检索结果-内蒙古大学图书馆

2021 China Automation Congress, CAC 2021

作者： Yu, Naigong Xu, Qiao Hasan, Mohammad Mehedi Jiang, Kai Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Computing Intelligence and Intelligent System Beijing China Green Energy and Architechture Research Center China Energy Investment Corporation Beijing China

ISBN: (纸本)9781665426473

Wafer map defect pattern (WMDP) recognition is critical to evaluate the semiconductor manufacturing process. Traditional WMDP recognition algorithms, such as deep learning-based methods, only focus on improving the accuracies of the seen patterns in the training set but ignore the recognition and incremental generalization of new emerging patterns. The model can only be retrained by using the overall dataset composed of new and old patterns to gain the ability to recognize the new patterns. To address the above problems, this paper proposes a WMDP recognition method based on self-organizing incremental neural network. The proposed method detects abnormal patterns according to the relationship between input response and adaptive threshold of winner neurons, updates the model only with new pattern samples by dynamically adjusting the number or connection of neurons. Experiments show that the proposed method has the ability to classify known patterns and discover unknown abnormal patterns. Its unique competitive learning mechanism makes it possible to update the model only with new pattern samples without catastrophic forgetting. © 2021 IEEE

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Facial Micro-Motion-Aware Mixup for Micro-Expression Recognition

Facial Micro-Motion-Aware Mixup for Micro-Expression Recogni...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zhuoyao Gu Miao Pang Zhen Xing Weimin Tan Xuhao Jiang Bo Yan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

Data-driven learning models have demonstrated strong benefits in capturing subtle facial movements for micro-expression recognition (MER), but are limited by the available data. Generative models can generate a variety of new data, but are typically computationally prohibitive compared to efficient Mixup-like methods. In this paper, we propose a novel Facial Micro-Motion-Aware Mixup approach for MER, namely MEMix. Our MEMix constructs a micro-motion-aware mask to select the most salient facial motions and generate a new sample with a mixed motion feature. This mixed motion feature can effectively expand the data distribution, leading to smoother decision boundaries for MER models. To demonstrate the good generality of MEMix, we integrate it with three advanced vision transformer-based models. The results show that the three integrated models consistently achieve performance improvements ranging from 4.07% to 7.32% in accuracy and from 6.54% to 9.18% in F1-score. Besides, to further explore the ability of MEMix, we propose a two-stream network called MixMeFormer, which unlocks the potential of the transformer by simply integrating mixed motion features with facial semantics for MER. Extensive experiments demonstrate that our MixMeFormer outperforms other state-of-the-art methods on three well-known micro-expression datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tissue P systems with rule production/removal 18th

Tissue P systems with rule production/removal

引用

18th International Conference on Membrane computing, CMC 1018

作者： Pan, Linqiang Song, Bosheng Zhang, Gexiang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology WuhanHubei430074 China School of Electric and Information Engineering Zhengzhou University of Light Industry ZhengzhouHenan450002 China Robotics Research Center and Key Laboratory of Fluid and Power Machinery Xihua University Chengdu610039 China

ISBN: (纸本)9783319733586

Tissue P systems are computational models inspired by the way of biochemical substance movement/exchange between two cells or between a cell and the environment, where all communication (symport/antiport) rules used in a system are initially set up and keep unchanged during any computation. In this work, a variant of tissue P systems, called tissue P systems with rule production/removal (abbreviated as TRPR P systems) is considered, where rules in a system are dynamically changed during a computation, that is, at any computation step new rules can be produced and some existing rules can be removed. The computation power of TRPR P systems is investigated. It is proved that Turing universality is achieved for TRPR P systems with one cell, and using symport rules of length at most 1, antiport rules of length at most 2 or symport rules of length at most 2 and working in a maximally parallel manner. We further show that TRPR P systems with two cells, using symport rules of length at most 1, and working in a flat maximally parallel manner, are Turing universal. © 2018, Springer International Publishing AG.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Improving Classroom Quality by Analyzing Student Behaviors Through Computer Vision 4

Improving Classroom Quality by Analyzing Student Behaviors T...

引用

4th International Conference on information Science and Education, ICISE-IE 2023

作者： Chen, Xiaopan Li, Boyuan Zhu, Xiaoke Zhang, Tao School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology Henan University Kaifeng China Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China

ISBN: (纸本)9798350394610

This paper aims to enhance the efficiency of teaching and learning by leveraging computer vision technology for automated analysis of student behavior in the classroom. We propose a feature-enhanced method for recognizing student behavior, which integrates an Upsampling module (UPS) and a convolutional block layer (CBL) module into the YOLOv5 model. This innovative approach significantly improves the detection and feature extraction capabilities for student targets, effectively addressing challenges associated with small-sized targets and lowresolution images. Through algorithm optimization, it achieves a balance in sample diversity, enhancing the model's adaptability and generalizability in complex classroom environments. Building upon these technological advancements, we have developed a Classroom Student Posture Perception System (CSP2S). This system integrates functions for data collection, student behavior detection, and result visualization. The CSP2S operates in realtime by capturing and analyzing students' behavioral dynamics while providing teachers with immediate feedback. Experimental results demonstrate that this system substantially reduces teachers' workload in student assessment, offering significant potential to improve teaching effectiveness. These robust technical advancements provide strong support for future applications in real educational environments. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Deep Feature Fusion for Vehicle Re-Identification

Multi-Scale Deep Feature Fusion for Vehicle Re-Identificatio...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Yiting Cheng Chuanfa Zhang Kangzheng Gu Lizhe Qi Zhongxue Gan Wenqiang Zhang Shanghai Key Laboratory of Intelligent Information Processing Fudan University Academy for Engineering & Technology Fudan University

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

Vehicle re-identification (re-id) is challenging due to the small inter-class distance. The differences between similar vehicles can be extremely subtle and only captured at particular scales and semantic levels. In this paper, we propose a novel Multi-Scale Deep Feature Fusion Network (MSDeep) to conduct both multi-scale and multi-level features for precise vehicle re-id. Based on the backbone deep CNN, MS-Deep mainly consists of two modules: 1) Multi-Scale Fusion (MSF) Block which encapsulates combination of multi-scale streams as MSF feature;2) Multi-Level Fusion (MLF) Block which fuses MSF features of multiple levels to build the final descriptor. Importantly, in MSF, Multi-Scale Attention (MSA) is introduced to dynamically emphasize important channels of each scale, and Level-Wise Attention(LWA) is utilized in MLF to determine the different weightings for each MSF feature of different levels. As a result, experiments show that our MSDeep outperforms state-of-the-art algorithms on challenging VeRi and VehicleID benchmarks in terms of abundant and hierarchical hyper-descriptors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance for Class Incremental Learning in Medical Image Classification

arXiv

引用

arXiv 2024年

作者： Hao, Xuze Ni, Wenqian Jiang, Xuhao Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Deep convolutional neural networks have made significant breakthroughs in medical image classification, under the assumption that training samples from all classes are simultaneously available. However, in real-world medical scenarios, there’s a common need to continuously learn about new diseases, leading to the emerging field of class incremental learning (CIL) in the medical domain. Typically, CIL suffers from catastrophic forgetting when trained on new classes. This phenomenon is mainly caused by the imbalance between old and new classes, and it becomes even more challenging with imbalanced medical datasets. In this work, we introduce two simple yet effective plug-in methods to mitigate the adverse effects of the imbalance. First, we propose a CIL-balanced classification loss to mitigate the classifier bias toward majority classes via logit adjustment. Second, we propose a distribution margin loss that not only alleviates the inter-class overlap in embedding space but also enforces the intra-class compactness. We evaluate the effectiveness of our method with extensive experiments on three benchmark datasets (CCH5000, HAM10000, and EyePACS). The results demonstrate that our approach outperforms state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A general approach to extracting full names and abbreviations for Chinese entities from the web

A general approach to extracting full names and abbreviation...

引用

作者： Jiang, Guang Cungen, Cao Yuefei, Sui Lu, Han Wang, Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences No.6 Kexueyuan South Road Zhongguancun Beijing 100190 China Graduate University of Chinese Academy of Sciences No.19 Yuquan Road Shi Jing Shan Distinct Beijing 100049 China

ISBN: (纸本)3642163262

Identifying Full names/abbreviations for entities is a challenging problem in many applications, e.g. question answering and information retrieval. In this paper, we propose a general extraction method of extracting full names/abbreviations from Chinese Web corpora. For a given entity, we construct forward and backward query items and commit them to a search engine (e.g. Google), and utilize search results to extract full names and abbreviations for the entity. To verify the results, filtering and marking methods are used to sort all the results. Experiments show that our method achieves precision of 84.7% for abbreviations, and 77.0% for full names. © 2010 IFIP.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Novel constructions of complex orthogonal designs for space-time block codes

Novel constructions of complex orthogonal designs for space-...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Yuan Li Chen Yuan Haibin Kan Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9781467307734;9781467307758

Complex orthogonal designs (CODs) are used to construct space-time block codes in wireless transmission. COD O z with parameter [p, n, k] is a p × n matrix, where nonzero entries are filled by ±z i or ±z i * , i = 1, 2, ..., k, such that equation. In practice, n is the number of antennas, k=p the code rate, and p the decoding delay. One fundamental problem is to construct COD to maximize k/p and minimize p when n is given. Recently, this problem is completely solved by Liang and Adams et al. It's proved that when n = 2m or 2m - 1, the maximal possible rate is (m + 1)/(2m) and the minimum delay ( m-1 2m )(with the only exception n ≡2 (mod 4) where it is 2( m-1 2m )). However, when the number of antennas increase, the minimum delay grows fast and eats the otherwise fast decoding. For example, when n = 14 the minimal delay for a code with maximal rate is 6006! Therefore, it is very important to study whether it is possible, by lowering the rate slightly, to shorten the decoding delay considerably. In this paper, we demonstrate this possibility by constructing a series of CODs with parameter [p, n, k] = [( w - 1 n )+( w + 1 n ), n, ( w n )], where 0 ≤ w ≤ n. Besides that, all optimal CODs, which achieve the maximal rate and minimal delay, are contained in our explicit-form constructions. And this is the first explicit-form construction, while the previous are recursive or algorithmic.

关键词： Delay Vectors Maximum likelihood decoding Block codes Transceivers Antennas

来源：评论

学校读者我要写书评

暂无评论

An improved multi-attribute decision-making based network selection algorithm for heterogeneous vehicular network

引用

Frontiers of Computer Science 2022年第3期16卷 211-213页

作者： Lei NIE Bo LIU Peng LI Heng HE Libing WU School of Computer Science and Technology Wuhan University of Science and TechnologyWuhan 430065China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan 430065China School of Cyber Science and Engineering and School of Computer Science Wuhan UniversityWuhan 430072China Shenzhen Research Institute of Wuhan University Shenzhen 518057China

1 Introduction With sharply rising quantity of urban vehicles over the past few decades,traffic jams and safety have gradually become outstanding *** recent years,Vehicular Ad hoc Network(VANET)is appeared and utilized to solve traffic related *** is a type of self-organized and open-structured network,and provides Vehicle-to-Everything(V2X)*** all kinds of applications in VANET rely on efficient data transmission and interaction[1-3].

关键词： network sharply utilized

来源：评论

学校读者我要写书评

暂无评论

SPEECHTOKENIZER: UNIFIED SPEECH TOKENIZER FOR SPEECH LANGUAGE MODELS

arXiv

引用

arXiv 2023年

作者： Zhang, Xin Zhang, Dong Li, Shimin Zhou, Yaqian Qiu, Xipeng School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Fudan University

Current speech large language models build upon discrete speech representations, which can be categorized into semantic tokens and acoustic tokens. However, existing speech tokens are not specifically designed for speech language modeling. To assess the suitability of speech tokens for building speech language models, we established the first benchmark, SLMTokBench. Our results indicate that neither semantic nor acoustic tokens are ideal for this purpose. Therefore, we propose SpeechTokenizer, a unified speech tokenizer for speech large language models. SpeechTokenizer adopts the Encoder-Decoder architecture with residual vector quantization (RVQ). Unifying semantic and acoustic tokens, SpeechTokenizer disentangles different aspects of speech information hierarchically across different RVQ layers. Furthermore, We construct a Unified Speech Language Model (USLM) leveraging SpeechTokenizer. Experiments show that SpeechTokenizer performs comparably to EnCodec in speech reconstruction and demonstrates strong performance on the SLMTokBench benchmark. Also, USLM outperforms VALL-E in zero-shot Text-to-Speech tasks. Code and models are available at https://***/ZhangXInFD/SpeechTokenizer/. © 2023, CC BY-SA.

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：