检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Cong, Runmin Lin, Qinwei Zhang, Chen Li, Chongyi Cao, Xiaochun Huang, Qingming Zhao, Yao Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China School of Computer Science and Engineering Nanyang Technological University Singapore School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University 518107 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China

Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement. For the cross-modality interaction, 1) a progressive attention guided integration unit is proposed to sufficiently integrate RGB-D feature representations in the encoder stage, and 2) a convergence aggregation structure is proposed, which flows the RGB and depth decoding features into the corresponding RGB-D decoding streams via an importance gated fusion unit in the decoder stage. For the cross-modality refinement, we insert a refinement middleware structure between the encoder and the decoder, in which the RGB, depth, and RGB-D encoder features are further refined by successively using a self-modality attention refinement unit and a cross-modality weighting refinement unit. At last, with the gradually refined features, we predict the saliency map in the decoder stage. Extensive experiments on six popular RGB-D SOD benchmarks demonstrate that our network outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively. The code and results can be found from the link of https://***. io/proj_***. © 2022, CC BY-NC-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

SSCGAN: Speech style conversion based on GAN

SSCGAN: Speech style conversion based on GAN

引用

2022 International Conference on Algorithms, Microchips and Network Applications

作者： Li, Jixing Guo, Xiaozhou Shen, Ronxuan Lu, Huaxiang Wang, Xinggang Cao, Zhanzhong Zhang, Chi Mao, Wenyu Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China University of Chinese Academy of Sciences Beijing100089 China Materials and Optoelectronics Research Center University of Chinese Academy of Sciences Beijing100083 China College of Microelectronics University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Laboratory Beijing100083 China Nanjing Research Institute of Information Technology Nanjing210009 China

ISBN: (纸本)9781510653290

Speech conversion has significant applications in medical, robotics, and other industries. With the rise of deep learning, CycleGAN is widely used in speech conversion technology. However, the existing CycleGAN-based methods do not consider the speech signal's temporal and spatial features. In addition, the training of CycleGAN is difficult to converge due to the gradient disappearance problem of the generator. We propose SSCGAN, whose generator is a U-shaped encoder-decoder network that extracts the temporal and spatial features by using 1DCNN and 2DCNN in parallel. A feature fusion module based on multi-scale mixed convolution is embedded between encoder and decoder to achieve high-level fusion of spatial features and temporal features. To make the network training more stable and easier to converge, SSCGAN uses Wasserstein distance instead of the original Jensen-Shannon divergence to calculate the distance of the probability distribution, which can alleviate the gradient extinction problem for generators. In addition, SSCGAN utilizes the PatchGAN structure in the discriminator, which considers the samples' local details by dividing them into different patches. It can improve the discriminative ability of SSCGAN. The experiment results in the nonparallel corpus database VCC 2018 show that SSCGAN is superior to existing methods such as CycleGAN-VC, StarGan-VC. In inter-gender speech conversion, the MSD of SSCGAN is decreased by 0.162 on average compared to other methods, and in intra-gender speech conversion, the MSD is decreased by 0.118 on average. In subjective evaluation, participants also think SSCGAN is the best. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Large Scale Visual Food Recognition

arXiv

引用

arXiv 2021年

作者： Min, Weiqing Wang, Zhiling Liu, Yuxin Luo, Mengjiang Kang, Liping Wei, Xiaoming Wei, Xiaolin Jiang, Shuqiang The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Meituan Group China

Food recognition plays an important role in food choice and intake, which is essential to the health and well-being of humans. It is thus of importance to the computer vision community, and can further support many food-oriented vision and multimodal tasks, e.g., food detection and segmentation, cross-modal recipe retrieval and generation. Unfortunately, we have witnessed remarkable advancements in generic visual recognition for released large-scale datasets, yet largely lags in the food domain. In this paper, we introduce Food2K, which is the largest food recognition dataset with 2,000 categories and over 1 million images. Compared with existing food recognition datasets, Food2K bypasses them in both categories and images by one order of magnitude, and thus establishes a new challenging benchmark to develop advanced models for food visual representation learning. Furthermore, we propose a deep progressive region enhancement network for food recognition, which mainly consists of two components, namely progressive local feature learning and region feature enhancement. The former adopts improved progressive training to learn diverse and complementary local features, while the latter utilizes self-attention to incorporate richer context with multiple scales into local features for further local feature enhancement. Extensive experiments on Food2K demonstrate the effectiveness of our proposed method. More importantly, we have verified better generalization ability of Food2K in various tasks, including food image recognition, food image retrieval, cross-modal recipe retrieval, food detection and segmentation. Food2K can be further explored to benefit more food-relevant tasks including emerging and more complex ones (e.g., nutritional understanding of food), and the trained models on Food2K can be expected as backbones to improve the performance of more food-relevant tasks. We also hope Food2K can serve as a large scale fine-grained visual recognition benchmark, and contr

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

DeepMesh: A Comprehensive Survey of Deep Learning-Based Routing Performance in Wireless Mesh Networks

DeepMesh: A Comprehensive Survey of Deep Learning-Based Rout...

引用

International Conference on intelligent System and Knowledge Engineering, ISKE

作者： Qiu Xiaoping Md Zahidul Alam Shiling Du Zhongjian Yue Yulan Wang School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China Tangshan Institute of Southwest Jiaotong University Tangshan China National United Engineering Laboratory of Integrated and Intelligent Transportation Chengdu China Ministry of Education Engineering Research Center of Sustainable Urban Intelligent Transportation Chengdu China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Chengdu China Sichuan Institute of industrial Software Technology Chengdu Sichuan China

This paper provides a analysis of the challenges faced in routing in wireless mesh networks and how deep learning can be used to improve performance. Wireless mesh networks (WMNs) are a particular kind of wireless network that use mesh routers and mesh clients that talk to one another to provide wireless coverage over a wide area. The paper discusses the limitations of traditional routing methods in WMNs and highlights the potential of deep learning-based routing approaches to revolutionize WMNs. The survey evaluates the literature focusing on the various routing approaches, performances, and research methodologies. The study aims to provide several potential areas for further investigation in deep learning-based routing approaches for WMNs and discusses several research challenges and opportunities in the field. The identification of trends and challenges, and recommendations for future research directions provide valuable insights for researchers and practitioners in the field of wireless mesh networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Generative Model Assisted 3D Semantic Communication

arXiv

引用

arXiv 2024年

作者： Jiang, Feibo Peng, Yubo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China The Department of Computer Science Brunel University London United Kingdom The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Frontiers Science Center for Mobile Information Communication and Security National Mobile Communications Research Laboratory Southeast University Nanjing China The Purple Mountain Laboratories Nanjing China

Semantic Communication (SC) is a novel paradigm for data transmission in 6G. However, there are several challenges posed when performing SC in 3D scenarios: 1) 3D semantic extraction;2) Latent semantic redundancy;and 3) Uncertain channel estimation. To address these issues, we propose a Generative AI Model assisted 3D SC (GAM-3DSC) system. Firstly, we introduce a 3D Semantic Extractor (3DSE), which employs generative AI models, including Segment Anything Model (SAM) and Neural Radiance Field (NeRF), to extract key semantics from a 3D scenario based on user requirements. The extracted 3D semantics are represented as multi-perspective images of the goal-oriented 3D object. Then, we present an Adaptive Semantic Compression Model (ASCM) for encoding these multi-perspective images, in which we use a semantic encoder with two output heads to perform semantic encoding and mask redundant semantics in the latent semantic space, respectively. Next, we design a conditional Generative adversarial network and Diffusion model aided-Channel Estimation (GDCE) to estimate and refine the Channel State information (CSI) of physical channels. Finally, simulation results demonstrate the advantages of the proposed GAM-3DSC system in effectively transmitting the goal-oriented 3D scenario. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Libad: Accurately and Rapidly Detecting Obfuscated Third-Party Java Libraries in Large-Scale Datasets

SSRN

引用

SSRN 2023年

作者： Zhuo, Wang Zhiyu, Wang Fang, Zuo Hong, Li Jingdong, Guo Weifeng, Wang Xin, Zheng Wenming, Liu School of software Henan University Kaifeng China Institute of Information Engineering Chinese Academy of Sciences Beijing China Henan International Joint Laboratory of Intelligent Network Theory and Key Technology Henan University Kaifeng China Subject Innovation and Intelligence Introduction Base of Henan Higher Educational Institution -Software Engineering Intelligent Information Processing Innovation and Intelligence Introduction Base of Henan University Henan University Kaifeng China

The use of third-party libraries (TPLs) is becoming increasingly prevalent in Java development for optimizing code, however, the widespread use of TPLs poses serious security threats. Existing methods are limited by code obfuscation and version identification, and even more, they lack the ability to detect TPLs on a large-scale ***, we propose a novel method called LibAD that accurately identifies obfuscated TPLs in Java, along with their specific versions, and is suitable for fast detection of large-scale datasets. For TPL detection, we utilize a multi-granularity feature matching approach. A list of candidate TPLs is initially constructed using coarse-grained features, specifically the three levels of TPL class dependency signatures. Thereafter, class-level and method-level obfuscation-resilient features are utilized as fine-grained features to identify a specific TPL *** evaluate the effectiveness of LibAD against a large-scale feature database of TPLs, which comprises 32,488 TPLs with 1,075,630 versions. Our experimental results show that LibAD outperforms state-of-the-art detection tools by achieving 95.42\% and 73.35\% accuracy at the library and version levels, respectively. Furthermore, LibAD performs significantly better than other tools in detecting different code obfuscation techniques. In addition, LibAD demonstrates remarkable efficiency, being almost 400 times faster than LIBLOOM in large-scale experiments. © 2023, The Authors. All rights reserved.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Domain generalization for document authentication against practical recapturing attacks

arXiv

引用

arXiv 2021年

作者： Chen, Changsheng Zhang, Shuzheng Lan, Fengbo Huang, Jiwu The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Recapturing attack can be employed as a simple but effective anti-forensic tool for digital document images. Inspired by the document inspection process that compares a questioned document against a reference sample, we proposed a document recapture detection scheme by employing Siamese network to compare and extract distinct features in a recapture document image. The proposed algorithm takes advantages of both metric learning and image forensic techniques. Instead of adopting Euclidean distance-based loss function, we integrate the forensic similarity function with a triplet loss and a normalized softmax loss. After training with the proposed triplet selection strategy, the resulting feature embedding clusters the genuine samples near the reference while pushes the recaptured samples apart. In the experiment, we consider practical domain generalization problems, such as the variations in printing/imaging devices, substrates, recapturing channels, and document types. To evaluate the robustness of different approaches, we benchmark some popular off-the-shelf machine learning-based approaches, a state-of-the-art document image detection scheme, and the proposed schemes with different network backbones under various experimental protocols. Experimental results show that the proposed schemes with different network backbones have consistently outperformed the state-of-the-art approaches under different experimental settings. Specifically, under the most challenging scenario in our experiment, i.e., evaluation across different types of documents that produced by different devices, we have achieved less than 5.00% APCER (Attack Presentation Classification Error Rate) and 5.56% BPCER (Bona Fide Presentation Classification Error Rate) by the proposed network with ResNeXt101 backbone at 5% BPCER decision *** Codes 94A08 Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation 28

Meet Changes with Constancy: Learning Invariance in Multi-So...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Liu, Jianfeng Luo, Ling Ao, Xiang Song, Yan Xu, Haoran Ye, Jian Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences China Beijing Key Laboratory of Mobile Computing and Pervasive Device China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences China The Chinese University of HongKong Shenzhen China Shenzhen Research Institute of Big Data China

ISBN: (纸本)9781952148279

Multi-source neural machine translation aims to translate from parallel sources of information (e.g. languages, images, etc.) to a single target language, which has shown better performance than most one-to-one systems. Despite the remarkable success of existing models, they usually neglect the fact that multiple source inputs may have inconsistencies. Such differences might bring noise to the task and limit the performance of existing multi-source NMT approaches due to their indiscriminate usage of input sources for target word predictions. In this paper, we attempt to leverage the potential complementary information among distinct sources and alleviate the occasional conflicts of them. To accomplish that, we propose a source invariance network to learn the invariant information of parallel sources. Such network can be easily integrated with multi-encoder based multi-source NMT methods (e.g. multi-encoder RNN and transformer) to enhance the translation results. Extensive experiments on two multi-source translation tasks demonstrate that the proposed approach not only achieves clear gains in translation quality but also captures implicit invariance between different sources. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

A hybrid Chinese named entity recognition method for Internet of Things

A hybrid Chinese named entity recognition method for Interne...

引用

2022 International Conference on Algorithms, Microchips and Network Applications

作者： Wang, Ying Wang, Zehao Li, Hong Liu, Peipei Li, Yachao Zuo, Fang Institute of Intelligence Networks System Henan University Henan475001 China Henan Experimental Teaching Demonstration Centre of Modern Network Technology Henan University Henan475001 China Intelligent Data Processing Engineering Research Center of Henan Province Henan University Henan475001 China Institute of Information Engineering Chinese Academy of Sciences Beijing China Henan International Joint Laboratory of Theories and Key Technologies on Intelligence Networks Henan University Henan475001 China

ISBN: (纸本)9781510653290

In order to facilitate government departments to assess security risks and prevent infiltration, it's necessary to recognize the IoT device from open data by the method of Named entity recognition (NER). In this study, a hybrid method of chinese NER which contains neural networks and templates is proposed to extract IoT device information from open web. The model first initiates characters of input through BERT, which can create character embedding while reduce dependency with external datasets. Then, the initiated vectors are fed into a multi-layers BiLSTM model to encode the contextual representation of each character, and a linear CRF layer after BiLSTM is used to assign the scores to every character for entity annotation. In addition, a dictionary and rule base is constructed based on the characteristics of IoT devices to correct the annotation results. We experimented the methods on the dataset of IoT, the results prove the proposed model achieves better recognition effect than other models, and the F-scores value is 88.9%. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Mining latent structures for multimedia recommendation

arXiv

引用

arXiv 2021年

作者： Zhang, Jinghao Zhu, Yanqiao Liu, Qiang Wu, Shu Wang, Shuhui Wang, Liang Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Artificial Intelligence Research Chinese Academy of Sciences

Multimedia content is of predominance in the modern Web era. Investigating how users interact with multimodal items is a continuing concern within the rapid development of recommender systems. The majority of previous work focuses on modeling user-item interactions with multimodal features included as side information. However, this scheme is not well-designed for multimedia recommendation. Specifically, only collaborative item-item relationships are implicitly modeled through high-order item-user-item relations. Considering that items are associated with rich contents in multiple modalities, we argue that the latent semantic item-item structures underlying these multimodal contents could be beneficial for learning better item representations and further boosting recommendation. To this end, we propose a LATent sTructure mining method for multImodal reCommEndation, which we term LATTICE for brevity. To be specific, in the proposed LATTICE model, we devise a novel modality-aware structure learning layer, which learns item-item structures for each modality and aggregates multiple modalities to obtain latent item graphs. Based on the learned latent graphs, we perform graph convolutions to explicitly inject high-order item affinities into item representations. These enriched item representations can then be plugged into existing collaborative filtering methods to make more accurate recommendations. Extensive experiments on three real-world datasets demonstrate the superiority of our method over state-of-the-art multimedia recommendation methods and validate the efficacy of mining latent item-item relationships from multimodal features. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

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：