERNATIONAL CONFERENCE ON INTELLIGENT COMMUNICATION AND COMPUTATIONAL TECHNIQUES (ICCT)
(2019)
Article
Computer Science, Artificial Intelligence
Gauthier Doquire et al.
Article
Computer Science, Artificial Intelligence
Qinghua Hu et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2011)
Article
Computer Science, Information Systems
T. Guan et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2009)
Review
Computer Science, Artificial Intelligence
Thomas B. Moeslund et al.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2006)
