检索结果-内蒙古大学图书馆

Audio2AB:Audio-driven collaborative generation of virtual character animation

虚拟现实与智能硬件（中英文） 2024年第1期6卷 56-70页

作者： Lichao NIU Wenjun XIE Dong WANG Zhongrui CAO Xiaoping LIU School of Computer Science and Information Engineering Hefei University of TechnologyHeifei 230009China School of Software Hefei University of TechnologyHeifei 230009China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei University of TechnologyHefei 230601China

Background Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of ***,few methods exist for generating full-body animations,and the portability of virtual character gestures and facial animations has not received sufficient *** Therefore,we propose a deep-learning-based audio-to-animation-and-blendshape(Audio2AB)network that generates gesture animations and ARK it's 52 facial expression parameter blendshape weights based on audio,audio-corresponding text,emotion labels,and semantic relevance labels to generate parametric data for full-body *** parameterization method can be used to drive full-body animations of virtual characters and improve their *** the experiment,we first downsampled the gesture and facial data to achieve the same temporal resolution for the input,output,and facial *** Audio2AB network then encoded the audio,audio-corresponding text,emotion labels,and semantic relevance labels,and then fused the text,emotion labels,and semantic relevance labels into the audio to obtain better audio ***,we established links between the body,gestures,and facial decoders and generated the corresponding animation sequences through our proposed GAN-GF loss *** By using audio,audio-corresponding text,and emotional and semantic relevance labels as input,the trained Audio2AB network could generate gesture animation data containing blendshape ***,different 3D virtual character animations could be created through *** The experimental results showed that the proposed method could generate significant gestures and facial animations.

关键词： Audio-driven Virtual character Full-body animation Audio2AB Blendshape GAN-GF

来源：评论

学校读者我要写书评

暂无评论

Precise and efficient Chinese license plate recognition in the real monitoring scene of intelligent transportation system

引用

The Journal of China Universities of Posts and Telecommunications 2022年第3期29卷 1-14页

作者： Jia Wei Gong Chao School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China

In this paper, the performance of you only look once(YOLO) series detectors on Chinese license plate recognition(LPR) in the real intelligent transportation system(ITS) monitoring scene is investigated. Specially, a precise and efficient automatic license plate recognition(ALPR) system based on the YOLOv4 detector is proposed. The proposed ALPR system contains three stages including vehicle detection, license plate detection(LPD) and LPR. In vehicle detection stage, YOLOv4 detector is directly applied. In LPD stage, YOLOv4-tiny detector is exploited. In the last stage, the YOLOv4-tiny detector with attention mechanism for LPR is proposed to use. In addition, a large Chinese license plate dataset containing 10 500 images collected from all 31 provinces in the Chinese mainland is created. This Chinese license plate dataset is named hefei university of technology license plate version 1(HFUT-LP v1). Particularly, HFUT-LP v1 dataset is collected in the real ITS monitoring scene. In order to compare the performance of different object detection algorithms for ALPR, a variety of object detection algorithms are used to make a comprehensive performance evaluation. Experimental results show that the proposed ALPR system achieves very high accuracy and has very fast processing speed, which is suitable for real-time LPR.

关键词： license plate detection(LPD) license plate recognition(LPR) YOLOv4-tiny detector attention mechanism intelligent transportation

来源：评论

学校读者我要写书评

暂无评论

A Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism

引用

computers, Materials & Continua 2024年第3期78卷 3001-3019页

作者： Nannan Wu Xianyi Chen James Msughter Adeke Junjie Zhao School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China

Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information ***,these approaches have some *** example,a cover image lacks self-adaptability,information leakage,or weak *** address these issues,this study proposes a universal and adaptable image-hiding ***,a domain attention mechanism is designed by combining the Atrous convolution,which makes better use of the relationship between the secret image domain and the cover image ***,to improve perceived human similarity,perceptual loss is incorporated into the training *** experimental results are promising,with the proposed method achieving an average pixel discrepancy(APD)of 1.83 and a peak signal-to-noise ratio(PSNR)value of 40.72 dB between the cover and stego images,indicative of its high-quality ***,the structural similarity index measure(SSIM)reaches 0.985 while the learned perceptual image patch similarity(LPIPS)remarkably registers at ***,self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces,making it suitable for diverse computer vision tasks.

关键词： Deep image hiding attention mechanism privacy protection data security visual quality

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based software engineering: progress,challenges, and opportunities

引用

science China(information sciences) 2025年第1期68卷 57-144页

作者： Xiangping CHEN Xing HU Yuan HUANG He JIANG Weixing JI Yanjie JIANG Yanyan JIANG Bo LIU Hui LIU Xiaochen LI Xiaoli LIAN Guozhu MENG Xin PENG Hailong SUN Lin SHI Bo WANG Chong WANG Jiayi WANG Tiantian WANG Jifeng XUAN Xin XIA Yibiao YANG Yixin YANG Li ZHANG Yuming ZHOU Lu ZHANG School of Journalism and Communication Sun Yat-sen University School of Software Technology Zhejiang University School of Software Engineering Sun Yat-sen University School of Software Dalian University of Technology School of Computer Science and Technology Beijing Institute of Technology Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of EducationSchool of Computer Science Peking University State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering Beihang University Institute of Information Engineering Chinese Academy of Sciences School of Computer Science Fudan University State Key Laboratory of Complex & Critical Software Environment (CCSE) School of Software Beihang University School of Computer and Information Technology Beijing Jiaotong University School of Computer Science and Technology Harbin Institute of Technology School of Computer Science Wuhan University Huawei Technologies

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many studies have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However,although several surveys have provided overall pictures of the application of deep learning techniques in software engineering,they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this study, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas,we highlight the major advances achieved by applying deep learning techniques with pointers to the available datasets i

关键词： deep learning software engineering software benchmark software artifact representation survey

来源：评论

学校读者我要写书评

暂无评论

MTLS: Making Texts into Linguistic Symbols

MTLS: Making Texts into Linguistic Symbols

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Fei, Wenlong Wang, Xiaohua Hu, Min Zhang, Qingyu Li, Hongbo School of Computer Science and Information Engineering HeFei University of Technology China

ISBN: (纸本)9798891761643

In linguistics, all languages can be considered as symbolic systems, with each language relying on symbolic processes to associate specific symbols with meanings. In the same language, there is a fixed correspondence between linguistic symbol and meaning. In different languages, universal meanings follow varying rules of symbolization in one-to-one correspondence with symbols. Most work overlooks the properties of languages as symbol systems. In this paper, we shift the focus to the symbolic properties and introduce MTLS: a pre-training method to improve the multilingual capability of models by Making Texts into Linguistic Symbols. Initially, we replace the vocabulary in pre-trained language models by mapping relations between linguistic symbols and semantics. Subsequently, universal semantics within the symbolic system serve as bridges, linking symbols from different languages to the embedding space of the model, thereby enabling the model to process linguistic symbols. To evaluate the effectiveness of MTLS, we conducted experiments on multilingual tasks using BERT and RoBERTa, respectively, as the backbone. The results indicate that despite having just over 12,000 pieces of English data in pre-training, the improvement that MTLS brings to multilingual capabilities is remarkably significant. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Landslide extraction model for remote sensing images based on improved DeepLabv3+

Landslide extraction model for remote sensing images based o...

引用

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Wu, Yanling Lang, Wenhui School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China

ISBN: (纸本)9781510680425

In order to realize the accurate recognition of landslides in remote sensing images, an improved DeepLabv3+ landslide extraction model is proposed in this paper.(1) Hybrid Module and Attention Module based CSPNet (HA-CSPNet) is constructed as the backbone feature extraction network to enhance the feature information of small landslides and suppress the interference of irrelevant background information.(2) Combining the advantages of Residual Structure and Dense Connected Module, Residual-dense ASPP is designed to focus landslide features at different scales, enhance feature reuse and prevent gradient *** experimental results show that the landslide extraction model proposed in this paper is *** can improve the accuracy of landslide semantic segmentation. © 2024 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Dense mutual information maximization for few-shot classification

Dense mutual information maximization for few-shot classific...

引用

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Shen, Yiming Guo, Yanrong School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9781510680425

Few-shot learning (FSL) aims to learn new visual categories from a limited number of labeled examples. The use of mutual information is beneficial for improving the discrimination of feature embeddings, which makes metric classification more accurate. In this context, we propose Dense Masked Deep InfoMax Networks (DMDIN) based on Masked Image Modeling (MIM) framework with convolutional neural networks (CNN). DMDIN effectively incorporates the mutual information maximization strategy into self-supervised pretraining, improving its performance in few-shot learning. More specifically, DMDIN first generates two augmented views of each image through spatial transformations and color jittering for one view, and random RGB mean patching for the other. Second, DMDIN maximizes mutual information between dense features from these views, DMDIN learns more generalized representations, diverging from traditional patch reconstruction-based methods. Our method is evaluated on the miniImageNet, CIFAR-FS, and CUB datasets. The results validate the effectiveness of the proposed method in the few-shot learning scenario. © 2024 SPIE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Joat: to dynamically aggregate visual queries in transformer for visual question answering 3

Joat: to dynamically aggregate visual queries in transformer...

引用

3rd International Conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Wang, Mingben Yang, Juan Xue, Lixia Wang, Ronggui School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China

ISBN: (纸本)9781510681880

Attention mechanisms have shown impressive abilities in solving downstream multi-modal tasks. However, there exists a natural semantic gap between vision and language modalities that hinders conventional attention-based models in achieving effective cross-modal semantic alignment. In this paper, we present JoAt, a Joint Attention net, through which we investigate how to utilize the visual background information more directly in a query-adaptive manner to enrich querying semantics for each visual token, and how to more fully bridge the semantic gap to achieve cross-modal alignment between visual-grid and textual features. Specifically, our JoAt utilizes each query’s neighboring pixels, aggregates the visual query tokens from different receptive fields, and allows the model to dynamically select the most relevant neighboring tokens for each query, then obtains representations that are more semantically matched with the textual features to realize better interaction between visual and linguistic modalities. The experimental results show that our JoAt net can fully utilize different semantic-level signals from visual features at different receptive fields and effectively narrow the natural semantic differences between visual and language modalities. Our JoAt achieved an accuracy of 72.15% and 98.90% on the VQAv2.0 test-std and CLEVR benchmarks, respectively. © 2024 SPIE.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Improved high-resolution network for palmprint principal line extraction 3

Improved high-resolution network for palmprint principal lin...

引用

3rd International Conference on Electronic information engineering and Data Processing, EIEDP 2024

作者： Jia, Wei Zhou, Xin School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

ISBN: (纸本)9781510680531

Recently, there has been growing interest in deep learning-based semantic segmentation. We propose a high-resolution network UC-HRNet for palmprint principal line extraction. Compared with other popular deep learning semantic segmentation networks, the performance is stronger. Dense prediction tasks rely heavily on both high-resolution imagery and sophisticated semantic representations for optimal performance. Generally, low-resolution feature maps excel in conveying robust semantic representations, whereas high-resolution feature maps excel in capturing fine-grained details like edges but may lack in semantic richness. Current cutting-edge frameworks, like HRNet, preserves the parallelism between low- and high-resolution feature maps and iteratively exchanges information across different resolutions. The success of UNet is mainly due to its U-shaped structure as well as jump *** symmetric U-shaped structure allows for a more thorough fusion of front and back features, it turns out that skip connections are effective in recovering complex details of target objects. We propose a kind of U-shaped structure based on HRNet and add skip connections to make it able to segment the target more accurately. We utilize deep supervision to acquire hierarchical representations from fully aggregated feature maps. Compared to other popular semantic segmentation networks, UC-HRNet proves its effectiveness on three master libraries of semantically segmented palmprints created by ourselves. © 2024 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Two-wheeler rider re-identification that combines attention mechanism and local feature fusion

Two-wheeler rider re-identification that combines attention ...

引用

2024 International Conference on Image Processing and Artificial Intelligence, ICIPAl 2024

作者： Sun, Siheng Jia, Wei The School of Computer Science and Information Engineering Hefei University of Technology Hefei230011 China

ISBN: (纸本)9781510681514

Two-wheeler riders primarily refer to drivers of bicycles, electric bicycles, electric motorcycles, and motorcycles. Due to the minimal protection afforded to riders on the road, they are highly vulnerable to injuries and fatalities in traffic accidents. Therefore, the identification and supervision of riders on the road are of significant research importance. To address this issue, this paper proposes a novel rider re-identification algorithm based on deep learning, named the two-wheeler rider re-identification algorithm that combines attention mechanism and local feature fusion (AMLFF-Net). Firstly, we divide the network into global and local branches, where the global branch captures coarse-grained features of the entire image, while the local branch captures fine-grained features of specific regions. Secondly, we introduce attention modules and local feature fusion modules. The attention modules enable the network to focus on the target itself, reducing interference from background factors, while the local feature fusion module merges rider features with two-wheeler features, thus increasing the differentiation between feature vectors of different identities. Finally, we compare the proposed method with existing algorithms on two rider re-identification datasets. Experimental results demonstrate that AMLFF-Net achieves Rank-1 accuracies of 72.6% and 89.8% on the BPReid and MoRe datasets respectively, with mAP scores of 73.7% and 91.4% respectively, outperforming other methods and confirming the effectiveness of our proposed approach. © 2024 SPIE.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：