检索结果-内蒙古大学图书馆

Vision-Text Bidirectional Collaborative Image Captioning Algorithm

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2025年第2期52卷 515-523页

作者： Li, Mei-Qi Zhou, Zi-Wei School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Image captioning is an interdisciplinary research hotspot at the intersection of computer vision and natural language processing, representing a multimodal task that integrates core technologies from both fields. This task requires the use of computer vision techniques to analyze and extract key visual features from images, followed by the application of natural language processing techniques to generate descriptive text that is syntactically and semantically aligned with human cognition. This process poses a significant challenge for computers. Existing models mostly ignore the relative positional information of visual objects and struggle to efficiently capture the complex relationships between visual and textual data. To address these challenges, we propose a vision-to-text bidirectional collaborative image captioning method. This approach extracts both visual features and positional information of objects, allowing the model to better understand the spatial relationships between objects. The CEW word embedding approach encodes textual information more profoundly, enhancing semantic expression and contextual understanding. In the decoding phase, a bidirectional cross-attention mechanism strengthens the interaction between vision and text, leading to improved accuracy in image understanding. The model is trained and tested on the MSCOCO 2014 dataset and compared with several popular models. Experimental results demonstrate that the proposed method achieves significant improvements on the CIDEr and BLEU-1 evaluation metrics with an increase of 1.5 and 1.1, respectively. In addition, we conduct ablation experiments, quantitative analysis, and qualitative analysis to comprehensively validate the effectiveness and stability of the proposed algorithm. © (2025), (International Association of Engineers). All rights reserved.

关键词： Embeddings

VAT: Visibility Aware Transformer for Fine-Grained Clothed Human Reconstruction

学校读者我要写书评

暂无评论

IEEE Transactions on Visualization and computer Graphics 2025年第5期31卷 2277-2287页

作者： Zhang, Xiaoyan Zhu, Zibin Xie, Hong Ren, Sisi Shenzhen University College of Computer Science and Software Engineering Shenzhen518000 China

In order to reconstruct 3D clothed human with accurate fine-grained details from sparse views, we propose a deep cooperating two-level global to fine-grained reconstruction framework that constructs robust global geometry to guide fine-grained geometry learning. The core of the framework is a novel visibility aware Transformer VAT, which bridges the two-level reconstruction architecture by connecting its global encoder and fine-grained decoder with two pixel-aligned implicit functions, respectively. The global encoder fuses semantic features of multiple views to integrate global geometric features. In the fine-grained decoder, visibility aware attention mechanism is designed to efficiently fuse multi-view and multi-scale features for mining fine-grained geometric features. The global encoder and fine-grained decoder are connected by a global embeding module to form a deep cooperation in the two-level framework, which provides global geometric embedding as a query guidance for calculating visibility aware attention in the fine-grained decoder. In addition, to extract highly aligned multi-scale features for the two-level reconstruction architecture, we design an image feature extractor MSUNet, which establishes strong semantic connections between different scales at minimal cost. Our proposed framework is end-to-end trainable, with all modules jointly optimized. We validate the effectiveness of our framework on public benchmarks, and experimental results demonstrate that our method has significant advantages over state-of-the-art methods in terms of both fine-grained performance and generalization. © 2025 IEEE.

关键词： Decoding

The Improved Unet Semantic Segmentation Network for Remote Sensing Images

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2025年第4期52卷 1187-1195页

作者： Zhu, Hang Zhao, Ji School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

With the development of artificial intelligence, deep learning has been increasingly used to achieve automatic detection of geographic information, replacing manual interpretation and improving efficiency. However, remote sensing images themselves have the issue of slight inter-class variance and significant intra-class variance, making it challenging to extract valuable information. Additionally, the increasing resolution and size of remote sensing images in recent years have introduced more complexity in the types of information, further increasing the difficulty of extracting valuable data. This paper proposes an improved Unet semantic segmentation network (referred to as RAUnet). First, in the encoder, continuous convolutional blocks are enhanced to extract features. At the same time, the EMAM multi-scale attention module is employed for cross-channel learning, capturing information from different feature channels of the target and using the surrounding feature information to assist in distinguishing target information. To capture multi-directional long-range dependencies, the Lo2 module is used for long-range modeling, which captures not only local contextual information but also long-range dependencies. In the decoder, a Dysample upsampling module is used to restore feature details, and in the skip connection layer, features are added for feature fusion. Experimental results show that compared to mainstream models, the proposed method achieves superior segmentation results on the Potsdam and Vihingen datasets. © (2025), (International Association of Engineers). All rights reserved.

关键词： Semantic Segmentation

Infrared Fault Detection Method for Dense Electrolytic Bath Polar Plate Based on YOLOv5s

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第9期80卷 4859-4874页

作者： Huiling Yu Yanqiu Hang Shen Shi Kangning Wu Yizhuo Zhang Software Engineering Department of Computer ScienceChangzhou UniversityChangzhou213146China Electrical Engineering Department of Computer ScienceChangzhou UniversityChangzhou213146China

Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal *** at the problems of time-consuming and poor accuracy of existing infrared methods for high-temperature detection of dense pole plates in electrolysis tanks,an infrared dense pole plate anomalous target detection network YOLOv5-RMF based on You Only Look Once version 5(YOLOv5)is ***,we modified the Real-Time Enhanced Super-Resolution Generative Adversarial Network(Real-ESRGAN)by changing the U-shaped network(U-Net)to Attention U-Net,to preprocess the images;secondly,we propose a new Focus module that introduces the Marr operator,which can provide more boundary information for the network;again,because Complete Intersection over Union(CIOU)cannot accommodate target borders that are increasing and decreasing,replace CIOU with Extended Intersection over Union(EIOU),while the loss function is changed to Focal and Efficient IOU(Focal-EIOU)due to the different difficulty of sample *** the homemade dataset,the precision of our method is 94%,the recall is 70.8%,and the map@.5 is 83.6%,which is an improvement of 1.3%in precision,9.7%in recall,and 7%in map@.5 over the original *** algorithm can meet the needs of electrolysis tank pole plate abnormal temperature detection,which can lay a technical foundation for improving production efficiency and reducing production waste.

关键词： Infrared polar plate fault detection YOLOv5 Real-ESRGAN Marr boundary detection operator Focal-EIoU loss

LoRaDIP: Low-Rank Adaptation With Deep Image Prior for Generative Low-Light Image Enhancement

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 909-920页

作者： Zhao, Zunjin Shi, Daming Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

This article presents LoRaDIP, a novel low-light image enhancement (LLIE) model based on deep image priors (DIPs). While DIP-based enhancement models are known for their zero-shot learning, their expensive computational cost remains a challenge. In addressing this issue, our proposed LoRaDIP introduces a low-rank adaptation technique, significantly reducing computational expenses without compromising performance. The contributions of this work are threefold. First, we eliminate the need for estimating initial illumination and reflectance, opting instead to directly estimate the illumination map from the observed image in a generative fashion. The illumination is parameterized by a DIP network. Second, considering the overparameterization of DIP networks, we introduce a low-rank adaptation technique to decrease the number of trainable parameters, thereby reducing computational demands. Third, differing from the existing DIP-based models that rely on a preset fixed number of iterations to halt the optimization process of Retinex decomposition, we propose an automatic stopping criterion based on stable rank, preventing unnecessary iterations. LoRaDIP not only inherits the advantage of requiring only the single input image but also exhibits reduced computational costs while maintaining or even surpassing the performance of state-of-the-art models. © 2020 IEEE.

关键词： Zero-shot learning

YOLOv7-DSE: An Efficient Safety Equipment Detection Network

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2024年第6期51卷 572-581页

作者： Ren, Jiaxin Cui, Wenhua Tao, Ye Shi, Tianwei School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Safety equipment detection is an important application of object detection, receiving widespread attention in fields such as smart construction sites and video surveillance. Significant progress has been made in object detection due to the rapid development of deep learning. Multi-scale targets and complex scenes increase the likelihood of false positives and missed detections, which can affect the accuracy of the detection. To address this issue, this study proposes YOLOv7-DSE. It is a small complex target scene detection network based on the improved YOLOv7. Also, we have created a private dataset of safety equipment. First, we enhanced the ELAN and MP backbone networks. Backbone is replaced by ordinary convolution by the depthwise separable convolution. We enabled the backbone network to extract deeper image features without increasing the amount of parameters and computation. Simultaneously, the model incorporates the EIOU loss function to improve its convergence speed and positioning effect. Secondly, we propose a new ELAN-SPD structure in the head network. Based on the ELAN structure, a space-to-depth convolutional layer is added to fully downsample the feature map, preserving all learnable features. Our network model can better detect objects with significant size differences faced with complex scenes. YOLOv7-DSE achieved the mAP of 82.38%, surpassing the original YOLOv7 with 2.64%. The YOLOv7-DSE model has a minor size compared to the baseline model. Our improvement has reduced the model parameters by 22.4%. © (2024), (International Association of Engineers). All rights reserved.

关键词： Object detection

Application of Face Detection and Recognition Algorithm Based on Deep Learning in Automatic Interception of Target Person Video Clips

学校读者我要写书评

暂无评论

IAENG International Journal of computer science 2024年第10期51卷 1546-1559页

作者： Wang, Zhibiao Tao, Ye Liu, Xu Yu, Jiayi Cui, Wenhua School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Current automatic segment extraction techniques for identifying target characters in videos have several limitations, including low accuracy, slow processing speeds, and poor adaptability to diverse scenes. This paper introduces an optimized algorithm to address these issues that enhance the RetinaFace and FaceNet models. We selected RetinaFace for face detection, employing MobileNetV1-0.25 as the backbone network and simplifying its Feature Pyramid Network (FPN) structure to boost detection speeds. Analysis of 460 images with a 720P resolution demonstrated an average speed improvement of 20.6%. For face recognition, we utilized FaceNet with MobileNetV3 as the backbone, augmenting its feature extraction capability by integrating four Receptive Field Block (RFB) structures and replacing the Squeeze-and-Excitation (SE) module with the Convolutional Block Attention Module (CBAM). Experimental results indicate that our enhancements elevate the maximum accuracy to 97%, outperforming the original model. Additionally, we integrated these refined algorithms and conducted disintegration experiments on segment extraction in 10 videos, evaluating various metrics. The findings show improvements in both precision and recall. We also compared our algorithm against the Dlib model;our system achieved an overall interception accuracy of 79.94%, surpassing Dlib’s 75.55%. This confirms the enhanced performance and feasibility of our proposed algorithm. © (2024), (International Association of Engineers). All rights reserved.

关键词： Face recognition

A review of optimization methods for computation offloading in edge computing networks

学校读者我要写书评

暂无评论

Digital Communications and Networks 2023年第2期9卷 450-461页

作者： Kuanishbay Sadatdiynov Laizhong Cui Lei Zhang Joshua Zhexue Huang Salman Salloum Mohammad Sultan Mahmud College of Computer Science and Software Engineering Shenzhen UniversityShenzhen518061China

Handling the massive amount of data generated by Smart Mobile Devices(SMDs)is a challenging computational *** Computing is an emerging computation paradigm that is employed to conquer this *** can bring computation power closer to the end devices to reduce their computation latency and energy ***,this paradigm increases the computational ability of SMDs by collaboration with edge *** is achieved by computation offloading from the mobile devices to the edge nodes or ***,not all applications benefit from computation offloading,which is only suitable for certain types of *** properties,SMD capability,wireless channel state,and other factors must be counted when making computation offloading ***,optimization methods are important tools in scheduling computation offloading tasks in Edge Computing *** this paper,we review six types of optimization methods-they are Lyapunov optimization,convex optimization,heuristic techniques,game theory,machine learning,and *** each type,we focus on the objective functions,application areas,types of offloading methods,evaluation methods,as well as the time complexity of the proposed *** discuss a few research problems that are still *** purpose for this review is to provide a concise summary that can help new researchers get started with their computation offloading researches for Edge Computing networks.

关键词： Edge computing Computation offloading Latency and energy consumption minimization

Deep learning for code generation: a survey

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第9期67卷 5-40页

作者： Huangzhao ZHANG Kechi ZHANG Zhuo LI Jia LI Jia LI Yongmin LI Yunfei ZHAO Yuqi ZHU Fang LIU Ge LI Zhi JIN Key Lab of High Confidence Software Technologies (Peking University) Ministry of Education School of Computer Science Peking University School of Computer Science and Engineering Beihang University

In the past decade, thanks to the powerfulness of deep-learning techniques, we have witnessed a whole new era of automated code generation. To sort out developments, we have conducted a comprehensive review of solutions to deep learning-based code generation. In this survey, we generally formalize the pipeline and procedure of code generation and categorize existing solutions according to taxonomy from perspectives of architecture, model-agnostic enhancing strategy, metrics, and tasks. In addition, we outline the challenges faced by current dominant large models and list several plausible directions for future research. We hope that this survey may provide handy guidance to understanding, utilizing, and developing deep learning-based code-generation techniques for researchers and practitioners.

关键词： code generation automated software engineering deep learning large model artificial intelligence