检索结果-内蒙古大学图书馆

International Conference on Wireless communications and Signal processing (WCSP)

作者： Jieying Zheng Haoxian Li Feng Liu Jiangsu Key Lab on Image Processing & Image Communications Nanjing University of Posts and Telecommunications Nanjing China School of Geographic and Biologic Information Nanjing University of Posts and Telecommunications Smart Health Big Data Analysis and Location Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781665450867

Face sketch-photo synthesis aims at generating a facial photo conditioned on a given photo. It has attracted wide attention in computer vision and has been widely applied in law enforcement and entertainment. However, precisely synthesizing high-quality face photos is still challenging due to the missing color information in face sketches. To alleviate the problem, we propose an attribute and Semantic constrained Generative Adversarial Networks (ASGAN), which introduces face attribute and semantic constraints to improve the quality and accuracy of synthesized photos. Specifically, We first annotate the key attributes in the dataset and form a 14-dimensional attribute vector for each face. Then, the attribute features and semantic features obtained by face parsing are fused. Finally, the generator takes the fused constrain features and sketches as input and constructs two-stream encoders to synthesize high-quality photos. Extensive experimental results demonstrate that our method can significantly outperform state-of-the-art methods. It can synthe-size higher-quality face photos while maintaining the identity, attributes, and structure. Meanwhile, it can alleviate the problem of background and skin color synthesis errors.

关键词： Wireless communication Law enforcement Semantics Entertainment industry Color Signal processing Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Face Segmentation Based on Face Attention Model and Seeded Region Merging

Efficient Face Segmentation Based on Face Attention Model an...

引用

9th International Conference on Signal processing(第九届国际信号处理学术会议)(ICSP'08)

作者： Zhi Liu Weiwei Li Xiang Zhang Jie Yang School of Communication and Information Engineering Shanghai UniversityChina Key Lab of Advanced Di School of Communication and Information Engineering Shanghai UniversityChina Institute of Image Processing and Pattern Recognition Shanghai Jiaotong UniversityChina

This paper presents an efficient face segmentation approach based on face attention model and seeded region merging.A face attention model that jointly exploits the information of skin color and eye's position is first constructed to obtain a facial saliency map,which indicates the position of possible faces and is used to determine seed *** a seeded region merging algorithm based on regional facial saliency is proposed to generate a sequence of regions,and the region with the highest regional facial saliency is selected to represent each *** results on a variety of images demonstrate the good segmentation performance of the proposed face segmentation algorithm.

关键词： face segmentation face attention model seeded region merging

来源：评论

学校读者我要写书评

暂无评论

Data-consistent Unsupervised Diffusion Model for Metal Artifact Reduction

Data-consistent Unsupervised Diffusion Model for Metal Artif...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tong, Zhan Wu, Zhan Yang, Yang Mao, Weilong Wang, Shijie Li, Yinsheng Chen, Yang Southeast University Laboratory of Image Science and Technology Nanjing210096 China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing210096 China Chinese Academy of Sciences Research Center for Medical Artificial Intelligence Shenzhen Institutes of Advanced Technology Shenzhen518055 China School of Computer Science and Engineering Key Lab. of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Laboratory of Image Science and Technology Nanjing210096 China

ISBN: (纸本)9798350337488

Computed Tomography (CT) is an imaging technique widely used in clinical diagnosis. However, high-attenuation metallic implants result in the obstruction of low-energy Xrays and further lead to metal artifacts in the reconstructed CT images. Deep supervised model-based metal artifact reduction(MAR) approaches are limited in clinical applications due to the difficulty in obtaining paired artifact-affected and artifactfree data. Furthermore, these model-based methods lack the consideration of data consistency in the sinogram-domain to perform exact metal trace inpainting. To address these challenges, we propose a Data-consistent unsupErVised diffusiOn model for meTal artifact rEDuction, called DEVOTED-Net. First, DEVOTED-Net leverages prior knowledge to guide the conditional diffusion model for fine-grained metal trace inpainting. Second, an unsupervised MAR framework is designed in the reverse process for the unknown metal traces restoration in the sinogram domain. Third, to further enhance the sinogram-domain data consistency, physics-based consistency constraint loss including conjugateray consistency loss and accumulation-ray consistency loss is designed. Extensive experiments are carried out to verify the performance of our algorithm on the publicly available dataset and clinical experimental dataset. This efficient, accurate, and reliable MAR approach holds great potential in clinics. © 2023 IEEE.

关键词： computed tomography deep unsupervised learning denoising diffusion probabilistic model Metal artifact reduction physics-based consistency constraint

来源：评论

学校读者我要写书评

暂无评论

An improved algorithm of pattern matching for information security audit system

引用

Journal of Computational Information Systems 2008年第5期4卷 2221-2228页

作者： Ding, Lei Yu, Fei Xu, Cheng Yue, Guangxue School of Physics Science and Information Engineering Jishou University Jishou 416000 China Provincial Key Lab. of Image Processing and Imagecom Communication Nanjing University of Post and Telecommunications Nanjing 210003 China College of Computer and Communication Hunan University Changsha 410082 China

At present, network information audit system is almost based on text information filtering. Text categorization is the basic technology of text information filtering. Pattern matching algorithms are very important for the rule based information audit system. It directly influences the accuracy and real-time performance of the system. The KMP and BM algorithms are introduced in this paper. Research is carried out to improve the BM algorithm and a better BM algorithm is proposed According to the situation that the system characters group is bigger and that characters of the pat tern are less, the thesis puts forward an improved string-matching algorithm. The results of our experiments prove that it promotes the precision of text categorization. © 2008 Binary Information Press.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Vehicle Color Recognition Using Monocular camera

Vehicle Color Recognition Using Monocular camera

引用

2011年无线通信与信号处理国际会议(WCSP 2011)

作者： Mengjie Yang Xiuchang Zhu Liang Li Guang Han Xiaofei Li Jiangsu Provincial Key Lab of Image Processing and ImageCommunication Nanjing Univ. of P&TNanjing Engineering Research Center of Wideband Wireless Communication and Display Technique Ministry of Ed Engineering Research Center of Wideband WirelessCommunication and Display Technique Ministry ofEduc

This paper introduces a novel moving vehicle color recognition method. By processing videos recorded by monocular camera on traffic, we get single color image of vehicles which are crossed the traffic in any direction. First, paper employed a H-S two dimension histogram method to detect the color of the vehicles, and distinguish red, yellow, green and blue four color vehicles. Due to deal with the vehicles that do not satisfy above 4 colors, Regional Color Judgment method is proposed. This method consists of the following five steps: Firstly, position the color detection region by identifying the travelling direction of the vehicle. Then pick out the candidate color extraction region used to vehicle recognition. At last extract the color of the candidate region and match the color with the templates we predefined, the color of the best fit template is the color of the vehicle.

关键词： vehicle color recognition region choice HSV space vehicle detection

来源：评论

学校读者我要写书评

暂无评论

Mask-Guided Transformer for Human-Object Interaction Detection

Mask-Guided Transformer for Human-Object Interaction Detecti...

引用

IEEE Visual communications and image processing (VCIP)

作者： Daocheng Ying Hua Yang Jun Sun Shanghai Key Lab of Digital Media Processing and Transmission Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

ISBN: (纸本)9781665475938

Human-object interaction (HOI) detection is a meaningful research topic on human activity understanding. Recent works have made significant progress by focusing on efficient triplet matching and leveraging image-wide features based on encoder-decoder architecture. However, the ability to gather relevant contextual information about human is limited and different sub-tasks in HOI detection are not differentiated by specific decoupling in previous methods. To this end, we propose a new transformer-based method for HOI detection, namely, Mask-Guided Transformer (MGT). Our model, which is composed of five parallel decoders with a shared encoder, not only emphasizes interactive regions by applying body features, but also disentangles the prediction of instance and interaction. We achieve a favorable result at 63.3 mAP on the well-known HOI detection dataset V-COCO.

关键词： Visual communication image processing Focusing Predictive models Transformers Decoding

来源：评论

学校读者我要写书评

暂无评论

Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model

Exploring Interactive Semantic Alignment for Efficient HOI D...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jihao Dong Hua Yang Renjie Pan Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission China China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Human-Object Interaction (HOI) detection aims to localize human-object pairs and comprehend their interactions. Recently, two-stage transformer-based methods have demonstrated competitive performance. However, these methods frequently focus on object appearance features and ignore global contextual information. Besides, vision-language model CLIP which effectively aligns visual and text embeddings has shown great potential in zero-shot HOI detection. Based on the former facts, We introduce a novel HOI detector named ISA-HOI, which extensively leverages knowledge from CLIP, aligning interactive semantics between visual and textual features. We first extract global context of image and local features of object to Improve interaction Features in images (IF). On the other hand, we propose a Verb Semantic Improvement (VSI) module to enhance textual features of verb labels via cross-modal fusion. Ultimately, our method achieves competitive results on the HICO-DET and V-COCO benchmarks with much fewer training epochs, and outperforms the state-of-the-art under zero-shot settings.

关键词： Training Visualization Target recognition Semantics Detectors Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MPASNET: Motion prior-aware siamese network for unsupervised deep crowd segmentation in video scenes

arXiv

引用

arXiv 2021年

作者： Yang, Jinhai Yang, Hua Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Crowd segmentation is a fundamental task serving as the basis of crowded scene analysis, and it is highly desirable to obtain refined pixel-level segmentation maps. However, it remains a challenging problem, as existing approaches either require dense pixel-level annotations to train deep learning models or merely produce rough segmentation maps from optical or particle flows with physical models. In this paper, we propose the Motion Prior-Aware Siamese Network (MPASNET) for unsupervised crowd semantic segmentation. This model not only eliminates the need for annotation but also yields high-quality segmentation maps. Specially, we first analyze the coherent motion patterns across the frames and then apply a circular region merging strategy on the collective particles to generate pseudo-labels. Moreover, we equip MPASNET with siamese branches for augmentation-invariant regularization and siamese feature aggregation. Experiments over benchmark datasets indicate that our model outperforms the state-of-the-arts by more than 12% in terms of mIoU. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model

arXiv

引用

arXiv 2024年

作者： Dong, Jihao Pan, Renjie Yang, Hua Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission China China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive and Collaborative Multi-scale Alignment for Text-Based Person Search

Adaptive and Collaborative Multi-scale Alignment for Text-Ba...

引用

IEEE Visual communications and image processing (VCIP)

作者： Xinxin Yang Renjie Pan Hua Yang Shanghai Key Lab of Digital Media Processing and Transmission Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Text-to-image person search is challenging due to the cross-scale correspondences and information inequality between modalities. Specifically, images and text are complexly linked at different scales and images are usually more informative and complete than text. It is crucial to establish semantic correlations between modalities and focus on task-relevant information in images. In this paper, we propose a novel Adaptive and Collaborative Multi-scale Alignment network (ACMA) for text-based person search that learns semantically consistent and information-aligned multi-modal representations. Firstly, we introduce a novel joint embedding module that adaptively integrates features of different pixels and words, thereby extracting semantically consistent multi-modal features at different scales. Second, we design a cross-modal fusion feature-based auxiliary visual branch to guide the extraction of key visual features that are beneficial for cross-modal matching. Extensive experiments validate that ACMA outperforms the state-of-the-art method.

关键词：

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：