检索结果-内蒙古大学图书馆

2nd World Conference on Intelligent and 3D Technologies, WCI3DT 2023

作者： Lu, Wanli Zhang, Wen Sun, Mingrui Zhang, Jindong College of Computer Science and Technology Jilin University Changchun130012 China College of Software Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)9789819721436

Visual perception plays an important role in autonomous driving technology. The two key factors in visual perception tasks are monocular object detection and structured data analysis. In this paper, a structured data parsing algorithm based on monocular vision is proposed. Firstly, using the single-stage YOLOv5 object detection model, the target was located and its kind was identified. Secondly, the 3D position of the object in the camera coordinate system is calculated according to the mapping relationship between the imaging point and the target point. Finally, the distance between the object and the camera is calculated by using the pinhole camera model, and the size of the object and the horizontal declination Angle relative to the optical center of the camera are estimated by geometric derivation. This method not only has a simple principle, but also guarantees the precision of structured data output. Experimental findings support the method's viability and efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An image segmentation fusion algorithm based on density peak clustering and Markov random field

引用

Multimedia Tools and Applications 2024年第37期83卷 85331-85355页

作者： Feng, Yuncong Liu, Wanru Zhang, Xiaoli Zhu, Xiaoyan College of Computer Science and Engineering Changchun University of Technology Jilin Changchun130012 China Artificial Intelligence Research Institute Changchun University of Technology Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China College of Computer Science and Technology Jilin University Jilin Changchun130012 China

Image segmentation is a crucial task in the field of computer vision. Markov random fields (MRF) based image segmentation method can effectively capture intricate relationships among pixels. However, MRF typically requires an initial labeling field, and the number of classifications needs to be manually selected. To tackle these issues, we propose a novel medical image segmentation algorithm based on density peak clustering (DPC) and Markov random fields. Firstly, we improve DPC to make it applicable to grayscale images, named GIDPC. In the GIDPC method, local gray density and gray bias are defined to enable the automatic determination of the number of classifications. Then, GIDPC and MRF are combined to achieve image segmentation. Furthermore, a segmentation fusion method is employed to enhance the accuracy of image segmentation. We conduct comparison experiments on the whole brain atlas image library. Our proposed algorithm achieves high average values in uniformity measure, accuracy, precision and sensitivity, respectively. Experimental results demonstrate that the proposed algorithm outperforms other image segmentation methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Transformer for Data Inference and Long Prediction in Sparse Mobile CrowdSensing 42

Spatiotemporal Transformer for Data Inference and Long Predi...

引用

42nd IEEE International Conference on Computer Communications, INFOCOM 2023

作者： Wang, En Liu, Weiting Liu, Wenbin Xiang, Chaocan Yang, Bo Yang, Yongjian Jilin University College of Computer Science and Technology China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Chongqing University College of Computer Science China

ISBN: (纸本)9798350334142

Mobile CrowdSensing (MCS) is a data sensing paradigm that recruits users carrying mobile terminals to collect data. As its variant, Sparse MCS has been further proposed for large-scale and fine-grained sensing task with the advantage of collecting only a few data to infer unsensed data. However, in many real-world scenarios, such as early prevention of epidemic, people are interested in not only the data at the current, but also in the future or even long-term future, and the latter may be more important. Long-term prediction not only reduces sensing cost, but also identifies trends or other characteristics of the data. In this paper, we propose a spatiotemporal model based on Transformer to infer and predict the data with sparse sensed data by utilizing spatiotemporal relationships. We design a spatiotemporal feature embedding to embed the prior spatiotemporal information of sensing map into the model to guide model learning. Moreover, we also design a novel multi-head spatiotemporal attention mechanism to dynamically capture spatiotemporal relationships among data. Extensive experiments have been conducted on three types of typical urban sensing tasks, which verify the effectiveness of our proposed algorithms in improving the inference and long-term prediction accuracy with the sparse sensed data. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Driving Area Detection Algorithm Based on Swin Transformer 5

A Driving Area Detection Algorithm Based on Swin Transformer

引用

5th International Conference on Frontiers Technology of Information and Computer, ICFTIC 2023

作者： Liu, Shuang Li, Ying Jilin University College of Computer Science and Technology Jilin Changchun130012 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin Changchun130012 China

ISBN: (纸本)9798350309034

The detection of drivable areas holds immense significance within the perception system of autonomous vehicles. This capability enables intelligent vehicles to gain a comprehensive understanding of the current road conditions and effectively identify safe areas suitable for safe navigation. Convolutional Neural Networks (CNNs) have achieved significant progress in the application of drivable areas detection, particularly in semantic segmentation. However, most existing CNN-based methods for drivable area detection only consider information within a local neighborhood, thus failing to effectively capture long-range dependencies. To tackle this concern, we propose a novel U-shaped network based on the Swin Transformer. The Swin Transformer block was employed as the fundamental element of both the encoder and decoder. Additionally, an upsampling layer was introduced in the decoder to effectively restore the resolution of the feature map. We evaluate our approach on the Cityscapes dataset, a publicly available benchmark for autonomous driving. Experimental results verify the exceptional performance of our proposed method, achieving an impressive mean Intersection over Union (mIoU) score of 91.61%. Our method outperforms existing state-of-the-art techniques in road segmentation detection, further demonstrating its superiority. © 2023 IEEE.

关键词： CNNS Driving Area Detection Semantic segmentation Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE DEPTH GRAPH ATTENTION NETWORKS

arXiv

引用

arXiv 2023年

作者： Zhou, Jingbo Du, Yixuan Zhang, Ruqiong Zhang, Rui Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University China

As one of the most popular GNN architectures, the graph attention networks (GAT) is considered the most advanced learning architecture for graph representation and has been widely used in various graph mining tasks with impressive results. However, since GAT was proposed, none of the existing studies have provided systematic insight into the relationship between the performance of GAT and the number of layers, which is a critical issue in guiding model performance improvement. In this paper, we perform a systematic experimental evaluation and based on the experimental results, we find two important facts: (1) the main factor limiting the accuracy of the GAT model as the number of layers increases is the oversquashing phenomenon;(2) among the previous improvements applied to the GNN model, only the residual connection can significantly improve the GAT model performance. We combine these two important findings to provide a theoretical explanation that it is the residual connection that mitigates the loss of original feature information due to oversquashing and thus improves the deep GAT model performance. This provides empirical insights and guidelines for researchers to design the GAT variant model with appropriate depth and well performance. To demonstrate the effectiveness of our proposed guidelines, we propose a GAT variant model-ADGAT that adaptively selects the number of layers based on the sparsity of the graph, and experimentally demonstrate that the effectiveness of our model is significantly improved over the original GAT. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Attribution rollout: a new way to interpret visual transformer

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第1期14卷 163-173页

作者： Xu, Li Yan, Xin Ding, Weiyue Liu, Zechao College of Computer Science and Technology Harbin Engineering University Nantong Street Heilongjiang Harbin150001 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China Department of Medicine Harvard Medical School Longwood Avenue BostonMA02115 United States

Transformer-based models are dominating the field of natural language processing and are becoming increasingly popular in the field of computer vision. However, the black box characteristics of transformers seriously hamper their application in certain fields. Prior work relies on the raw attention scores or employs heuristic propagation along with the attention graph. In this work, we propose a new way to visualize model. The method computes attention scores based on attribution and then propagates these attention scores through the layers. This propagation involves attention layers and multi-head attention mechanism. Our method extracts salient dependencies in each layer to visualize prediction results. We benchmark our method on recent visual transformer networks and demonstrate its many advantages over the existing interpretability methods. Our code is available at: https://***/yxheartipp/attr-rollout. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Prototype-Guided Multimodal Relation Extraction based on Entity Attributes 39

Prototype-Guided Multimodal Relation Extraction based on Ent...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Zefan Zhang, Weiqi Li, Yanhui Bai, Tian College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China

ISBN: (纸本)157735897X

Multimodal Relation Extraction (MRE) aims to predict relations between head and tail entities based on the context of sentence-image pairs. Most existing MRE methods progressively incorporate textual and visual inputs to dominate the learning process, assuming both contribute significantly to the task. However, the diverse visual appearances and text with ambiguous semantics contain less-informative contexts for the corresponding relation. To tackle these challenges, we highlight the importance of semantically invariant entity attributes that encompass fine-grained categories. Towards this, we propose a novel Prototype-Guided Multimodal Relation Extraction (PG-MRE) framework based on Entity Attributes. Specifically, we first generate detailed entity explanations using Large Language Models (LLMs) to supplement the attribute semantics. Then, the Attribute Prototype Module (APM) refines attribute categories and condenses scattered entity attribute features into cluster-level prototypes. Furthermore, prototype-aligned attribute features guide diverse visual appearance features to produce compact and distinctive multimodal representations in the Relation Prototype Module (RPM). Extensive experiments demonstrate that our method gains superior relation classification capability (especially in scenarios involving various unseen entities), achieving new state-of-the-art performances on MNRE dataset. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling 38

Decision Mamba: Reinforcement Learning via Hybrid Selective ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Huang, Sili Hu, Jifeng Yang, Zhejian Yang, Liwei Luo, Tao Chen, Hechang Sun, Lichao Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education China School of Artificial Intelligence Jilin University China Institute of High Performance Computing Agency for Science Technology and Research Singapore Lehigh University BethlehemPA United States

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to process long-term dependencies, which provides an opportunity for in-context RL to solve tasks that require long-term memory. To this end, we first implement Decision Mamba (DM) by replacing the backbone of Decision Transformer (DT). Then, we propose a Decision Mamba-Hybrid (DM-H) with the merits of transformers and Mamba in high-quality prediction and long-term memory. Specifically, DM-H first generates high-value sub-goals from long-term memory through the Mamba model. Then, we use sub-goals to prompt the transformer, establishing high-quality predictions. Experimental results demonstrate that DM-H achieves state-of-the-art in long and short-term tasks, such as D4RL, Grid World, and Tmaze benchmarks. Regarding efficiency, the online testing of DM-H in the long-term task is 28× times faster than the transformer-based baselines. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training

arXiv

引用

arXiv 2024年

作者： Liu, Yonghao Li, Mengyu Li, Ximing Huang, Lan Giunchiglia, Fausto Liang, Yanchun Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China University of Trento Trento Italy Zhuhai Laboratory of the Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Zhuhai College of Science and Technology Zhuhai China

Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning with graph neural networks to solve few-shot node classification on graphs. Despite their promising performance, some limitations remain. First, they employ the node encoding mechanism of homophilic graphs to learn node embeddings, even in heterophilic graphs. Second, existing models based on meta-learning ignore the interference of randomness in the learning process. Third, they are trained using only limited labeled nodes within the specific task, without explicitly utilizing numerous unlabeled nodes. Finally, they treat almost all sampled tasks equally without customizing them for their uniqueness. To address these issues, we propose a novel framework for few-shot node classification called Meta-GPS++. Specifically, we first adopt an efficient method to learn discriminative node representations on homophilic and heterophilic graphs. Then, we leverage a prototype-based approach to initialize parameters and contrastive learning for regularizing the distribution of node embeddings. Moreover, we apply self-training to extract valuable information from unlabeled nodes. Additionally, we adopt S2 (scaling & shifting) transformation to learn transferable knowledge from diverse tasks. The results on real-world datasets show the superiority of Meta-GPS++. Our code is available here. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A METHOD FOR INCREMENTAL DISCOVERY OF FINANCIAL EVENT TYPES BASED ON ANOMALY DETECTION

arXiv

引用

arXiv 2023年

作者： Gu, Dianyue Li, Zixu Guan, Zhenhai Zhang, Rui Huang, Lan Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University Changchun China

Event datasets in the financial domain are often constructed based on actual application scenarios, and their event types are weakly reusable due to scenario constraints;at the same time, the massive and diverse new financial big data cannot be limited to the event types defined for specific scenarios. This limitation of a small number of event types does not meet our research needs for more complex tasks such as the prediction of major financial events and the analysis of the ripple effects of financial events. In this paper, a three-stage approach is proposed to accomplish incremental discovery of event types. For an existing annotated financial event dataset, the three-stage approach consists of: for a set of financial event data with a mixture of original and unknown event types, a semi-supervised deep clustering model with anomaly detection is first applied to classify the data into normal and abnormal events, where abnormal events are events that do not belong to known types;then normal events are tagged with appropriate event types and abnormal events are reasonably clustered. Finally, a cluster keyword extraction method is used to recommend the type names of events for the new event clusters, thus incrementally discovering new event types. The proposed method is effective in the incremental discovery of new event types on real data sets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly 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：