检索结果-内蒙古大学图书馆

2024 International Conference on intelligent Perception and Pattern Recognition, IPPR 2024

作者： Xi, Shuting Bai, Jing Yan, Hao School of Computer Science and Engineering North Minzu University China The Key Laboratory of Images Graphics Intelligent Processing of State Ethnic Affairs Commission China

ISBN: (纸本)9798400707315

The large-scale pre-trained models have demonstrated excellent performance in processing visual and language tasks in open-world scenarios. However, recent studies have shown that there are limitations in using comparative language-vision pretrained models for zero-shot 3D model classification, mainly in ignoring the multi-view independent information of 3D models, and using only a single template for text prompts, which fails to exploit the rich contextual information provided by the language, and restricts the matching of visual and semantic information. In order to solve these problems, this paper proposes a new framework of Parameter-free zero-shot 3D model classification based on "interaction first, fusion later", which utilizes a pre-trained visual encoder to extract multi-view visual features, and then explores contextual information from multiple perspectives with the help of semantic comprehension of a large language model, establishes fine-grained associations between independent views and prompts through view-by-view interaction with text features, and integrates the independent decision results among views through decision-level fusion strategy to realize zero-shot classification. Without any 3D training, the proposed method achieves 78.8% accuracy on the ZS3D dataset, and 53.2%, 40.3%, and 26.3% accuracy on the three sub-datasets of Ali, which verifies the generalizability and effectiveness of the proposed algorithm. © 2024 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Visual saliency based aerial video summarization by online scene classification

Visual saliency based aerial video summarization by online s...

引用

International Conference on image and graphics

作者： Wang, Jiewei Wang, Yunhong Zhang, Zhaoxiang Laboratory of Intelligent Recognition and Image Processing Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9780769545417

Compared with traditional video summarization approaches, aerial video summarization is a new and challenging issue for its particular characteristics. Aerial video data is a massive data stream, without pre-edit structures such as sports or news video data, lack of camera motion such as zoom and pan. On account of these characteristics, we proposed a novel approach for summarization. First, we extract GIST features for each frame as the holistic scene representation. Then, we divide aerial video into temporal segments representing a visual scene using on-line clustering method by examine GIST features of each frame only once. Finally, we select several key frames from each scene for summarization according to visual saliency index (VSI) of each frame computed from their visual saliency map. In the paper, we proposed new criterion for estimation of temporal segmentation of streaming video. Experimental observations show the success of our approach on aerial video summarization. © 2011 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

A multi-agent coordinated planning approach for deadline required emergency response tasks

引用

IET Control Theory and Applications 2015年第3期9卷 447-455页

作者： Zhou, Chao Wang, Hongwei Zhuo, Hankz Hankui Key Laboratory of Image Processing and Intelligent Control of Education Ministry Institute of Systems Engineering Huazhong University of Science and Technology Wuhan430074 China School of Advanced Computing SunYat-sen University Guangzhou510006 China

This study investigates the emergency decision-making problem in a multi-agent system. Departments are modeled as agents to perform coordinated planning to obtain a global action plan with a short execution time constrained by a prescribed deadline. A novel multi-agent planning approach is proposed to coordinate for the solution among agents in the system. The approach consists of two stages. For the first stage, a coordinated planning and scheduling method is designed to generate a candidate global action plan. In this plan, durative actions are assigned to proper time intervals with the consideration of temporal relationships among agents. For the second stage, a coordination mechanism based on local heuristics is proposed to reduce the global time cost of the candidate plan to satisfy the deadline. An experimental study of emergency evacuation problem is conducted to demonstrate the effectiveness and efficiency of the proposed approach. © 2015 The Institution of Engineering and Technology.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

CDF-Net: A zero-shot 3D classification network with CLIP Decoder for Feature Fusion 24

CDF-Net: A zero-shot 3D classification network with CLIP Dec...

引用

2024 International Conference on intelligent Perception and Pattern Recognition, IPPR 2024

作者： Yan, Hao Bai, Jing Liu, Lu School of Computer Science and Engineering North Minzu University China The Key Laboratory of images Graphics Intelligent Processing of State Ethnic Affairs Commission China

ISBN: (纸本)9798400707315

Zero-shot 3D model classification requires neural networks to correctly classify models with unseen categories, which has important practical implications for fields such as autonomous driving and robotics. PointCLIP demonstrates that transferring knowledge from the 2D image domain to the 3D model domain is beneficial for zero-shot 3D model classification, even without incorporating new 3D-specific knowledge. However, its effectiveness is limited by the lack of 3D knowledge. As a result, subsequent improvements have focused on refining 3D-to-2D projection algorithms rather than exploiting 3D information. Our approach aims to exploit both image domain knowledge and the full potential of 3D models. To this end, we propose CDF-Net, a learnable model architecture. CDF-Net consists of two components: an initial feature encoding module using the Contrastive Language-image Pre-training network to extract 2D knowledge from multi-view representations of 3D models, and a learnable module to extract 3D knowledge and integrate it with 2D knowledge. Evaluations on two benchmarks consisting of four datasets show that CDF-Net achieves competitive classification accuracies, demonstrating the effectiveness of our method. © 2024 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Fine-grained point cloud classification based on adaptive KNN algorithm 24

Fine-grained point cloud classification based on adaptive KN...

引用

2024 International Conference on intelligent Perception and Pattern Recognition, IPPR 2024

作者： Liu, Lu Bai, Jing Yan, Hao School of Computer Science and Engineering North Minzu University China The Key Laboratory of images Graphics Intelligent Processing of State Ethnic Affairs Commission China

ISBN: (纸本)9798400707315

In point cloud deep learning, local feature aggregation is crucial to improve the performance of the model. The traditional KNN (K-Nearest Neighbors) method performs local feature aggregation by fixing the K value, but often performs poorly in the face of different local structural variations. In order to overcome these limitations, this study proposes an improved KNN method that adapts to the diversity of local regions of the point cloud by adaptively adjusting the neighborhood size in order to maintain feature diversity and accuracy in regions of varying importance. Specifically, in this paper, we dynamically adjust different neighborhood ranges according to the attention weights of individual points, thus ensuring that local features are effectively captured in both important as well as non-important regions. In addition, we conduct experiments on the FG3D and ModelNet40, point cloud datasets. The overall accuracy of AK-Net reaches 96.31%, 79.85%, and 82.38% in the experimental results on the three sub-datasets Airplane, Car, and Chair of FG3D, and 94.04% on ModelNet40. Therefore, the classification performance of AK-Net is superior. © 2024 Copyright held by the owner/author(s).

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Variable structure multiple model for articulated human motion tracking from monocular video sequences

引用

Science China(Information Sciences) 2012年第5期55卷 1138-1150页

作者： HAN Hong 1,TONG MingLei 2,CHEN ZhiChao 1 & FAN YouJian 1 1 key laboratory of intelligent Perception and image Understanding of Ministry of Education of China,Institute of intelligent Information processing,Xidian University,Xi'an 710071,China 2 School of Computer and Information Engineering,Shanghai University of Electric Power,Shanghai 200090,China 1. Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi’an 710071 China2. School of Computer and Information Engineering Shanghai University of Electric Power Shanghai 200090 China

A new model-based human body tracking framework with learning-based theory is introduced in this *** propose a variable structure multiple model (VSMM) framework to address challenging problems such as uncertainty of motion styles,imprecise detection of feature points,and ambiguity of joint *** human joint points are detected automatically and the undetected points are estimated with Kalman *** motion models are learned from motion capture data using a ridge regression *** model set that covers the total motion set is designed on the basis of topological and compatibility relationships,while the VSMM algorithm is used to estimate quaternion vectors of joint *** using real image sequences and simulation videos demonstrate the high efficiency of our proposed human tracking framework.

关键词： human motion tracking ridge regression model groups design variable structure multiple model (VSMM) motion model group adaptation

来源：评论

学校读者我要写书评

暂无评论

Small universal spiking neural p systems with exhaustive use of rules

Small universal spiking neural p systems with exhaustive use...

引用

作者： Zhang, Xingyi Jiang, Yun Pan, Linqiang Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 Hubei China

We consider the problem of looking for small universal spiking neural P systems with exhaustive use of rules, which was formulated as an open problem by Andrei PǍun and Gheorghe PǍun in a survey paper. Here, spiking neural P systems are used in two versions: as devices computing functions and as devices generating sets of numbers, with two ways of encoding the result of a computation. As devices of computing functions, if we associate the result with the distance between the first two spikes emitted by the output neuron, we produce a universal computing spiking neural P system with exhaustive use of rules (without delay) having 125 neurons;if we introduce the usual way of defining the result of a computation in membrane systems to encode the result, namely, the number of spikes emitted during a computation, then a universal computing system (without delay) with 126 neurons is also obtained in the sense of the exhaustive use of rules. For spiking neural P systems used as generators of sets of numbers, we construct a universal system (without delay) by using 128 neurons under the first way of defining the computation result, and a system (without delay)by using127 neurous under the second way of defining the comutation result. Copyright © 2010 American Scientific Publishers. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Grammatical Error Correction Model 5

Context-Aware Grammatical Error Correction Model

引用

5th International Conference on Big Data and Artificial Intelligence and Software Engineering, ICBASE 2024

作者： Lin, Jianxing Huang, Guimin Wang, JiaHao Guilin University of Electronic Technology School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331506612

The pursuit of accurate and fluent English communication is the cornerstone of global academic exchange and expression. The accuracy of written English is crucial for effective discourse;however, despite advancements in grammatical error correction (GEC) technology, these systems often fall short when analyzing coherent text. This paper delves into the complexities of English writing and the challenges posed by current GEC systems, advocating for a shift toward understanding document-level context in error correction. We propose a dual-encoder architecture within an encoder-decoder model, referred to as the Context-Aware Grammatical Error Correction (CAGEC) model. The CAGEC model employs an innovative dual-encoder structure, combining the encoder of the Transformer model with a Bi-GRU (Bidirectional Gated Recurrent Unit) neural network, and integrates encoding into the decoder through attention and gating mechanisms to achieve a deep understanding of the source sentence and its context. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Extended state observer based non-iteration predicted entry guidance

Extended state observer based non-iteration predicted entry ...

引用

2012 International Conference on Modelling, Identification and Control, ICMIC 2012

作者： Chang, Songtao Su, Mao Zhang, Da Wang, Yongji Department of Control Science and Engineering Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780956715715

It is difficult to guide the entry vehicle to prescribed area due to the disperse of environment and kinematics. Through predicted residual range at the current state based on drag acceleration, we developed a predictor-corrector guidance law which doesn't need iteration to figure out the reference trajectory. Then using extended state observer based controller to track the reference trajectory. We use several missions(under various disperse conditions) to test the guidance law. Simulation results demonstrated that the guidance law is able to achieve the prescribed terminal conditions under various perturbations in the aerodynamic coefficients, the density of the atmosphere and the mass of the vehicle. © 2012 Huazhong Univ of Sci & Tec.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

A novel small dim infrared target detecting method based on grayscale merging and connected components analysis

A novel small dim infrared target detecting method based on ...

引用

2012 International Conference on Modelling, Identification and Control, ICMIC 2012

作者： Zhang, Ying Wang, Min Niu, Shaoqing Key Laboratory of Image Processing and Intelligent Control of Education Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780956715715

Target detecting algorithm in infrared image is drawing extensive attention both at home and abroad, expecially when the infrared images own complex backgrounds and low resolution. How to make sure of the accuracy of infrared dim-small target detecting is the key point during the processing procedure. In this paper, a novel region of interest detecting algorithm is proposed for aerial small dim infrared target with clutter background. Different from traditional region of interest extraction method, we extract region of interest based on the grayscale merging algorithm and connected components analysising approach. First, the infrared image is reconstructed by separating the grayscale into several interval sections, then binarization is used to segment the processed image according to estimate the threshold value using minimum error probability;finally, analysis and select the connected components, to sift the accurate connected domain which contain the target. The validity of the proposed approach is demonstrated by experiment of infrared target region extraction. © 2012 Huazhong Univ of Sci & Tec.

关键词： Object detection

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：