Article
Computer Science, Information Systems
Pengqing Li, Hongjuan Zhang, Yansong Chen
Summary: In this work, a novel deep features-based structural local sparse low-rank tracker is proposed, which exploits sparsity and low-rank constraint of local patches and considers the spatial structure of target regions. Elegant pre-locating and pruning schemes are developed to maintain the tracker's performance in challenging scenarios, while reducing computational burden. An upgraded effective template update scheme is also designed to adapt to changes in target appearance. Comprehensive experiments on benchmark datasets demonstrate the superiority of the proposed method over popular handcrafted features-based trackers.
MULTIMEDIA SYSTEMS
(2023)
Article
Environmental Sciences
Xiang Chen, Na Chen, Jiangtao Peng, Weiwei Sun
Summary: Hyperspectral image (HSI) classification is a hot research topic in remote sensing. Traditional vector-based spectral-spatial features degrade in performance when the number of labeled samples is limited. To address this, a novel local matrix feature (LMF) is proposed to fully mine discriminative features. This LMF incorporates both the correlation between spectral pixels and the similarity between spectral bands. A Log-Euclidean distance-based linear kernel is then introduced to measure the similarity between the LMFs, and an LMF-based kernel joint sparse representation (LMFKJSR) model is proposed for HSI classification. The LMFKJSR model shows superior results compared to existing methods on three well-known HSI datasets with limited labeled samples.
Article
Engineering, Electrical & Electronic
Shurun Wang, Zhao Wang, Shiqi Wang, Yan Ye
Summary: In this paper, a deep image compression scheme towards machine vision is proposed, which improves the end-to-end image compression with a unified optimization scheme and variable bitrate modules. Experimental results show that the proposed framework achieves state-of-the-art performance in object detection for machine vision.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Environmental Sciences
Houye Yang, Jindong Yu, Zhuo Li, Ze Yu
Summary: In this paper, a novel SAR image despeckling algorithm based on K-SVD is proposed, which achieves better speckle noise suppression and information preservation compared to existing algorithms.
Article
Computer Science, Artificial Intelligence
Hongliang Han, Wei Lu, Fan Feng
Summary: This paper proposes a novel research approach to improve the efficiency of target recognition in SAR images. By applying sparse representation and dictionary learning, a SAR image target recognition model is constructed. The results of experiments validate the effectiveness of the proposed model in improving recognition accuracy.
APPLIED ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Multidisciplinary
Jinzhao Yang, Peter Tse
Summary: This paper discusses a new non-contact vibration measurement method using a high-speed digital camera for structural health monitoring. By combining the multi-scale pyramid decomposition method and sparse representation technique, a new video signal processing method is proposed, which can replace traditional mounted sensors with the advantages of low cost and efficiency.
Article
Engineering, Electrical & Electronic
Hangfan Liu, Jian Zhang, Ruiqin Xiong
Summary: The paper introduces a novel image restoration technique that aims to separately exploit the local and non-local correlations of image contents to achieve near-optimal sparse representations and minimize signal uncertainty. The proposed scheme outperforms existing methods in image denoising, surpassing them with satisfactory results.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2021)
Article
Computer Science, Information Systems
Zhijie Li, Ningde Jin, Xin Wang, Jidong Wei
Summary: An extreme learning machine-based tone reservation scheme is proposed to reduce the PAPR of OFDM system, achieving comparable performance with low complexity compared to other Neural Network-based algorithms. The algorithm shows advantages of fast learning capability and short training length in simulation results.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Yong Yang, Yingmei Zhang, Shuying Huang, Yifan Zuo, Jiancheng Sun
Summary: The proposed method for infrared and visible image fusion achieves the goal of generating a target image through multiscale decomposition, visual saliency sparse representation, and detail injection model. Experimental results show that this method has advantages in preserving detail information and enhancing brightness.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Chemistry, Analytical
Yumei Li, Ningfang Liao, Wenmin Wu, Chenyang Deng, Yasheng Li, Qiumei Fan, Chuanjie Liu
Summary: This study aims to solve the difficulties in displaying high dynamic range (HDR) images on conventional standard display devices. The proposed modified tone-mapping operator (TMO), called iCAM06-m, combines iCAM06 and a multi-scale enhancement algorithm to compensate for saturation and hue drift. Subjective evaluation shows the better performance of iCAM06-m compared to other TMOs, confirming the effectiveness of chroma compensation and multi-scale decomposition. The proposed algorithm overcomes the limitations of other algorithms and is a good candidate for a general purpose TMO.
Article
Geochemistry & Geophysics
Yule Duan, Hong Huang, Yuxiao Tang
Summary: The LC-SMHL algorithm is a novel dimensionality reduction method that can simultaneously discover the manifold-based sparse structure and multivariate discriminant sparse relationship of HSI. By constructing sparse hypergraphs and learning optimal projections, the LC-SMHL method demonstrates better performance in HSI classification.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Xuqin Wei, Yun Shi, Weiyin Gong, Yanyun Guan
Summary: This paper introduces a novel image classification algorithm that uses an improved image representation method to generate virtual samples and designs a weight fusion scheme. The proposed algorithm improves the accuracy of image classification.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Rajkumari Bidyalakshmi Devi, Yambem Jina Chanu, Khumanthem Manglem Singh
Summary: The paper presents an efficient and robust visual object tracking method based on sparse discriminative classifier and principal component analysis. Through comparisons with existing tracking algorithms using both quantitative and qualitative analyses, the proposed method outperforms them.
MULTIMEDIA SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Lin Tian, Jiaqing Miao, Xiaobing Zhou, Chao Wang
Summary: This study introduces an image denoising method based on sparse representation, which utilizes adaptive regularization techniques and outperforms other algorithms in terms of PSNR and visual performance.
IET IMAGE PROCESSING
(2021)
Article
Computer Science, Information Systems
Xiaomei Qin, Yuxi Ban, Peng Wu, Bo Yang, Shan Liu, Lirong Yin, Mingzhe Liu, Wenfeng Zheng
Summary: This paper analyzes the causes of defocusing in a video microscope and proposes a new multi-focus image fusion method based on sparse representation (DWT-SR). By utilizing GPU parallel operation, the algorithm's running time is reduced, resulting in higher image contrast and more detailed representation.
Article
Computer Science, Information Systems
Xiaoyu Zhang, Wei Gao, Ge Li, Qiuping Jiang, Runmin Cong
Summary: Due to the diverse nature of degradation process, recovery of mixed distorted images remains challenging. Training deep learning models for one degradation type leads to significant decline in performance for other degradation types. In this article, we propose a hierarchical toolkit to address the limitations of a single deep network and explore the use of reinforcement learning for efficient restoration of distorted images. Our method accurately captures distortion preferences and achieves quality improvements through exploration using various evaluation methods. Experimental results show significant improvement in peak signal-to-noise ratio compared to state-of-the-art RL-based methods.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Yaozu Kang, Qiuping Jiang, Chongyi Li, Wenqi Ren, Hantao Liu, Pengjun Wang
Summary: This paper proposes a perception-aware decomposition and fusion framework for underwater image enhancement (UIE). Two complementary pre-processed inputs are fused in a perception-aware and conceptually independent image space through a structural patch decomposition and fusion (SPDF) approach. The main advantage of SPDF is that it can fuse different components separately without any interactions and information loss. Comprehensive comparisons demonstrate that SPDF outperforms state-of-the-art UIE algorithms.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Siying Li, Tianwei Zhou, Miaohui Wang, Jingfeng Du, Qiuping Jiang, Wei Gao, Tianfu Wang, Jun Lv
Summary: Automatic and accurate polyp segmentation is a challenging issue. We construct a benchmark dataset and propose a novel adaptive context exploration network (ACENet) which achieves superior performance on multiple evaluation metrics over state-of-the-art methods.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Haoning Wu, Chaofeng Chen, Liang Liao, Jingwen Hou, Wenxiu Sun, Qiong Yan, Weisi Lin
Summary: Compared with existing works, temporal relationships between frames and their influences on video quality assessment (VQA) are relatively under-studied. This study proposes a Transformer-based VQA method to tackle these issues. The method extracts spatial-temporal features and handles temporal quality attention, achieving state-of-the-art performance on multiple benchmarks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Jinguang Cheng, Zongwei Wu, Shuo Wang, Cedric Demonceaux, Qiuping Jiang
Summary: This article introduces a novel organism detection method called BCMNet, which fully utilizes texture and context clues during the encoding and decoding stages, improving the accuracy of locating the target organism object in marine scenes.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Hangwei Chen, Feng Shao, Xiongli Chai, Yuese Gu, Qiuping Jiang, Xiangchao Meng, Yo-Sung Ho
Summary: This paper discusses the important topic of arbitrary neural style transfer, which has significant research value and wide industrial application. The focus is on improving the quality of arbitrary style transfer (AST) and the lack of exploration in quality evaluation of AST images. The paper proposes a new AST images quality assessment database (AST-IQAD) and a sparse representation-based method for measuring the image quality.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Yuxin Feng, Xiaozhe Meng, Fan Zhou, Weisi Lin, Zhuo Su
Summary: This paper proposes a sliding self-attention wavelet network for image haze removal in complex natural haze scenes. The method uses a sliding self-attention module to identify haze regions and uses discrete wavelet transform and inverse transform to construct a hierarchical encoder-decoder structure for gradually recovering sharp edges and precise texture details. Experimental results demonstrate that the proposed algorithm achieves favorable dehazing performance on relevant benchmark datasets.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Hangwei Chen, Feng Shao, Xiongli Chai, Qiuping Jiang, Xiangchao Meng, Yo-Sung Ho
Summary: In this article, a learnable network named CLSAP-Net is proposed to address the perceptual evaluation issue of arbitrary style transfer (AST) images. The network consists of three parts: content preservation estimation network (CPE-Net), style resemblance estimation network (SRE-Net), and OV target network (OVT-Net). Reliable quality factors are generated using self-attention mechanism and joint regression strategy, and the importance weights of factors are manipulated using a novel style-adaptive pooling strategy. Extensive experiments on existing AST image quality assessment (IQA) databases validate the effectiveness and robustness of CLSAP-Net.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Wujie Zhou, Fan Sun, Qiuping Jiang, Runmin Cong, Jenq-Neng Hwang
Summary: In recent years, various neural network architectures such as the visual transformer and multilayer perceptron (MLP) have been developed for computer vision. The transformer, utilizing an attention mechanism, outperforms traditional convolutional neural networks. The MLP, on the other hand, offers stronger generalization by introducing less inductive bias. However, the transformer suffers from significant increase in inference, training, and debugging times. This article proposes the WaveNet architecture for salient object detection in RGB-thermal infrared images, using a vision task-oriented wavelet-based MLP for feature extraction. The knowledge distillation from a transformer and the use of a Kullback-Leibler distance regularization term are also employed.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Chenlei Lv, Weisi Lin, Baoquan Zhao
Summary: In this paper, a two-step intrinsic and isotropic (I&I) resampling framework is proposed to address the major difficulties in point cloud utilization. Experimental results demonstrate that our framework achieves outstanding performance in various applications, including point cloud simplification, mesh reconstruction, and shape registration.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Chenlei Lv, Weisi Lin, Baoquan Zhao
Summary: In this paper, a new registration method called KSS-ICP is proposed for rigid registration in Kendall shape space (KSS) with Iterative Closest Point (ICP). The KSS is a quotient space that removes influences of translations, scales, and rotations for shape feature-based analysis. The KSS-ICP achieves accurate registration from point clouds and outperforms the state-of-the-art.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Information Systems
Jian Jin, Xingxing Zhang, Lili Meng, Weisi Lin, Jie Liang, Huaxiang Zhang, Yao Zhao
Summary: In this paper, an auto-weighted layer representation based view synthesis distortion estimation model is proposed, which calculates sub-synthesis distortion and learns a nonlinear mapping function to obtain the associated weights. It can efficiently and accurately estimate the view synthesis distortion.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Jingwen Hou, Weisi Lin, Guanghui Yue, Weide Liu, Baoquan Zhao
Summary: Personalized image aesthetics assessment aims to estimate aesthetic experiences based on individual preferences. This research proposes a method that directly estimates personalized aesthetic experiences from the interaction between image contents and user preferences, without the need for prior knowledge on generic aesthetics assessment. Extensive experiments show that the proposed method outperforms previous personalized methods and generic methods in terms of both personalized and generic aesthetics assessment.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Geochemistry & Geophysics
Huiwen Wang, Liang Liao, Jing Xiao, Weisi Lin, Mi Wang
Summary: This article proposes an enhanced remote-sensing image compression approach that utilizes uplink assistance to improve compression efficiency. By leveraging historical images from ground stations as reference images for on-orbit compression, spatiotemporal redundancy in remote-sensing images can be effectively eliminated. The proposed dual-end referencing downsampling-based coding framework effectively mitigates fake texture generation and achieves significant bitrate savings compared to standard compression baselines.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Wujie Zhou, Xiaomin Fan, Weiqing Yan, Shengdao Shan, Qiuping Jiang, Jenq-Neng Hwang
Summary: In this study, a lightweight student network framework called GAGNet-S* is proposed, which combines graph attention guidance network and knowledge distillation. This framework distills knowledge from a large teacher network and optimizes an untrained student network with weak labels, achieving semantic segmentation of high-resolution remote sensing images with excellent performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
