检索结果-内蒙古大学图书馆

17th European Conference on Computer Vision, ECCV 2022

作者： Zhang, Boshen Li, Yuxi Tu, Yuanpeng Peng, Jinlong Wang, Yabiao Wu, Cunlin Xiao, Yang Zhao, Cairong YouTu Lab Shenzhen China Tongji University Shanghai China Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9783031250620

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well. In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modality, including image classification (CIFAR, Clothing1M etc.) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient line-based architecture for 2-D discrete wavelet transform

引用

OPTICAL ENGINEERING 2006年第3期45卷 037004-1-037004页

作者： Xiong, Cheng-Yi Tian, Jin-Wen Liu, Jian Huazhong Univ Sci & Technol Key Lab Educ Minist Image Processing Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Intelligent Control Inst Pattern Recognit & Artif Wuhan 430074 Peoples R China S Ctr Univ Natl Coll Elect Informat Engn Wuhan 430074 Peoples R China

Efficient line-based very large scale integration architectures for the 2-D discrete wavelet transform (DWT) based on a lifting scheme, using the 9/7 wavelet filters adopted in the JPEG 2000 proposal, are proposed. The embedded decimation technique based on folding and time multiplexing was exploited to optimize the architecture, which reduces the size of buffer memory required and the amount of RAM access, and hence the occupied area and power consumption of the devices. Using this technique, a single-input, single-output architecture (SISOA) and a two-input, two-output architecture (TITOA) are proposed. The presented SISOA is designed to generate one output per clock cycle;the TITOA is designed to generate two outputs per clock cycle with the same memory requirement as that for SISOA, where the four sub-band coefficients of the transformed signal are available interleaved. Because only one line of data is required at a time, a single-port memory can be used. Performance analysis and comparison results demonstrate that the proposed method is economical of hardware cost and computation time. The advantages of the design also include short output latency, simple data flow, regularity, and scalability, as well as suitability for VLSI implementation. (c) 2006 Society of Photo-Optical Instrumentation Engineers.

关键词： 2-D DWT line-based lifting scheme embedded decimation VLSI

来源：评论

学校读者我要写书评

暂无评论

Accessibility and Vulnerability Analysis of the Integrated Road, High-speed Rail and Airline System in China 13

Accessibility and Vulnerability Analysis of the Integrated R...

引用

13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022

作者： Sun, Wenjing Zhang, Hui Ouyang, Min School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Lab. for Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China

ISBN: (数字)9781665486903

ISBN: (纸本)9781665486903

National-scale transportation systems are critical infrastructures to ensure the normal operation of the nation and offer essential services to modern societies. And they face a constant barrage of external stresses or threats that challenge their operation. This article analyzes the accessibility and vulnerability of the Chinese road, high-speed rail and airline systems. Firstly, it models the complementary relationship among road, high-speed rail and airline systems and takes them as an integrated transportation system (IRHAS). Then, the accessibility map from (to) the center of Beijing via IRHAS is displayed. Finally, modeling the extreme storm recently occurred in Zhengzhou as a reginal disruption, the vulnerability of the IRHAS is calculated. The findings in this paper provide guidance for city administrators to plan the road, high-speed rail, and airline systems as a whole. © 2022 IEEE.

关键词： Storms

来源：评论

学校读者我要写书评

暂无评论

Maneuvering target tracking based on fuzzy reasoning

引用

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics 2009年第3期31卷 541-544页

作者： Han, Hong Chen, Zhao-Ping Jiao, Li-Cheng Zhi, Jian-Wei Key Lab. of Intelligent Perception and Image Understanding Inst. of Intelligent Information Processing Xidian Univ. Xi'an 710071 China

The performance of the 'current' statistical model algorithm gets worse when there is a sudden maneuver. To solve this problem, an improved algorithm is presented. This algorithm is implemented through a pair of parallel adaptive filters together with information fusion technique. By introducing the state information of targets, the output of the fuzzy system can adjust the predicted covariance of the filter adaptively. The simulation results show that the proposed algorithm has better performance when there is a sudden maneuver.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Adaptive dictionary learning for distributed compressive video sensing

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第4期6卷 141-149页

作者： Wu, Minghu Zhu, Xiuchang Gan, Zongliang Li, Xin Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China School of Electrical and Electronic Enginesering Hubei University of Technology Wuhan China

Compressive sensing (CS) is a new technique for data sampling and compression simultaneously. In this paper, we propose a novel distributed video coding algorithm with dynamic measurement rate allocation based on compressive sensing principles, where almost all computation burdens can be shifted to the decoder, resulting in a very low-complexity encoder. So the proposed algorithm can be useful in those video applications that require very low complex encoders. At the decoder, the compressed video can be efficiently reconstructed with adaptive dictionary learning. The simulation results show that the proposed algorithm outperforms the distributed compressive video sensing with non-adaptive learning local dictionary and global dictionary.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Supervised segmentation of vasculature in retinal images using neural networks

Supervised segmentation of vasculature in retinal images usi...

引用

IEEE International Conference on Orange Technologies (ICOT)

作者： Chen Ding Yong Xia Ying Li Shaanxi Key Lab of Speech & Image Information Processing (SAIIP) Northwestern Polytechnical University Xian

ISBN: (纸本)9781479962853

This paper proposes a neural network based supervised segmentation algorithm for retinal vessel delineation. The histogram of each training image patch and its optimal threshold acquired through iteratively comparing the binaryzation result to the manual segmentation are applied to a BP neural network to establish the correspondence between the intensity distribution and optimal segmentation parameter. Finally, each test image can be segmented by using a number of local thresholds that are predicted by the trained the neural network according the histograms of image patches. The propose algorithm has been evaluated on the DRIVE database that contains forty retinal images with manually segmented vessel trees. Our results show that the proposed algorithm can effective segment the vasculature in retinal images.

关键词： image segmentation Biomedical imaging Blood vessels Retina Training Histograms Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic integral sliding mode for launch vehicle attitude control system

Dynamic integral sliding mode for launch vehicle attitude co...

引用

Chinese Control and Decision Conference, CCDC

作者： Zirui Wang Lei Liu Yongji Wang Zhishen Wang Key Lab for Image Processing & Intelligent Control Huazhong University of Science & Technology Wuhan China

As it is known that launch vehicle is facing a very harsh environment during the fight process. The challenge of various perturbations and uncertainties has lead to many traditional control methods' failure to meet the requirements of attitude control system. Due to the main advantage of sliding mode control's robustness to the system uncertainties and disturbances in the so-called sliding mode, it has been widely used in engineering. In this paper, regarding particularly on chattering problem, the authors developed a novel dynamic integral sliding mode control scheme and the comparative simulation results carried out with traditional dynamic integral sliding mode demonstrates the superiority of the newly designed control law.

关键词： Sliding mode control Rockets Attitude control Simulation Vehicle dynamics Vehicles

来源：评论

学校读者我要写书评

暂无评论

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians 16th

Do Not Disturb Me: Person Re-identification Under the Interf...

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Zhao, Shizhen Gao, Changxin Zhang, Jun Cheng, Hao Han, Chuchu Jiang, Xinyang Guo, Xiaowei Zheng, Wei-Shi Sang, Nong Sun, Xing Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent Youtu Lab Shanghai China Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783030585389

In the conventional person Re-ID setting, it is assumed that cropped images are the person images within the bounding box for each individual. However, in a crowded scene, off-shelf-detectors may generate bounding boxes involving multiple people, where the large proportion of background pedestrians or human occlusion exists. The representation extracted from such cropped images, which contain both the target and the interference pedestrians, might include distractive information. This will lead to wrong retrieval results. To address this problem, this paper presents a novel deep network termed Pedestrian-Interference Suppression Network (PISNet). PISNet leverages a Query-Guided Attention Block (QGAB) to enhance the feature of the target in the gallery, under the guidance of the query. Furthermore, the involving Guidance Reversed Attention Module and the Multi-Person Separation Loss promote QGAB to suppress the interference of other pedestrians. Our method is evaluated on two new pedestrian-interference datasets and the results show that the proposed method performs favorably against existing Re-ID methods. © 2020, Springer Nature Switzerland AG.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Deep neural network and switching Kalman filter based continuous affect recognition

Deep neural network and switching Kalman filter based contin...

引用

2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016

作者： Pei, Ercheng Xia, Xiaohan Le, Yang Dongmei, Jiang Sahli, Hichem United States NPU-VUB Joint AVSP Lab Shaanxi Key Lab on Speech and Image Information Processing Xi'an710072 China Pleinlaan 2 Brussels1050 Belgium Interuniversity Microelectronics Centre Kepeldreef 75 Heverlee3001 Belgium

ISBN: (纸本)9781509015528

In this paper, we propose the deep neural network - switching Kalman filter (DNN-SKF) based frameworks for both single modal and multi-modal continuous affective dimension estimation. The DNN-SKF framework firstly models the complex nonlinear relationship between the input (audio, visual, or lexical) features and the affective dimensions via the non-recurrent DNN, then models the temporal dynamics embedded in the emotions via the segmental linear SKF. Affective dimension estimation experiments are carried out on the Audio Visual Emotion Challenge (AVEC2012) database. Single modal estimation results are compared to those from the Support Vector Regression (SVR) models and Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) models, results show that for all modalities, and for all affective dimensions except for arousal from the audio features, the DNN-SKFs outperform SVR and BLSTM-RNN models in estimating the affective dimensions. Multi-modal estimation results are compared with the state of the art results on the competition of AVEC2012. Results show that both on the development set and test set, the proposed DNN-SKF models obtain the best performance in estimating the affective dimensions. On the test set, with the audio visual features, the average Pearson correlation coefficient (COR) is improved to 0.326 from 0.226 of the linear regression method [1], while with the audio visual and lexical features, the COR is improved to 0.355 from 0.344 of the particle filter fusion method (SVR-PF) [2]. © 2016 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Solving TSP by dismantling cross paths

Solving TSP by dismantling cross paths

引用

IEEE International Conference on Orange Technologies (ICOT)

作者： Yongsheng Pan Yong Xia Shaanxi Key Lab of Speech & Image Information Processing (SAIIP) Northwestern Polytechnical University Xi'an

ISBN: (纸本)9781479962853

Traveling salesman Problem (TSP) is a classical NP-hard problem and has been extensively studied in literature. Eliminating the cross paths, which commonly exist in approximate solutions to large scale TSP, can effectively improve the quality of the solutions. Through studying the impact of cross paths on the cost of a loop, in this paper we develop a method to detect and dismantle cross paths, and thus propose a novel greedy algorithm-based approach to the TSP. This approach has been evaluated on ten TSP data sets and compared to three classical optimization techniques, including the elastic network, ant colony algorithm and genetic algorithm. Our results show that the proposed approach can get approximate solution of high quality with far less computational cost and has an excellent performance in solving large-scale TSP.

关键词： Optimization Genetic algorithms Approximation algorithms Greedy algorithms Computers Educational institutions Traveling salesman problems

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：