检索结果-内蒙古大学图书馆

A new video images text localization approach based on a fast hough transform

3rd International Conference on Image Analysis and Recognition, ICIAR 2006

作者： Bouaziz, Bassem Mahdi, Walid Hamadou, Abdelmajid Ben MIRACL Multimedia InfoRmation System and Advanced Computing Laboratory Higher Institute of Computer Science and Multimedia BP 1030 Sfax 69042 Tunisia

ISBN: (纸本)3540448918

The amount of digital video data is increasing over the world. It highlights the need for efficient algorithms that can retrieve this data by content. The full use of this media is currently limited by the opaque nature of the video which prevents content-based access. To facilitate video indexing and browsing, it is essential to allow non-linear access, especially for long programs. This can be achieved by identifying semantic description captured automatically from video story structure. Among these descriptions, text within video frames is considered as rich features that enable a good way for browsing video. In this paper we propose a fast Hough transformation based approach for automatic video frames text localization. Experimental results, that we drove on a large sample of video images issued from portions of news broadcasts, sports program, advertisements and movies, shows that our method is very efficient, capable to locate text regions with different character sizes, directions and styles even in case of complex image background. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

A property grammar-based method to enrich the arabic treebank ATB 7

引用

7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015

作者： Bahloul, Raja Bensalem Haddar, Kais Blache, Philippe Multimedia InfoRmation Systems and Advanced Computing Laboratory Higher Institute of Computer Science and Multimedia Sfax Tunisia Laboratoire Parole et Langage CNRS Université de Provence Marseille France

ISBN: (纸本)9783319527574

We present a method based on the formalism of Property Grammars to enrich the Arabic treebank ATB with syntactic constraints (so-called properties). The Property Grammar formalism is an effectively constraint-based approach that directly specifies the constraints on information categories. This can facilitate the enrichment process. The latter is based on three phases: the problem formalization, the Property Grammar induction from the ATB and the treebank regeneration with a new syntactic property-based representation. The enrichment of the ATB can make it more useful for many NLP applications such as the ambiguity resolution. This allows also the acquisition of new linguistic resources and the ease of the probabilistic parsing process. This enrichment process is purely automatic and independent from any language and source corpus formalism. This motivates its reuse. We obtained good and encouraging experiment results and various properties of different types. © Springer International Publishing AG 2016.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Deep support vector machines for speech emotion recognition 19th

Deep support vector machines for speech emotion recognition

引用

19th International Conference on Intelligent systems Design and Applications, ISDA 2019

作者： Aouani, Hadhami Ben Ayed, Yassine National School of Engineers ENIS University of Sfax Sfax Tunisia Multimedia InfoRmation Systems and Advanced Computing Laboratory MIRACL University of Sfax Sfax Tunisia

ISBN: (纸本)9783030493417

Speech Emotions recognition has become the active research theme in speech processing and in applications based on human-machine interaction. In this work, our system is a two-stage approach, namely feature extraction and classification engine. Firstly, two sets of feature are investigated which are: the first one is extracting only 13 Mel-frequency Cepstral Coefficient (MFCC) from emotional speech samples and the second one is applying features fusions between the three features: zero crossing rate (ZCR), Teager Energy Operator (TEO), and Harmonic to Noise Rate (HNR) and MFCC features. Secondly, we use two types of classification techniques which are: the Support Vector Machines (SVM) and the k-Nearest Neighbor (k-NN) to show the performance between them. Besides that, we investigate the importance of the recent advances in machine learning including the deep kernel learning. A large set of experiments are conducted on Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of our experiments showed given good accuracy compared with the previous studies. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Rocchio's model based on vector space basis change for pseudo relevance feedback

Rocchio's model based on vector space basis change for pseud...

引用

3rd Symposium on Languages, Applications and Technologies, SLATE 2014

作者： Mbarek, Rabeb Tmar, Mohamed Hattab, Hawete Sfax University Multimedia Information Systems and Advanced Computing Laboratory Sfax Tunisia Umm Al-qura University Department of Mathematics Makkah Saudi Arabia

ISBN: (纸本)9783939897682

Rocchio's relevance feedback model is a classic query expansion method and it has been shown to be effective in boosting information retrieval performance. The main problem with this method is that the relevant and the irrelevant documents overlap in the vector space because they often share same terms (at least the terms of the query). With respect to the initial vector space basis (index terms), it is difficult to select terms that separate relevant and irrelevant documents. The Vector Space Basis Change is used to separate relevant and irrelevant documents without any modification on the query term weights. In this paper, first, we study how to incorporate Vector Space Basis Change into the Rocchio's model. Second, we propose Rocchio's models based on Vector Space Basis Change, called VSBCRoc models. Experimental results on a TREC collection show that our proposed models are effective. © Rabeb Mbarek, Mohamed Tmar, and Hawete Hattab.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

A recursive methodology for radical communities' detection on social networks 24

A recursive methodology for radical communities' detection o...

引用

24th KES International Conference on Knowledge-Based and Intelligent information and Engineering systems, KES 2020

作者： Rekik, Amal Jamoussi, Salma Hamadou, Abdelmajid Ben Multimedia InfoRmation systems and Advanced Computing Laboratory MIRACL University of Sfax 3021 Tunisia Digital Research Center of Sfax DRCS Sfax3021 Tunisia

In the recent years, radical communities have become very aware of the enormous impact of social networks around the world. Thus, these latter are being frequently explored by these groups. Therefore, penetrating into these communities by analyzing both their interactions and their shared content is a considerably challenging task that serves to counter the online radicalization. For this purpose, in this paper, we propose a new recursive methodology for radical communities' detection on social networks based on the analysis and extraction of their violent used vocabulary. Our methodology consists mainly on extracting recursively a set of dangerous profiles from Twitter based on their suspicious interactions. Then, we analyze their textual shared data in order to construct a rich glossary containing their violent used vocabulary. This glossary is exploited and enriched to detect recursively radical communities. Finally, in order to evaluate the performance of our methodology, we resort to an expert who verifies both the list of the dangerous extracted profiles and the violent constructed glossary. The given results show the effectiveness and efficiency of our method. © 2020 The Authors. Published by Elsevier B.V.

关键词： Glossaries

来源：评论

学校读者我要写书评

暂无评论

Semantic multimedia search: the case of SMIL documents

Semantic multimedia search: the case of SMIL documents

引用

4th International Conference on Web and information Technologies, ICWIT 2012

作者： Chkiwa, Mounira Jedidi, Anis Université de Sfax MIRACL Multimedia Information Systems and Advanced Computing Laboratory B.P. 242 Sakiet Ezziet 3021 Sfax Tunisia

Since the first implementations of its principles, the Semantic Web presented a field of free work to ensure its integration and adaptation to the various domains of research. The application of Semantic Web technologies into the process of search in a collection of SMIL documents appears a promising initiative seen the evolution of this language through its various versions. In this paper we propose a semantic search tool in a collection of SMIL documents;this tool adopts a procedure composed of three modules: description, interrogation and representation of the results. We employ for the first module metadata commonly used to annotate information semantically, and for the second we solicit languages of Semantic Web such as RDF, OWL and SPARQL and seen the importance of collaboration of ontologies in the semantic description of multimedia resources, we also present the technique of concepts connection allowing to extend an initial ontology.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Hybrid phase-locked loop with fast locking time and low spur in a 0.18-μm CMOS process

引用

Chinese Physics B 2014年第7期23卷 748-753页

作者：朱思衡司黎明郭超史君宇朱卫仁 Beijing Key Laboratory of Millimeter Wave and Terahertz Technology Department of Electronic Engineering School of Information and ElectronicsBeijing Institute of Technology Advanced Computing and Simulation Laboratory (AχL) Department of Electrical and Computer Systems EngineeringMonash University

We propose a novel hybrid phase-locked loop （PLL） architecture for overcoming the trade-off between fast locking time and low spur. To reduce the settling time and meanwhile suppress the reference spurs, we employ a wide-band single-path PLL and a narrow-band dual-path PLL in a transient state and a steady state, respectively, by changing the loop bandwidth according to the gain of voltage controlled oscillator （VCO） and the resister of the loop filter. The hybrid PLL is implemented in a 0.18-μm complementary metal oxide semiconductor （CMOS） process with a total die area of 1.4×0.46 mm2. The measured results exhibit a reference spur level of lower than -73 dB with a reference frequency of 10 MHz and a settling time of 20 μs with 40 MHz frequency jump at 2 GHz. The total power consumption of the hybrid PLL is less than 27 mW with a supply voltage of 1.8 V.

关键词： phase-locked loop （PLL） fast locking time low spur complementary metal oxide semiconductor（CMOS）

来源：评论

学校读者我要写书评

暂无评论

Parameter-efficient fine-tuning of Whisper for low-resource speech recognition 5

Parameter-efficient fine-tuning of Whisper for low-resource ...

引用

5th International Seminar on Artificial Intelligence, Networking and information Technology, AINIT 2024

作者： Liu, Yunpeng Qu, Dan School of Information Systems Engineering University of Information Engineering Laboratory For Advanced Computing and Intelligence Engineering Department of Artificial Intelligence Henan China Systems Engineering University of Information Engineering Laboratory For Advanced Computing and Intelligence Engineering Henan China

ISBN: (纸本)9798350385557

Limited data availability remains a significant challenge for Whisper's low-resource speech recognition performance, falling short of practical application requirements. While previous studies have successfully reduced the recognition error rates of target language speech through fine-tuning, a comprehensive exploration and analysis of Whisper's parameter-efficient fine-tuning capabilities, the advantages and disadvantages are still lacking. This paper aims to fill this gap by conducting comprehensive experimental exploration for Whisper's low-resource speech recognition performance using two parameter-efficient fine-tuning strategies with limited supervised data from multiple low-resource languages. The results and analysis demonstrate that all fine-tuning strategies explored in this paper significantly enhance Whisper's performance. However, different strategies vary in their suitability and practical effectiveness, highlighting the need for careful selection based on specific use cases and resources available. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

CrossViT Wide Residual Squeeze-and-Excitation Network for Alzheimer's disease classification with self attention ProGAN data augmentation

引用

International Journal of Hybrid Intelligent systems 2021年第3-4期17卷 163-177页

作者： Kadri, Rahma Bouaziz, Bassem Tmar, Mohamed Gargouri, Faiez Multimedia InfoRmation Systems and Advanced Computing Laboratory Miracl University of Sfax Tunisia Sfax Tunisia Faculty of Economics and Management of Sfax Fseg Sfax University of Sfax Tunisia Sfax Tunisia

Efficient and accurate early prediction of Alzheimer's disease (AD) based on the neuroimaging data has attracted interest from many researchers to prevent its progression. Deep learning networks have demonstrated an optimal ability to analyse large-scale multimodal neuroimaging for AD classification. The most widely used architecture of deep learning is the Convolution neural networks (CNN) that have shown great potential in AD detection. However CNN does not capture long range dependencies within the input image and does not ensure a good global feature extraction. Furthermore, increasing the receptive field of CNN by increasing the kernels sizes can cause a feature granularity loss. Another limitation is that CNN lacks a weighing mechanism of image features;the network doesn't focus on the relevant features within the image. Recently,vision transformer have shown an outstanding performance over the CNN and overcomes its main limitations. The vision transformer relies on the self-attention layers. The main drawbacks of this new technique is that it requires a huge amount of training data. In this paper, we combined the main strengths of these two architectures for AD classification. We proposed a new method based on the combination of the Cross ViT and Wide Residual Squeeze-and-Excitation Network. We acquired MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS). We also proposed a new data augmentation based on the self attention progressive generative adversarial neural network to overcome the limitation of the data. Our proposed method achieved 99% classification accuracy and outperforms CNN models. © 2021 - IOS Press. All rights reserved.

关键词： AD classification CNN CrossViT self attention ProGAN wide residual squeeze-and-excitation network

来源：评论

学校读者我要写书评

暂无评论

Towards collaborative research and education in computer architecture with the Archer system

Towards collaborative research and education in computer arc...

引用

International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication systems

作者： Venkatasubramanian, Girish Wolinsky, David Isaac Figueiredo, Renato J. Advanced Computing and Information Systems Laboratory University of Florida Gainesville FL United States

ISBN: (纸本)9780769541976

Archer is a simulation environment and computing resource for research in the field of computer architecture. Archer facilitates the creation of an on-demand computing grid, the deployment of simulation tools on this grid and the batch-scheduling of large-scale simulation jobs on this grid. These features enable the use of Archer for simulation-based research as well as dissemination of tools and results among multiple research groups. This paper overviews and reports our experience in the use of Archer for collaborative research and for education. © 2010 IEEE.

关键词： Computer architecture

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：