Article
Engineering, Civil
Guisik Kim, Junseok Kwon
Summary: A novel dehazing framework is proposed in this paper for real-world images containing hazy and low-light areas, which unifies dehazing and low-light enhancements using an illumination map estimated by a convolutional neural network. Experimental results show that the method outperforms state-of-the-art algorithms in real-world image dehazing in both quantitative and qualitative terms.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Feifan Lv, Yu Li, Feng Lu
Summary: Low-light image enhancement is a challenging task that involves not only brightness recovery, but also addressing issues like color distortion and noise. The proposed method utilizes attention maps to guide brightness enhancement and denoising tasks, resulting in high fidelity enhancement results for low-light images.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Software Engineering
Chongchong Yu, Shunan Li, Wenbin Feng, Tong Zheng, Shu Liu
Summary: Visible-infrared image fusion can reveal features and combine information, enhancing scene detection. In low-light conditions, the proposed infrared and visible image fusion architecture based on self- and cross-attention (SACA-Fusion) outperforms traditional methods by using a transformer-based fusion network. It extracts long-range dependencies and improves space recovery of fused images.
Article
Automation & Control Systems
Xufeng He, Zhihua Chen, Lei Dai, Lei Liang, Jianfa Wu, Bin Sheng
Summary: In this study, a global-and-local aware network (GLAN) is proposed to address the complex and unpredictable degradation in nighttime or backlit photos. By projecting features into the frequency domain and incorporating them in a knowledge-sharing manner, GLAN effectively integrates global modeling capability and local sensitivity to represent structure and texture. The method achieves competitive results through feature extraction, multi-scale feature construction, adaptive multi-scale feature block, multi-scale channel attention module, pixel attention module, and frequency-aware interaction module.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Mathematics
Seng Chun Hoo, Haidi Ibrahim, Shahrel Azmin Suandi, Theam Foo Ng
Summary: Inspired by the human visual system, attention modules recalibrate the weights of channel and spatial features to prioritize informative regions in a scene. LCAM, a lightweight attention mechanism with three parallel branches, achieves comparable or even better results in face recognition tasks.
Article
Computer Science, Artificial Intelligence
Xiaoling Zhou, Zetao Jiang, Idowu Paul Okuwobi
Summary: In this paper, a novel cross-attention fusion network (CAFNET) is proposed to fuse infrared and low illumination visible-light images. By extracting features using the first layer of pre-trained VGG16 network, calculating cross attention and spatial attention, and modulating the weight maps for fusion, as well as performing details injection, the proposed method achieves better performance in both subjective and objective evaluations compared to traditional multi-scale and state-of-the-art deep learning-based fusion methods.
NEURAL PROCESSING LETTERS
(2023)
Article
Computer Science, Information Systems
Jingzhao Xu, Mengke Yuan, Dong-Ming Yan, Tieru Wu
Summary: In this study, we propose an illumination guided attentive wavelet network (IGAWN) for low-light image enhancement. By integrating attention mechanisms with wavelet transform, noise can be effectively suppressed and desired content can be enhanced. Moreover, by extracting illumination information and utilizing frequency feature transform, image enhancement performance under extremely low-light conditions can be significantly improved.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Physics, Multidisciplinary
Wenshuo Yu, Liquan Zhao, Tie Zhong
Summary: This paper proposes a novel generative adversarial network to enhance low-light image quality. The proposed method consists of a generator with residual modules, hybrid attention modules, and parallel dilated convolution modules, a discriminator to improve the discrimination ability, and an improved loss function incorporating pixel loss. Experimental results show that the proposed method outperforms seven other methods in enhancing low-light images.
Article
Engineering, Electrical & Electronic
Praveen Kandula, Maitreya Suin, A. N. Rajagopalan
Summary: In this paper, an unsupervised low-light enhancement network using context-guided illumination-adaptive norm (CIN) is proposed. The network consists of two stages: the first stage uses a pixel amplifier module (PAM) to generate a coarse estimate, improving visibility and aesthetic quality, while the second stage enhances the image using CIN. A region-adaptive single input multiple output (SIMO) model is also introduced to generate multiple enhanced images for users to choose from. The experimental results show that the proposed model outperforms previous methods quantitatively and qualitatively.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Pengyue Li, Xiai Chen, Jiandong Tian, Yandong Tang
Summary: In this study, we propose a progressive feature-aware recurrent network that separates the enhancement task of low-light images into domain-specific subtasks to restore the illumination and color information gradually. Experimental results show that our method outperforms other methods on public low-light image datasets.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2023)
Article
Computer Science, Artificial Intelligence
Saeed Amirgholipour, Wenjing Jia, Lei Liu, Xiaochen Fan, Dadong Wang, Xiangjian He
Summary: This paper proposes a novel Pyramid Density-Aware Attention based network, PDANet, for density-aware crowd counting. By leveraging attention, pyramid scale feature, and two branch decoder modules, PDANet aims to extract features of different scales while focusing on relevant information and suppressing misleading information. It addresses the variation of crowdedness levels among different images with a Density-Aware Decoder (DAD) modules and achieves superior performance in accurate counting and generated density maps.
Article
Energy & Fuels
Jian Yu, Peris Sunny Leonard, Depeng Qiu, Yilin Zhao, Andreas Lambertz, Christoph Zahren, Lauterbach Volker, Weiyuan Duan, Junsheng Yu, Kaining Ding
Summary: This study evaluated the light soaking stress on glass/back sheet structure modules with different encapsulant materials and found that the SHJ solar modules with different encapsulant materials showed excellent light induced reliability. The LID-free SHJ solar cells have the potential to reduce the levelized cost of energy for photovoltaic power generation.
SOLAR ENERGY MATERIALS AND SOLAR CELLS
(2022)
Article
Computer Science, Software Engineering
Nana Yu, Jinjiang Li, Zhen Hua
Summary: In this study, we propose a multi-stage modular network called FLA-Net for low-light image enhancement. The method addresses the challenges associated with enhancing low-light images through feature extraction, feature aggregation, and image enhancement stages. Experimental results show that our method outperforms existing methods in terms of both subjective visual quality and objective evaluation indicators.
Article
Chemistry, Multidisciplinary
Shuwei Wu, Zhenbing Liu, Haoxiang Lu, Yingxing Huang
Summary: Recently, object detection has achieved significant success on images with normal illumination levels. However, the accuracy of object detection is diminished in suboptimal environments due to noise and low contrast. To improve object detection under low-illumination conditions, three modules are proposed: the low-level feature attention (LFA) module, the feature fusion neck (FFN), and the context-spatial decoupling head (CSDH). Experiments demonstrate the good performance of our end-to-end detection algorithm on low-illumination images.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Analytical
Wencai Xu, Jie Hu, Ruinan Chen, Yongpeng An, Zongquan Xiong, Han Liu
Summary: In this study, a novel single-stage object detector called keypoint-aware single-stage 3D object detector (KASSD) is proposed. By designing a lightweight location attention module and a keypoint-aware module, the method achieves high accuracy while maintaining low latency for object detection.
Article
Computer Science, Artificial Intelligence
Yongrong Zheng, Tao Zhang, Ying Fu
Summary: Flowers have significant value in our lives, and the HFD100 dataset of hyperspectral flower images plays an important role in flower classification and spectral analysis research.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)