检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： Aihua Zheng Feixia Zhu Hao Zhu Mandi Luo Ran He Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Heifei China Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) CASIA Beijing China Center for Excellence in Brain Science and Intelligence Technology CAS Beijing China

ISBN: (纸本)9781728188089;9781728188096

Given a speech clip and facial image, the goal of talking face generation is to synthesize a talking face video with accurate mouth synchronization and natural face motion. Recent progress has proven the effectiveness of the landmarks as the intermediate information during talking face generation. However, the large gap between audio and visual modalities makes the prediction of landmarks challenging and limits generation ability. This paper proposes a semantic and temporal synchronous landmark learning method for talking face generation. First, we propose to introduce a word detector to enforce richer semantic information. Then, we propose to preserve the temporal synchronization and consistency between landmarks and audio via the proposed temporal residual loss. Lastly, we employ a U-Net generation network with adaptive reconstruction loss to generate facial images for the predicted landmarks. Experimental results on two benchmark datasets LRW and GRID demonstrate the effectiveness of our model compared to the state-of-the-art methods of talking face generation.

关键词： Learning systems Visualization Face recognition Semantics Mouth Detectors Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Principled design of translation, scale, and rotation invariant variation operators for metaheuristics

arXiv

引用

arXiv 2021年

作者： Tian, Ye Zhang, Xingyi He, Cheng Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Guangdong Provincial Key Laboratory of Braininspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Computer Science University of Surrey Guildford SurreyGU2 7XH United Kingdom

In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed, this paper aims to design new operators automatically, which are expected to be search space independent and thus exhibit robust performance on different problems. For this purpose, this work first investigates the influence of translation invariance, scale invariance, and rotation invariance on the search behavior and performance of some representative operators. Then, we deduce the generic form of translation, scale, and rotation invariant operators. Afterwards, a principled approach is proposed for the automated design of operators, which searches for highperformance operators based on the deduced generic form. The experimental results demonstrate that the operators generated by the proposed approach outperform state-of-theart ones on a variety of problems with complex landscapes and up to 1000 decision variables. © 2021, CC BY.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Hybrid graph-based radiology report generation

引用

Expert Systems with applications 2025年 289卷

作者： Dengdi Sun Chaofan Mu Xuyang Fan Jin Tang Zegeng Li Jie Zhu Zhuanlian Ding Key Laboratory of Intelligent Computing & Signal Processing (ICSP) Ministry of Education School of Artificial Intelligence Anhui University Hefei 230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei 230601 China First Affiliated Hospital of Anhui University of Chinese Medicine Hefei 230031 China College of Integrated Chinese and Western Medicine Anhui University of Chinese Medicine Hefei 230012 China School of Internet Anhui University Hefei 230039 China

Automatic report generation plays a crucial role in clinical practice by alleviating the heavy workload on doctors and helping to prevent misdiagnoses or missed diagnoses. In the context of radiology report generation, knowledge injection is essential, particularly with the encoder-decoder framework commonly used in image captioning tasks. However, existing studies predominantly rely on expert knowledge, which is both challenging to collect and lacks universality. Additionally, this expert knowledge typically influences single-mode information and overlooks the importance of bridging the visual-to-textual gap. To address these challenges, we propose a hybrid graph-based approach for radiology report generation. Our method integrates two key components: the semantic homogeneous graph (SHG) and the cross-modal heterogeneous graph (CHG). Specifically, the SHG is constructed by mining semantic relationships between keywords across the entire corpus to generate universal knowledge. The CHG, conversely, is built from visual features, textual features, and corresponding knowledge embeddings, enabling knowledge injection during modal interaction. By leveraging graph convolutional networks to enhance graph embeddings, our model improves the quality of generated reports. Experimental results on two widely used benchmark datasets, IU-Xray and MIMIC-CXR, demonstrate the effectiveness of our approach. Notably, our method achieves a BLEU-4 score of 0.185 on the IU-Xray dataset and an F1 score of 0.418 on the MIMIC-CXR dataset, significantly outperforming existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenge-aware rgbt tracking

arXiv

引用

arXiv 2020年

作者： Li, Chenglong Liu, Lei Lu, Andong Ji, Qing Tang, Jin Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware neural network to handle the modality-shared challenges (e.g., fast motion, scale variation and occlusion) and the modality-specific ones (e.g., illumination variation and thermal crossover) for RGBT tracking. In particular, we design several parameter-shared branches in each layer to model the target appearance under the modality-shared challenges, and several parameter-independent branches under the modality-specific ones. Based on the observation that the modality-specific cues of different modalities usually contains the complementary advantages, we propose a guidance module to transfer discriminative features from one modality to another one, which could enhance the discriminative ability of some weak modality. Moreover, all branches are aggregated together in an adaptive manner and parallel embedded in the backbone network to efficiently form more discriminative target representations. These challenge-aware branches are able to model the target appearance under certain challenges so that the target representations can be learnt by a few parameters even in the situation of insufficient training data. From the experimental results we will show that our method operates at a real-time speed while performing well against the state-of-the-art methods on three benchmark datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-interactive dual-decoder for RGB-thermal salient object detection

arXiv

引用

arXiv 2020年

作者： Tu, Zhengzheng Li, Zhun Li, Chenglong Lang, Yang Tang, Jin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGB-thermal salient object detection (SOD) aims to segment the common prominent regions of visible image and corresponding thermal infrared image that we call it RGBT SOD. Existing methods don’t fully explore and exploit the potentials of complementarity of different modalities and multi-type cues of image contents, which play a vital role in achieving accurate results. In this paper, we propose a multi-interactive dual-decoder to mine and model the multi-type interactions for accurate RGBT SOD. In specific, we first encode two modalities into multi-level multi-modal feature representations. Then, we design a novel dual-decoder to conduct the interactions of multi-level features, two modalities and global contexts. With these interactions, our method works well in diversely challenging scenarios even in the presence of invalid modality. Finally, we carry out extensive experiments on public RGBT and RGBD SOD datasets, and the results show that the proposed method achieves the outstanding performance against state-of-the-art algorithms. The source code has been released at: https://***/lz118/Multi-interactiveDual-decoder. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Information fusion and feature selection for multi-source data utilizing Dempster-Shafer evidence theory and K-nearest neighbors

引用

Information Sciences 2025年 718卷

作者： Pengfei Zhang Qinli Zhang Jingxin Liu Dexian Wang Hua Ye Xiabing Zhang Tianrui Li School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu 611137 PR China Anhui Provincial Joint Construction Key Laboratory of Intelligent Education Equipment and Technology Chizhou University Anhui 247000 PR China School of Mathematics and Physics Sciences RI-IM⋅AI* Chongqing University of Science and Technology Chongqing 401331 PR China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 PR China

The Dempster-Shafer (D-S) evidence theory stands out in its ability to accurately and flexibly model the inherent uncertainties of data without requiring prior probabilities. This paper introduces an innovative information fusion algorithm alongside a novel feature selection algorithm, both grounded in the principles of evidence theory. Initially, the multi-source data is segmented into distinct information systems based on their unique features. Each of these information systems is then transformed into a probability distribution matrix utilizing the K-Nearest Neighbors (KNN) algorithm. Subsequently, Dempster's combination rule is utilized to integrate each probability distribution matrix into a cohesive piece of evidence. These consolidated evidences are then leveraged to ascertain the final fused system. Furthermore, a novel bridge is established between rough set theory and evidence theory, upon which a unique feature selection algorithm is proposed for the fused system, grounded in the concept of belief. Experimental results indicate that, in comparison to several advanced methodologies, the information fusion classification accuracy has seen an average enhancement of 2.72%. Similarly, the feature selection classification accuracy has witnessed a significant improvement of 6.80% on average. Consequently, two proposed algorithms demonstrate effectiveness, yielding exceptional results in both information fusion and feature selection tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3R: Word and Phoneme Edition based Data Augmentation for Lexical Punctuation Prediction

3R: Word and Phoneme Edition based Data Augmentation for Lex...

引用

International Conference on Computational Intelligence and Security

作者： Aihua Zheng Naipeng Ye Xiao Wang Xiao Song Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Hefei China Peking University Shenzhen Institute Shenzhen China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China

Existing Lexical Punctuation Prediction methods are mainly trained on the standard clean data while losing the generalization in practical automatic speech recognition (ASR) system with ubiquitous transcription errors. To bridge the gap between clean training data and noisy testing data, we propose three random (3R) data augmentation strategies: random word deletion (RWD), random word substitution (RWS), and random phoneme edition (RPE) in both word and phoneme levels on the training dataset. Specifically, we contribute an acoustically similar vocabulary with phoneme level editions for acoustically similar word substitution. In addition, we first introduce the RoBERTa-large model into a punctuation prediction task to capture the semantics and the long-distance dependencies in language. Extensive experiments on the English dataset IWSLT2011 yield to a new state-of-the-art comparing to the prevalent punctuation prediction methods.

关键词： Training Vocabulary Semantics Training data Predictive models Noise measurement Security

来源：评论

学校读者我要写书评

暂无评论

A niching-based nondominated sorting for multimodal multiobjective optimization with local pareto fronts

引用

Applied Soft computing 2025年 179卷

作者： Qi Deng Juan Zou Shengxiang Yang Yuan Liu Fan Yu Tianbin Xie Jinhua Zheng Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Computer Science and School of Cyberspace Science of Xiangtan University Xiangtan Hunan Province China Faculty of School of Computer Science and School of Cyberspace Science of Xiangtan University Xiangtan 411105 China School of Computer Science and Informatics De Montfort University Leicester LE1 9BH UK School of Traffic and Transport Engineering Central South University Changsha China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang 421002 China

In multimodal multiobjective optimization problems (MMOPs), there may be local Pareto optimal solutions (PSs). Finding both global PS and local PS simultaneously can provide additional options for decision makers. However, since individuals on the global Pareto front (PF) dominate individuals on the local PF, traditional multimodal multiobjective evolutionary algorithms (MMEAs) cannot effectively handle MMOPs with local PF (MMOPLs). In this paper, we improve our previous dynamic-niching-based Pareto domination (DNPD) approach to search for local Pareto optimal solutions. The new version is called niching-based non-dominated sorting (NNSL). There are two improvements to NNSL. First, the dynamic niche is changed to a fixed niche to increase the diversity of the population. Second, individuals with poor convergence in the non-dominated layer are deleted to ensure the convergence of the population. NNSL can be combined with Pareto dominance-based algorithms. We apply NNSL to solve MMOPLs (MMF_e and IDMP_e series). Experiments show that NNSL can help traditional MMEAs find global PF/PS and local PF/PS simultaneously.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Free-Standing Aqueous Zinc-Ion Capacitor Based on MnO2–CNTs Cathode and MXene Anode

引用

Nano-Micro Letters 2019年第4期11卷 227-238页

作者： Siliang Wang Qiang Wang Wei Zeng Min Wang Limin Ruan Yanan Ma Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityNo.3 Feixi RoadHefei 230039Anhui ProvincePeople’s Republic of China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Electronics and Information EngineeringAnhui UniversityNo.111 Jiulong RoadHefei 230601Anhui ProvincePeople’s Republic of China School of Sciences Hubei University of Automotive TechnologyNo.167 Checheng West RoadShiyan 442002Hubei ProvincePeople’s Republic of China

Restricted by their energy storage mechanism,current energy storage devices have certain drawbacks,such as low power density for batteries and low energy density for ***,the nearest ion capacitors,such as lithium-ion and sodium-ion capacitors containing battery-type and capacitor-type electrodes,may allow achieving both high energy and power *** the inspiration,a new zinc-ion capacitor(ZIC)has been designed and realized by assembling the free-standing manganese dioxide-carbon nanotubes(MnO2-CNTs)battery-type cathode and MXene(Ti3C2Tx)capacitortype anode in an aqueous *** ZIC can avoid the insecurity issues that frequently occurred in lithium-ion and sodium-ion capacitors in organic *** expected,the ZIC in an aqueous liquid electrolyte exhibits excellent electrochemical performance(based on the total weight of cathode and anode),such as a high specific capacitance of 115.1 F g?1(1 mV s?1),high energy density of 98.6 Wh kg?1(77.5 W kg?1),high power density of 2480.6 W kg?1(29.7 Wh kg?1),and high capacitance retention of^83.6%of its initial capacitance(15,000 cycles).Even in an aqueous gel electrolyte,the ZIC also exhibits excellent *** work provides an essential strategy for designing next-generation high-performance energy storage devices.

关键词： Energy storage Zinc-ion capacitor Battery-type and capacitor-type electrodes MXene Electrochemical performance

来源：评论

学校读者我要写书评

暂无评论

Correction to: Enhancing cyber defense strategies with discrete multi-dimensional Z-numbers: a multi-attribute decision-making approach

引用

Complex & intelligent Systems 2025年第7期11卷 1-1页

作者： Yao, Aiting Huang, Chen Zhang, Weiqi Dong, Chengzu Lu, Meiqu Mao, Junjun Liu, Xiao Li, Xuejun Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Hefei China AI Techplus Pty Ltd Organization Melbourne Australia School of Information Technology Deakin University Geelong Australia School of Data Science Lingnan University Hongkong China School of Artificial Intelligence Guangxi Minzu University Nanning China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China

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：