检索结果-内蒙古大学图书馆

Aesthetically Relevant Image Captioning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhong, Zhipeng Zhou, Fei Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Peng Cheng National Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Institute for Artificial Intelligence and Robotics for Society China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen China School of Computer Science The University of Nottingham United Kingdom

Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image AQA and IAC together and present a new IAC method termed Aesthetically Relevant Image Captioning (ARIC). Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS. We then use the ARS to design the ARIC model which includes an ARS weighted IAC loss function and an ARS based diverse aesthetic caption selector (DACS). We present extensive experimental results to show the soundness of the ARS concept and the effectiveness of the ARIC model by demonstrating that texts with higher ARS’s can predict the aesthetic ratings more accurately and that the new ARIC model can generate more accurate, aesthetically more relevant and more diverse image captions. Furthermore, a large new research database containing 510K images with over 5 million comments and 350K aesthetic scores, and code for implementing ARIC are available at https://***/PengZai/ARIC. © 2022, CC BY-NC-ND.

关键词：

Universal deep network for steganalysis of color image based on channel representation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wei, Kangkang Luo, Weiqi Tan, Shunquan Huang, Jiwu The Guangdong Key Lab of Information Security Technology School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Up to now, most existing steganalytic methods are designed for grayscale images, and they are not suitable for color images that are widely used in current social networks. In this paper, we design a universal color image steganalysis network (called UCNet) in spatial and JPEG domains. The proposed method includes preprocessing, convolutional, and classification modules. To preserve the steganographic artifacts in each color channel, in preprocessing module, we firstly separate the input image into three channels according to the corresponding embedding spaces (i.e. RGB for spatial steganography and YCbCr for JPEG steganography), and then extract the image residuals with 62 fixed high-pass filters, finally concatenate all truncated residuals for subsequent analysis rather than adding them together with normal convolution like existing CNN-based steganalyzers. To accelerate the network convergence and effectively reduce the number of parameters, in convolutional module, we carefully design three types of layers with different shortcut connections and group convolution structures to further learn high-level steganalytic features. In classification module, we employ a global average pooling and fully connected layer for classification. We conduct extensive experiments on ALASKA II to demonstrate that the proposed method can achieve state-of-the-art results compared with the modern CNN-based steganalyzers (e.g., SRNet and J-YeNet) in both spatial and JPEG domains, while keeping relatively few memory requirements and training time. Furthermore, we also provide necessary descriptions and many ablation experiments to verify the rationality of the network design. Copyright © 2021, The Authors. All rights reserved.

关键词： Steganography

Construction and optimization of a file distribution model for all-to-all comparison of big dataset

学校读者我要写书评

暂无评论

Ingenierie des Systemes d'Information 2019年第3期24卷 337-342页

作者： Li, Leixiao Gao, Jing Wang, Hui Deng, Dan Lin, Hao College of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data Based Software Service Hohhot010080 China College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot010018 China Inner Mongolia Autonomous Region Key Laboratory of big data research and application for agriculture and animal husbandry Hohhot010018 China

This paper probes into the all-to-all comparison of large dataset, and gives a formal mathematical description of the problem. Then, a multi-objective file distribution model was constructed based on the LP, aiming to localize the data, balance node storage and loads, minimize the storage occupation, and control the occupied storage within the storage limit of each node. To save storage space, the established model was further optimized, and the file distribution algorithm was designed for the distributed environment. Experimental results show that our model and algorithm successfully balanced the storage occupation and loads between computing nodes, and minimized the occupation of node storage. © 2019 International Information and engineering Technology Association. All rights reserved.

关键词： Linear programming

A two-stage deep learning-based hybrid model for daily wind speed forecasting

学校读者我要写书评

暂无评论

Heliyon 2025年第1期11卷 e41026页

作者： Band, Shahab S. Ameri, Rasoul Qasem, Sultan Noman Mehdizadeh, Saeid Gupta, Brij B. Pai, Hao-Ting Shahmirzadi, Danyal Salwana, Ely Mosavi, Amir Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Computer Science Department College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh 11432 Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz 6803 Yemen Water Engineering Department Urmia University Urmia Iran Department of Computer Science and Information Engineering Asia University Taichung 413 Taiwan Symbiosis Centre for Information Technology (SCIT) Symbiosis International University Pune India Center for Interdisciplinary Research University of Petroleum and Energy Studies (UPES) Dehradun India Department of Big Data Business Analytics National Pingtung University Pingtung Taiwan of Engineering Science and Technology National Yunlin University of Science and Technology 123 University Road Yunlin Douliou 64002 Taiwan Institute of Visual Informatics Universiti Kebangsaan Malaysia Selangor Bangi 43600 Malaysia John von Neumann Faculty of Informatics Obuda University Budapest Hungary Ludovika University of Public Service Budapest Hungary

Global adoption of wind energy continues to increase, while improving the efficiency of turbine settings requires reliable wind speed (WS) models. The latest models rely on artificial intelligence (AI) optimizations which constructs tests on a range of novel hybrid models to examine the reliability. Gradient Boosting (GB), Random Forest (RF), and Long Short-Term Memory (LSTM) are used in new combinations for data pre-processing. A Time Varying Filter-based Empirical Mode Decomposition (TVFEMD) model is coupled with the GB and LSTM standalone models, to create TVFEMD-GB and TVFEMD-LSTM hybrids, which are run in competition with each other. Eventually, a preferred hybrid form is established, simultaneous hybridization of TVFEMD with GB and LSTM. This study is the first to hybridize these fundamental systems, and create a TVFEMD-GB-LSTM model that can forecast WS. This study finds that the novel hybrid models exhibit superior performance to standalone GB and LSTM models, opening the pathway to alternative WS prediction techniques. © 2024 The Authors

关键词： Artificial intelligence big data data science Forecasting Gradient boosting Long short-term memory Machine learning Wind speed

Single-path Bit Sharing for Automatic Loss-aware Model Compression

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Jing Zhuang, Bohan Chen, Peng Shen, Chunhua Cai, Jianfei Tan, Mingkui The School of Software Engineering South China University of Technology China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China The School of Computer Science the University of Adelaide Australia The Faculty of Information Technology Monash University Australia The College of Computer Science and Technology Zhejiang University Hangzhou China

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct quantization based on the pruned model. However, this strategy may ignore that the pruning and quantization would affect each other and thus performing them separately may lead to sub-optimal performance. To address this, performing pruning and quantization jointly is essential. Nevertheless, how to make a trade-off between pruning and quantization is non-trivial. Moreover, existing compression methods often rely on some pre-defined compression configurations (i.e., pruning rates or bitwidths). Some attempts have been made to search for optimal configurations, which however may take unbearable optimization cost. To address these issues, we devise a simple yet effective method named Single-path Bit Sharing (SBS) for automatic loss-aware model compression. To this end, we consider the network pruning as a special case of quantization and provide a unified view for model pruning and quantization. We then introduce a single-path model to encode all candidate compression configurations, where a high bitwidth value will be decomposed into the sum of a lowest bitwidth value and a series of re-assignment offsets. Relying on the single-path model, we introduce learnable binary gates to encode the choice of configurations and learn the binary gates and model parameters jointly. More importantly, the configuration search problem can be transformed into a subset selection problem, which helps to significantly reduce the optimization difficulty and computation cost. In this way, the compression configurations of each layer and the trade-off between pruning and quantization can be automatically determined. Extensive experiments on CIFAR-100 and ImageNet show that SBS significantly reduces computation cost while achieving promising performance. For example, our SBS compressed MobileNetV2 achieves

关键词： Encoding (symbols)

An improved smith-waterman algorithm based on spark parallelization

学校读者我要写书评

暂无评论

International Journal Bioautomation 2019年第1期23卷 117-129页

作者： Liu, Yanfeng Li, Leixiao Gao, Jing College of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot010018 China Inner Mongolia Autonomous Region Engineering Technology Research Center of Big Data Based Software Service Inner Mongolia University of Technology Hohhot010080 China

This paper proposes the design and the implementation of a Spark parallelization plan for improving the Smith-Waterman (SW) algorithm, named the Spark-OSW algorithm. Then, the Spark-OSW was verified through accuracy, performance and acceleration tests. The results show that the proposed algorithm achieved 100% accuracy, ran much faster than the SW, and performed well in cluster environment. The research findings shed important new light on the database search for gene sequences. © 2019 INT. J. Bioautomation.

关键词： Search engines

Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Chunhui Yuan, Xiaoming Zhang, Qianyun Zhu, Guangxu Cheng, Lei Zhang, Ning The Michtom School of Computer Science Brandeis University WalthamMA United States The Qinhuangdao Branch Campus Northeastern University Qinhuangdao066004 China The School of Cyber Science and Technology Beihang University Beijing China The Shenzhen Research Institute of Big Data Guangdong Shenzhen China The College of Information Science and Electronic Engineering Zhejiang University China Hangzhou310027 China The Department of Electrical and Computing Engineering University of Windsor WindsorONN9B 3P4 Canada

Neural networks often encounter various stringent resource constraints while deploying on edge devices. To tackle these problems with less human efforts, automated machine learning becomes popular in finding various neural architectures that fit diverse Artificial Intelligence of Things (AIoT) scenarios. Recently, to prevent the leakage of private information while enable automated machine intelligence, there is an emerging trend to integrate federated learning and neural architecture search (NAS). Although promising as it may seem, the coupling of difficulties from both tenets makes the algorithm development quite challenging. In particular, how to efficiently search the optimal neural architecture directly from massive non-independent and identically distributed (non-IID) data among AIoT devices in a federated manner is a hard nut to crack. In this paper, to tackle this challenge, by leveraging the advances in ProxylessNAS, we propose a Federated Direct Neural Architecture Search (FDNAS) framework that allows for hardware-friendly NAS from non-IID data across devices. To further adapt to both various data distributions and different type of devices with heterogeneous embedded hardware platforms, inspired by meta-learning, a Cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve device-aware NAS, in the sense that each device can learn a tailored deep learning model for its particular data distribution and hardware constraint. Extensive experiments on non-IID datasets have shown the state-of-the-art accuracy-efficiency trade-offs achieved by the proposed solution in the presence of both data and device heterogeneity. © 2022, CC BY.

关键词： Network architecture

Behavior Classification and Spatiotemporal Analysis of Grazing Sheep Using Deep Learning

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Jin, Zhongming Shu, Hang Hu, Tianci Jiang, Chengxiang Yan, RuiRui Qi, Jingwei Wang, Wensheng Guo, Leifeng Agricultural Information Institute Chinese Academy of Agriculture Sciences Beijing100086 China AgroBioChem/TERRA Precision Livestock and Nutrition Unit Gembloux Agro-Bio Tech University of Liège Gembloux5030 Belgium College of Computer and Information Engineering Xinjiang Agricultural University Urumqi830052 China Institute of Agricultural Resources and Regional Planning Chinese Academy of Agricultural Sciences Beijing100086 China College of Animal Science Inner Mongolia Agricultural University Hohhot010018 China Big Data Development Center Ministry of Agriculture and Rural Affairs of the People’s Republic of China 100125 China

Monitoring multiple behavioral patterns and grazing trajectories of individual sheep canprovide valuable information for various aspects of livestock production. The emergence of low-cost, low-power miniature sensors, coupled with the continuous advancement of deep learning technologies, has ushered in a new generation of intelligent solutions for precision livestock farming. This study aims to explore the deployment methods of motion sensors, selection of data collection frequencies, and choice of deep learning algorithms to provide accurate classification of multiple behaviors in grazing sheep. Based on this, in conjunction with the acquired location information, the goal is to comprehend the spatiotemporal distribution of grazing sheep behaviors. Devices capable of collecting Inertial Measurement Units (IMU) and location data were attached to the jaw, neck, and hind leg of sheep. Four datasets were created using IMU data with a sampling frequency of 20Hz and a 5-second time window from different positions (neck, neck & leg, jaw, jaw & leg). Two deep learning models, Convolutional Neural Network (CNN) - Long Short Term Memory (LSTM) and Temporal Convolutional Network (TCN)-Transformer, were employed to classify six grazing sheep behaviors walking, standing, grazing, lying, standing-ruminating, and lying-ruminating. The results indicate that by fusing data from the neck- and leg-mounted device, utilizing the CNN-LSTM model, the highest accuracy for the classification of the six behaviors reached 98.4%. Furthermore, a comparison was made regarding the behavior classification accuracy of this fused data at different IMU data sampling frequencies (20, 10, 5, 2, 1Hz). It was found that even when the data frequency was reduced to 1Hz, the classification accuracy for the six sheep behaviors still exceeded 95%. Applying the trained model with the highest behavior classification accuracy to actual grazing processes of sheep allows for quantifying the total duration of each

关键词： Learning algorithms

A codebook-driven approach for low-light image enhancement

学校读者我要写书评

暂无评论

engineering Applications of Artificial Intelligence 2025年 156卷

作者： Xu Wu Xianxu Hou Zhihui Lai Jie Zhou Ya-nan Zhang Witold Pedrycz Linlin Shen College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou 215400 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen 518060 China School of Computer Science Sichuan Normal University Chengdu 610065 China The Department of Electrical & Computer Engineering University of Alberta Alberta T6G 1H9 Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations; (2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging discrete codebook priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. The code can be obtained from https://***/csxuwu/CodeEnhance or https://***/*** .

关键词： Image coding