检索结果-内蒙古大学图书馆

SibNet: Sibling convolutional encoder for Video Captioning

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2021年第9期43卷 3259-3272页

作者： Liu, Sheng Ren, Zhou Yuan, Junsong Univ Buffalo Dept Comp Sci & Engn Buffalo NY 14260 USA Wormpex AI Res Seattle WA 98004 USA

Visual captioning, the task of describing an image or a video using one or few sentences, is a challenging task owing to the complexity of understanding the copious visual information and describing it using natural language. Motivated by the success of applying neural networks for machine translation, previous work applies sequence to sequence learning to translate videos into sentences. In this work, different from previous work that encodes visual information using a single flow, we introduce a novel Sibling convolutional encoder (SibNet) for visual captioning, which employs a dual-branch architecture to collaboratively encode videos. The first content branch encodes visual content information of the video with an autoencoder, capturing the visual appearance information of the video as other networks often do. While the second semantic branch encodes semantic information of the video via visual-semantic joint embedding, which brings complementary representation by considering the semantics when extracting features from videos. Then both branches are effectively combined with soft-attention mechanism and finally fed into a RNN decoder to generate captions. With our SibNet explicitly capturing both content and semantic information, the proposed model can better represent the rich information in videos. To validate the advantages of the proposed model, we conduct experiments on two benchmarks for video captioning, YouTube2Text and MSR-VTT. Our results demonstrate that the proposed SibNet consistently outperforms existing methods across different evaluation metrics.

关键词： Visualization Decoding Semantics Task analysis Feature extraction Pipelines Natural languages SibNet video captioning autoencoder visual-semantic joint embedding convolutional encoder

来源：评论

学校读者我要写书评

暂无评论

Some interesting dual-code properties of convolutional encoder for standards self-recognition

引用

IET COMMUNICATIONS 2012年第8期6卷 931-935页

作者： Marazin, M. Gautier, R. Burel, G. Univ Europeenne Bretagne Brest France Univ Brest F-29238 Brest 3 France CNRS UMR 3192 Lab STICC ISSTB F-29238 Brest 3 France

For enhancement of the quality of digital transmissions, standards are in continual evolution, which generates compatibility problems. Cognitive radio systems permit one to solve this problem through the design of intelligent receivers. However, such receivers must be able to adapt themselves to a specific transmission context. This requires the development of new methods in order to blindly estimate error-correcting codes. Coding schemes such as turbocode, composed of convolutional codes, belong to a family of error-correcting codes in use in many standards. In most of the methods designed to identify convolutional encoders the algebraic properties are used implicitly. However usually, these dedicated properties are neither explicated, nor detailed, nor demonstrated. The study reported here investigates the algebraic properties of convolutional encoders, useful for blind recognition methods in the cognitive radio context and more specially the algebraic relationships between different forms of a convolutional code and its corresponding dual code. Moreover, some simulation results are presented to show the relevance of these properties for the blind identification of the convolutional encoder.

关键词： dual codes convolutional codes Codes error-correcting code estimation dual-code properties encoding cognitive radio system coding scheme radio receivers error correction codes standards self-recognition transmission context blind recognition method turbocode algebraic properties algebraic codes blind identification turbo codes Radio links and equipment cognitive radio intelligent receiver convolutional encoder digital transmission quality

来源：评论

学校读者我要写书评

暂无评论

The Effect of convolutional encoder Memory on The Sphere Decoding Search Radius in MIMO Systems

The Effect of Convolutional Encoder Memory on The Sphere Dec...

引用

21st Signal Processing and Communications Applications Conference (SIU)

作者： Karakus, Oktay Altinkaya, Mustafa A. Kilicaslan, Kagan Izmir Yuksek Teknol Enstitusu Elekt Elekt Muhendisligi Bolumu Izmir Turkey

ISBN: (纸本)9781467355636;9781467355629

In the new generation communication systems Multiple-Input-Multiple-Output systems are frequently used. The processing load of the Maximum Likelihood (ML) Detector which is the optimum detector for these systems, increases exponentially as a function of system dimension and memory due to testing all possible points. Sphere Decoding (SD) method which tests only the probable points, decreases the processing load dramatically. System memory changes by system dimensions and length of the convolutional encoder. This, in turn, affects the radius of the hyper sphere centered at the observation in the observation space at which SD attains the performance of the ML detector. This effect is investigated via simulation studies. In these simulations, it is observed that the radius of the SD is relatively smaller than the one in ML, and the ratio between the radius values varies from 6,61 in the case of memoryless 2x2 MIMO system to 1,02 in the case of 8x8 MIMO system with memory K=10 according to increased antenna numbers and system memory. In addition to these, it is observed that the radius of the hyper sphere is directly proportional to the memory of the encoder.

关键词： Multiple-Input-Multiple-Output systems Maximum Likelihood Sphere Decoding convolutional encoder

来源：评论

学校读者我要写书评

暂无评论

Blind Channel Coding Identification of convolutional encoder and Reed-Solomon encoder using Neural Networks 26

Blind Channel Coding Identification of Convolutional encoder...

引用

26th National Conference on Communications (NCC)

作者： Gautam, Naveenta Lall, Brejesh Indian Inst Technol Bharti Sch Telecommun Technol & Management Delhi India Indian Inst Technol Dept Elect Engn Delhi India

ISBN: (纸本)9781728151205

Forward error correcting (FEC) codes are used to improve the reliability of digital communication systems. They introduce redundancy in the signal which helps the receiver to correct errors without requesting for re transmission. FEC codes can be classified into two categories : convolutional codes and linear block codes (LBCs). Reed-Solomon (RS) codes lie in the category of LBCs. For non-cooperative communication applications such as adaptive modulation and coding (AMC), military applications and cognitive radio, the channel encoder has to be identified blindly for decoding the received signal. In this study, we propose a scheme for blind identification of convolutional and RS codes. We have used the pattern recognition properties of a neural network (NN) to identify the encoder from a candidate set. NNs have not been used for this purpose, to the best of our knowledge. Performance of the proposed classifier has been evaluated for both the noiseless and the noisy case. To show the application of the proposed approach we present the performance results for the two most common use cases namely the terrestrial wireless and the satellite communication channels. Experimental results have shown that the proposed classifier can identify the encoder with high accuracy in low signal-to-noise ratio.

关键词： Blind Identification channel parameter estimation RS encoder convolutional encoder neural network machine learning

来源：评论

学校读者我要写书评

暂无评论

Dual code method for blind identification of convolutional encoder for cognitive radio receiver design

Dual code method for blind identification of convolutional e...

引用

IEEE Globecom Workshops (Gc Workshops 2009)

作者： Marazin, M. Gautier, R. Burel, G. Univ Europeenne Bretagne Rennes France

ISBN: (纸本)9781424456246

Digital communication systems are in perpetual evolution in order to respond to the new user expectations and to new applications transmissions constraints, in term of data rate or reliability. With this fast development of new communication standards, it becomes very difficult for users and also for communications devices producers, to stay compatible with all standards used and with the oncoming ones. For that reason, cognitive radio systems seem to provide an interesting solution to this problem. The conception of intelligent receiver able to adapt itself to a specific transmission context and to blindly estimate the transmitter parameters is a promising solution for the future. In such context, new coding schemes like turbocodes, Low-Density Parity-Check (LDPC) or concatenated codes are developed to increase transmission robustness without significant degradation of the data rate. It is why we have developed a method, described in this paper, dedicated to the blind identification of convolutional encoders usually used in many standards. Moreover, an analysis of the method performances is detailed.

关键词： Cognitive radio intelligent receiver blind identification convolutional encoder dual code

来源：评论

学校读者我要写书评

暂无评论

RTL Design and VLSI Implementation of an efficient convolutional encoder and Adaptive Viterbi Decoder

RTL Design and VLSI Implementation of an efficient Convoluti...

引用

2nd IEEE International Conference on Communications and Signal Processing (ICCSP)

作者： Suganya, G. S. Kavya, G. Prathyusha Inst Technol & Management Dept Appl Elect Thiruvallur Chennai Tamil Nadu India

ISBN: (纸本)9781467348669;9781467348652

This paper focuses on the realization of an efficient logic design of a crypto system. The type of crypto system considered in this paper is convolutional encoder and adaptive Viterbi decoder (AVD) with a constraint length, K of 3 and a code rate (k/n) of 1/2 using field programmable gate array (FPGA) technology. Here, the features of convolutional encoder and decoder architecture are introduced and the way it can be implementable as an ASIC. Here the Viterbi Decoder is designed for faster decoding speed and less routing area with a special path management unit. The system is realized using Verilog HDL. It is simulated and synthesized using Modelsim Altera Starter Edition 6.6d and Xilinx 9.1 for RTL Design.

关键词： convolutional encoder Viterbi Decoder Verilog HDL FPGA PNPH Unit

来源：评论

学校读者我要写书评

暂无评论

Implementation of convolutional encoder and Viterbi Decoder using VHDL

Implementation of Convolutional Encoder and Viterbi Decoder ...

引用

IEEE Student Conference on Research and Development

作者： Wong, Yin Sweet Ong, Wen Jian Chong, Jin Hui Ng, Chee Kyun Noordin, Nor Kamariah Univ Putra Malaysia Fac Engn Dept Comp & Commun Syst Engn Serdang 43400 Selangor Malaysia

ISBN: (纸本)9781424451876

This work focuses on the realization of convolutional encoder and adaptive Viterbi decoder (AVD) with a constraint length, K of 3 and a code rate (k/n) of 1/2 using field-programmable gate array (FPGA) technology. This paper presents a 4-state, radix-2, hard decision AVD which has the ability to decode adaptively through different traceback length (TL). The performance of the implemented AVD is analyzed by using ISE 9.2 and MATLAB simulations. The AVD is targeted to a Xilinx XCV300PQ240-4 FPGA device for hardware realization. The decoder parameter TL can be reconfigured via the implementation of AVD, in accordance with the changing channel noise characteristics of the threshold signal-to-noise ratio (SNR), which is 6 dB. The synthesis results show that the reconfiguration parameter TL of 4 and 15 of AVD implementation has significant difference (>20% improvement) in FPGA device utilization. The results also show that the use of reconfiguration leads to a 28% area occupancy of slice usage improvement over a TL of 15 model compared to a TL of 4 model with tolerable loss of decode accuracy, in accordance with the bit error rate (BER) for real-time voice and video.

关键词： convolutional encoder Viterbi decoder VHDL FPGA

来源：评论

学校读者我要写书评

暂无评论

Amplitude Modulation and convolutional encoder Techinques for Gait Speed Classification 23

Amplitude Modulation and Convolutional Encoder Techinques fo...

引用

23rd International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Elkurdi, Abdulhakim Caliskanelli, Ipek Nefti-Meziani, Samia Univ Salford Comp Sci & Engn Manchester Lancs England Univ Salford Autonomous Syst & Adv Robot Ctr Manchester Lancs England

ISBN: (纸本)9781538643259

Human gait analysis can provide vital information especially with optical sensor to track and asses the changes in gait pattern. In this paper, the Kinect v2 based system is used for classifying a several walk speeds and convolutional encoder (CE) technique is validated. Positional skeletal data is collected from the lower body's joints and Amplitude Modulation (AM) is used to modify gait signal for extracting the gait features namely baseband frequency and modulation index. The obtained results show that 97.8% of the considered parameters are appropriate for classifying between three kinds of walk speeds.

关键词： gait analysis convolutional encoder amplitude modulation principle component analysis Hamming distance

来源：评论

学校读者我要写书评

暂无评论

RTL Design and VLSI Implementation of an efficient convolutional encoder and Adaptive Viterbi Decoder

RTL Design and VLSI Implementation of an efficient Convoluti...

引用

International Conference on Communication and Signal Processing

作者： G.S. Suganya G. kavya Department of Applied Electronics Prathyusha Institute of Technology and Management Thiruvallur Chennai. Department of Electronics and Communication Engineering Prathyusha Institute of Technology and Management Thiruvallur Chennai.

ISBN: (纸本)9781467348652

This paper focuses on the realization of an efficient logic design of a crypto system. The type of crypto system considered in this paper is convolutional encoder and adaptive Viterbi decoder (A VD) with a constraint length, K of 3 and a code rate (k/n) of 1/2 using field programmable gate array (FPGA) technology. Here, the features of convolutional encoder and decoder architecture are introduced and the way it can be implementable as an ASIC. Here the Viterbi Decoder is designed for faster decoding speed and less routing area with a special path management unit. The system is realized using Verilog HDL. It is simulated and synthesized using Modelsim Altera Starter Edition 6.6d and Xilinx 9.1 for RTL Design.

关键词： convolutional encoder Viterbi Decoder Verilog HDL FPGA PNPH Unit

来源：评论

学校读者我要写书评

暂无评论

Integrating wavelet transformation for end-to-end direct signal classification

引用

DIGITAL SIGNAL PROCESSING 2025年 156卷

作者： Ribeiro-Filho, Otavio, V Ponti, Moacir A. Curilem, Millaray Rios, Ricardo A. Itau Unibanco Sao Paulo Brazil Univ Sao Paulo Inst Math & Comp Sci Sao Carlos Brazil Univ La Frontera Dept Ingn Elect Temuco Chile Univ Fed Bahia Inst Comp Salvador Brazil

In addressing temporal dependencies within data, specifically in signal analysis, the integration of Deep Neural Networks (DNN) has demonstrated notable improvements when coupled with a preprocessing stage designed for extracting implicit information. In this context, the widely adopted Wavelet Transform (WT) has garnered attention for its remarkable results. However, inherent challenges, such as the imperative definition of parameters for optimal information extraction across diverse scales and resolutions, as well as the prerequisite batch conversion of signals prior to network training, underscore the need for innovative solutions. In response to these challenges, the main contribution of this manuscript is a novel DNN architecture to replace the preprocessing phase. This architecture produces output characteristics resembling those derived from WT, preventing the necessity for a preceding batch execution. Our contribution not only stands as an independent solution but also seamlessly integrates with other modeling techniques, eliminating the prerequisite for the upfront execution of any wavelet transformations. To assess its performance, our methodology undergoes rigorous evaluation against DNNs in classifying signals from real-world applications. Our findings indicate the promising potential of end-to- end schemes in advancing signal analysis applications.

关键词： Deep neural network Signal processing Wavelet transform convolutional encoder Local field potential Seismic signals

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：