检索结果-内蒙古大学图书馆

2007 8th International Conference on Electronic Measurement and Instruments, ICEMI

作者： Hu, Xuelong Yang, Li Zhang, Gensheng School of Information Engineering Yangzhou University Yangzhou 225009 China Jiangsu Province Key Lab. for Image Processing and Communication Nanjing University of Post and Telecommunications Nanjing 215006 China Jiangsu Province Key Lab. for Computer Information Processing Technology Suzhou University Suzhou 215006 China

ISBN: (纸本)1424411351

This paper addresses an effective issue of content-based image retrieval (CBIR) by presenting Fuzzy Hamming Distance (FHD). Firstly, the theory of FHD is introduced, which includes degree of difference and cardinality of the fuzzy set, and then follows defuzzification of FHD which is used as a fuzzy similarity measure. In the experiment, the image retrieval results show this method can be employed to capture implicitly some semantic contents of the image in addition to other features such as color, texture and shape. Finally, an implemented prototype system demonstrates a promising retrieval performance for a test database, as compared with FUZZYCLUB system. © 2007 IEEE.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

A new method for semi-automatic image annotation

A new method for semi-automatic image annotation

引用

2007 8th International Conference on Electronic Measurement and Instruments, ICEMI

作者： Xuelong, Hu Yuhui, Zhang Li, Yang School of Information Engineering Yangzhou University Yangzhou 225009 China Jiangsu Province Key Lab. of Image Processing and Communication Nanjing University of Post and Telecommunications Nanjing 215006 China Jiangsu Province Key Lab. of Computer Information Processing Technology Suzhou University Suzhou 215006 China

ISBN: (纸本)1424411351

Semantic-based image retrieval bridges the gap between visual features and human understanding of image in the field of image retrieval. image annotation is one important technology of image retrieval based on the semantic. This paper proposed one method to realize semi-automatic image annotation with the tool Support Vector Machine (SVM). The image collection was divided into two parts, one for manual annotation and the other for testing. After being classified by SVM, the output was changed into a probability, and K-NN algorithm was applied to get the keywords for unlabeled images. The experiments show that the approach is feasible. © 2007 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Spatio-Temporal Scale Based Affective Neural Network for Emotion Detection in Conversation

A Spatio-Temporal Scale Based Affective Neural Network for E...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Jiang Wang, Xiaoping Lei, Shanglin Zeng, Zhigang Wuhan430074 China Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China Key Laboratory of Brain-inspired Intelligent Systems Hubei Province Wuhan430074 China

ISBN: (纸本)9798350303759

Emotion Detection in Conversation (EDC) has been implemented in numerous domains and is under increasing attention. The EDC task is highly challenging due to the need to incorporate both the context of the utterance and the identity of the participant. Some existing EDC approaches employ redundant network structures and inadequately model contextual utterances, resulting in limited performance gains. In this work, we devise a Spatio-Temporal scale based Affective neural Network (STANet) in a simplistic and efficacious manner. STANet consists of two main components, i.e., spatial scale network and temporal scale network, which are applied to extract spatial scale and temporal scale information in the conversation, respectively. Prior to spatio-temporal scale modeling, we encode the identity information of participants to examine its impact on the performance of emotion detection. We conduct substantial comparative experiments and ablation studies on three conversational emotion datasets, and the results demonstrate that our STANet realizes superior performance without taking advantage of external knowledge. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A novel bimodal emotion database from physiological signals and facial expression

A novel bimodal emotion database from physiological signals ...

引用

作者： Yan, Jingjie Wang, Bei Liang, Ruiyu Jiangsu Provincial Key Laboratory of Image Processing and Image Communication College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing210003 China Research Center for Learning Science Southeast University Nanjing210096 China School of Communication Engineering Nanjing Institute of Technology Nanjing211167 China

In this paper, we establish a novel bimodal emotion database from physiological signals and facial expression, which is named as PSFE. The physiological signals and facial expression of the PSFE database are respectively recorded by the equipment of the BIOPAC MP 150 and the Kinect for Windows in the meantime. The PSFE database altogether records 32 subjects which include 11 women and 21 man, and their age distribution is from 20 to 25. Moreover, the PSFE database records three basic emotion classes containing calmness, happiness and sadness, which respectively correspond to the neutral, positive and negative emotion state. The general sample number of the PSFE database is 288 and each emotion class contains 96 samples. © Copyright 2018 The Institute of Electronics Information and communication Engineers.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Error concealment for stereoscopic images using boundary smooth degree

Error concealment for stereoscopic images using boundary smo...

引用

Asia-Pacific Conference on communications

作者： Guijin Tang Xiuchang Zhu Jiangsu Key Laboratory of Image Processing & Image Communication Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781424447848

Error concealment can be regarded as a sort of error resilient coding techniques. This paper proposes a method to recover lost blocks in stereoscopic images. We first utilize the correlation to perform disparity estimation to match the corresponding blocks for lost ones. And then we calculate the boundary smooth degree (BSD) for each recovered block. If BSD exceeds the threshold, it means that the boundary is discontinuous which mainly results from high detailed blocks, edge blocks or occluded blocks. So we consider neighboring blocks' BSD and estimate the content of a lost block, and adaptively use different methods to conceal it. Experimental results show that the proposed algorithm can greatly improve the subjective and objective quality of the reconstructed image.

关键词： Loss measurement image coding image reconstruction Video sequences image processing image communication Feedback Layout Video coding Newton method

来源：评论

学校读者我要写书评

暂无评论

Partical swarm optimization based unequal loss protection of embedded video streams

Partical swarm optimization based unequal loss protection of...

引用

International Conference on communication Technology (ICCT)

作者： Jiajing Hu Dong Hu The key Laboratory of image processing and image communications of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China

This paper presents a new scheme for optimal packetization of scalable multimedia data over lossy network. By assigning an unequal amount of forward error correction (FEC) bits to each segment of transmission packets, the proposed algorithm protects a progressive bitstream generated by a three-dimensional set partitioning in hierarchical trees (3-D SPIHT) algorithm. The partical swarm optimization (PSO) algorithm is used to reasonably allocate bits between source coding and channel coding across packets. Experimental results show that the proposed algorithm provides close to optimal average peak signal-to-noise ratio performance and that its' running time is significantly lower than that of previously known solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Fast Inter Mode Decision Algorithm for H.264/AVC

An Efficient Fast Inter Mode Decision Algorithm for H.264/AV...

引用

WRI International Conference on communications and Mobile Computing, CMC

作者： Huaibin Huang Dong Hu key Laboratory of image processing and image communications of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China

An efficient fast inter mode decision algorithm for the baseline H.264/AVC video coding is proposed in this paper. The main idea of the algorithm is to reduce the number of candidate modes for rate distortion optimization (RDO) by using early mode detection in four different levels, viz. SKIP mode detection, type detection at macroblock-level, type detection at submacroblock-level and intra modes detection. In addition, the correlation of cost of current MB and the one of previous frame, as well as the cost's monotonous property are both used to help the mode decision. Compared to JM8.6 reference software, our algorithm can save encoding time 71.743% on average with negligible PSNR loss, which is very helpful for H.264/AVC inter frame. encoding.

关键词： Automatic voltage control Costs image coding Encoding Video coding Rate-distortion Video sequences Mobile communication Mobile computing Telecommunication computing

来源：评论

学校读者我要写书评

暂无评论

A probability-based object tracking method

A probability-based object tracking method

引用

4th International Conference on Intelligence Science and Big Data Engineering, IScIDE 2013

作者： Song, Xu Li, Guoqiang Li, Ying Zhang, Yanning Shaanxi Province Key Lab. of Speech and Image Information Processing Northwestern Polytechnical University Xi'an 710129 China Science and Technology on Electro-optic Control Laboratory Louyang 471009 China

ISBN: (纸本)9783642420566

Here we take advantage of the signal recovery power of Compressive Sensing (CS) to significantly reduce the computational complexity brought by the high-dimension image data, then an effective and efficient low-dimensional subspace representation of the object is computing by applying Principal Component Analysis (PCA) to a collection of object observations which are low-dimensional vectors derived from CS. An incremental PCA algorithm is used to update this subspace model for characterizing the object appearance changes. Meanwhile, two distances derived from Probabilistic Principal Component Analysis (PPCA): distance from feature space (DFFS) and distance in feature space (DIFS), are used to describe visual similarity between the learned subspace representation model and candidate targets. Comparing with the traditional used reconstruction error, the sum of two distances: DFFS + DIFS, is more accurate and more robust to noises and partial occlusions. Numerous experiment demonstrate that subspace representation model can handle the situation that target objects experience pose changes, scale changes, significant illumination variation, partial occlusions and so on. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Impulse noise removal in two-dimensional electrophoresis images based on dome recognition 8

Impulse noise removal in two-dimensional electrophoresis ima...

引用

8th International Conference on BioMedical Engineering and Informatics, BMEI 2015

作者： Ou, Qiaofeng Zhang, Huisheng Li, Lixin Xiong, Bangshu School of Electronic Information Northwestern Polytechnical University Xi'an710072 Hong Kong Key Laboratory of Image Processing and Pattern Recognition of Jiangxi Province Nanchang Hangkong University Nanchang330063 China

ISBN: (纸本)9781509000227

Two-dimensional gel electrophoresis (2DE) images are often corrupted by impulse noise in broad sense (including various artifacts, such as fingerprints, hairs, gel cracks, strips, water stains, dust and so on). In this paper, we propose a novel adaptive directional filter (ADF) to remove impulse noise completely and accurately. Firstly, we detect the impulse noise based on the observation that the directional derivative distributions around the protein spot centers and noise pixels are very different. Then, according to the bell-shaped three-dimensional appearance of protein spots, the greatest and smallest gradient directions were used to restore the noised pixels. Lastly, the pixels adjacent to the modified pixels are iteratively detected and restored until no impulse noise is detected. Experimental results on the synthetic and real 2DE images show that the proposed method performs much better than the previous approaches. © 2015 IEEE.

关键词： Pixels

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：