检索结果-内蒙古大学图书馆

Find More Accurate Text Boundary for Scene Text Detection 26

Find More Accurate Text Boundary for Scene Text Detection

26th international Conference on pattern recognition / 8th international workshop on Image Mining - theory and Applications (IMTA)

作者： Pan, Runqiu Li, Zezhou Zhu, Anna Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Arbitrary shape text detection is still an open problem due to several challenges, e.g., dense text adhesion, various sizes, and noises. In this work, we propose a novel scene text detection network by extracting and connecting a set of points on the boundary of each text instance. Our method mainly consists of three branches, including text center line (TCL) prediction, text orientation (TO) prediction, and text boundary offset (TBO) prediction to get the text boundary point proposals. Utilize these proposals, and the final refinement results can be obtained by point sampling and graph attention network(GAT). the detector can overcome the text instance sticking problem with these text boundary representations. Additionally, we propose distance-based dice loss and instance-aware L1 loss to remove false positives and get over various text sizes on text boundary offset prediction respectively. In this way, our method can directly and efficiently generate accurate text boundaries without any post-processing. Extensive experiments on publicly available datasets show the effectiveness of our design and training strategy, which also demonstrates our method's state-of-the-art performance for arbitrary shape text detection.

关键词： Training Shape Adhesives Detectors pattern recognition Proposals

来源：评论

学校读者我要写书评

暂无评论

3D point clouds simplification based on geometric primitives and graph-structured optimization 26

3D point clouds simplification based on geometric primitives...

引用

26th international Conference on pattern recognition / 8th international workshop on Image Mining - theory and Applications (IMTA)

作者： Guinard, Stephane A. Daniel, Sylvie Badard, thierry Univ Laval Dept Sci Geomat Quebec City PQ G1V 0A6 Canada

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

We present a new method for the simplification of 3D point clouds for digital twin city models. Such data usually contains a large amount of redundant information, noise and outliers. this implies that most of subsequent processing tasks are costly both in terms of processing times and hardware infrastructure. the core idea of this paper is that most of the objects present in such scenes can be approximated as a combination of simple geometric primitives. this approximation can, in turn, be simplified by keeping only points and edges that effectively describe the shape of the input scene. Our main contribution is a formulation of the approximation of 3D point clouds with simple geometric primitives as a global optimization problem. We then introduce a new algorithm to efficiently solve this problem with a graph-cut-based approach. We measure the performances of our approach against state-of-the-art methods by comparing the geometric quality of the approximations with the amount of information needed to represent the simplified models. the evaluation of our approach is done on Mobile Laser Scanning (MLS) acquisitions in urban areas. Test areas include single objects and street portions to show the adaptability of our method to various geometries. We show improvements both in terms of geometrical error and final model size.

关键词： Point cloud compression Geometry Solid modeling Adaptation models three-dimensional displays Urban areas Vegetation

来源：评论

学校读者我要写书评

暂无评论

Trends in graph -based representations for pattern recognition

引用

pattern recognition LETTERS 2020年 134卷 3-9页

作者： Brun, Luc Foggia, Pasquale Vento, Mario Univ Salerno Dept Informat & Elect Engn & Appl Math Fisciano Italy GreyC Ecole Natl Super Ingn Caen ENSICAEN Caen France

In this paper we try to examine recent trends on the use of graph-based representations in pattern recognition, using as a vantage point the 11th IAPR-TC15 workshop GbR2017, dedicated to this topic. A survey of the paper presented at GbR2017 will give us the opportunity to reflect on the directions where the interest of the research community working on this subject is moving. (C) 2018 Elsevier B.V. All rights reserved.

关键词： graph-based representations graph matching graph edit distance graph kernels

来源：评论

学校读者我要写书评

暂无评论

Automatic target recognition module development for fire control system based on machine learning 6

Automatic target recognition module development for fire con...

引用

6th Modern Machine Learning Technologies workshop, MoMLeT 2024

作者： Vysotska, Victoria Romanchuk, Roman Nazarkevych, Mariia Lavrut, Oleksandr Lavrut, Tetiana Pysarchuk, Maksym Lviv Polytechnic National University Stepan Bandera 12 Lviv79013 Ukraine Hetman Petro Sahaidachnyi National Army Academy Heroes of Maidan 32 Lviv79026 Ukraine Organization and Planning Department of the Training Center "Partnership for Peace" of the International Peacekeeping and Security Center Lviv79026 Ukraine

Target recognition is a priority in military affairs. this task is complicated by the fact that it is necessary to recognize moving objects, different topography and landscape create obstacles for recognition. Combat actions can take place at different times of the day, accordingly, the lighting angle and general lighting must be taken into account. It is necessary to detect the object in the video by segmenting the video frames and to recognize and classify it. In the work, the authors propose the development of a target recognition module as a component of the fire control system within the framework of the proposed information technology through artificial intelligence use. the YOLOv8 pattern recognition model family was used to develop the target recognition module. the data was collected from open sources, in particular, from video footage posted in open sources on the YouTube platform. the main task of data pre-processing is the classification of three classes of objects on video or in real-time - APC, BMP, and TANK. the dataset is formed using the Roboflow platform based on marking tools and, subsequently, augmentation tools. the data set consists of 1193 unique images - approximately equally for each class. the training was conducted using Google Colab resources. 100 epochs were taken to train the model. the analysis is carried out according to mAP50 (mean Average Precision as 0.85), mAP50-95 (0.6), precision (0.89) and recall (0.75) metrics. Large losses are present because the background was not taken into account in the study - training the module based on validated data (images) of the background without the technique. this will be the next step. It is also necessary to expand the classification of objects of military equipment. © 2024 Copyright for this paper by its authors.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense graph representations 59

<i>Efficient</i> Text-based Reinforcement Learning by Jointl...

引用

Joint Conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th international Joint Conference on Natural Language Processing (IJCNLP) / 6th workshop on Representation Learning for NLP (RepL4NLP)

作者： Murugesan, Keerthiram Atzeni, Mattia Kapanipathi, Pavan Talamadupula, Kartik Sachan, Mrinmaya Campbell, Murray IBM Res Ruschlikon Switzerland Ecole Polytech Fed Lausanne Lausanne Switzerland Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9781954085534

Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowledge to improve the efficiency of RL agents for TBGs. In this paper, we posit that to act efficiently in TBGs, an agent must be able to track the state of the game while retrieving and using relevant commonsense knowledge. thus, we propose an agent for TBGs that induces a graph representation of the game state and jointly grounds it with a graph of commonsense knowledge from ConceptNet. this combination is achieved through bidirectional knowledge graph attention between the two symbolic representations. We show that agents that incorporate commonsense into the game state graph outperform baseline agents.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

11th IAPR-TC-15 international workshop on graph-based representations in pattern recognition, GbRPR 2017

11th IAPR-TC-15 International Workshop on Graph-Based Repres...

引用

11th IAPR-TC-15 international workshop on graph-based representations in pattern recognition, GbRPR 2017

ISBN: (纸本)9783319589602

the proceedings contain 26 papers. the special focus in this conference is on graph-based representations in pattern recognition. the topics include: Saliency detection via a graph based diffusion model;shape simplification through graph sparsification;reeb graphs of piecewise linear functions;learning graph matching with a graph-based perceptron in a classification context;a nested alignment graph kernel through the dynamic time warping framework;speeding-up graph-based keyword spotting in historical handwritten documents;error-tolerant coarse-to-fine matching model for hierarchical graphs;a Hungarian algorithm for error-correcting graph matching;a new algorithm for subgraph isomorphism;node matching computation between two large graphs in linear computational cost;measuring vertex centrality using the holevo quantity;on the interplay between strong regularity and graph densification;density normalization in density peak based clustering;fast nearest neighbors search in graph space based on a branch-and-bound strategy;exact computation of graph edit distance for uniform and non-uniform metric edit costs;improved graph edit distance approximation with simulated annealing;an edit distance between graph correspondences;a survey on applications of bipartite graph edit distance;minimising entropy changes in dynamic network evolution;synchronization over the birkhoff polytope for multi-graph matching and adaptive feature selection based on the most informative graph-based features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Link-Aware Link Prediction over Temporal graph by pattern recognition 36th

Link-Aware Link Prediction over Temporal Graph by Pattern Re...

引用

36th international Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE)

作者： Liu, Bingqing Huang, Xikun Chinese Acad Sci Acad Math & Syst Sci Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China

ISBN: (纸本)9783031368189;9783031368196

A temporal graph can be considered as a stream of links, each of which represents an interaction between two nodes at a certain time. On temporal graphs, link prediction is a common task, which aims to answer whether the query link is true or not. To do this task, previous methods usually focus on the learning of representations of the two nodes in the query link. We point out that the learned representation by their models may encode too much information with side effects for link prediction because they have not utilized the information of the query link, i.e., they are link-unaware. based on this observation, we propose a link-aware model: historical links and the query link are input together into the following model layers to distinguish whether this input implies a reasonable pattern that ends with the query link. During this process, we focus on the modeling of link evolution patterns rather than node representations. Experiments on six datasets show that our model achieves strong performances compared with state-of-the-art baselines, and the results of link prediction are interpretable. the code and datasets are available on the project website: https://***/lbq8942/TGACN.

关键词： Temporal graph Link prediction Sampling Transductive learning Inductive learning Interpretability

来源：评论

学校读者我要写书评

暂无评论

Distributed representations of Emotion Categories in Emotion Space 59

Distributed Representations of Emotion Categories in Emotion...

引用

作者： Wane, Xiangyu Zong, Chengqing Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing Peoples R China

ISBN: (纸本)9781954085527

Emotion category is usually divided into different ones by human beings, but it is indeed difficult to clearly distinguish and define the boundaries between different emotion categories. the existing studies working on emotion detection usually focus on how to improve the performance of model prediction, in which emotions are represented with one-hot vectors. However, emotion relations are ignored in one-hot representations. In this article, we first propose a general framework to learn the distributed representations for emotion categories in emotion space from a given emotion classification dataset. Furthermore, based on the soft labels predicted by the pre-trained neural network model, we derive a simple and effective algorithm. Experiments have validated that the proposed representations in emotion space can express emotion relations much better than word vectors in semantic space.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Learning Faithful representations of Causal graphs 59

Learning Faithful Representations of Causal Graphs

引用

作者： Balashankar, Ananth Subramanian, Lakshminarayanan NYU New York NY 10012 USA

ISBN: (纸本)9781954085527

Learning contextual text embeddings that represent causal graphs has been useful in improving the performance of downstream tasks like causal treatment effect estimation. However, existing causal embeddings which are trained to predict direct causal links, fail to capture other indirect causal links of the graph, thus leading to spurious correlations in downstream tasks. In this paper, we define the faithfulness property of contextual embeddings to capture geometric distance-based properties of directed acyclic causal graphs. By incorporating these faithfulness properties, we learn text embeddings that are 31.3% more faithful to human validated causal graphs with about 800K and 200K causal links and achieve 21.1% better Precision-Recall AUC in a link prediction fine-tuning task. Further, in a crowdsourced causal question-answering task on Yahoo! Answers with questions of the form "What causes X?", our faithful embeddings achieved a precision of the first ranked answer (P@1) of 41.07%, outperforming the existing baseline by 10.2%.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Sixth international workshop on pattern recognition

Sixth International Workshop on Pattern Recognition

引用

6th international workshop on pattern recognition, IWPR 2021

ISBN: (纸本)9781510646896

the proceedings contain 22 papers. the topics discussed include: tensor-patch-based discriminative marginalized least squares regression for membranous nephropathy hyperspectral data classification;quality perception and discrimination thresholds in quantized triangle meshes;image classification based on self-attention convolutional neural network;flight trajectory prediction of point-conditioned time and altitudes;the sentiment analysis model with multi-head self-attention;improved error-correcting from extracted handwritings in Chinese;the generalized covariance union fusion approach for distributed sensors with different fields of view;grading and profiling for export quality coffee beans using red green blue analysis, blob analysis, Huâ€™s moments and back-propagation neural network;and contrastive learning for solar cell micro-crack detection.

关键词：

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：