检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, LiHua Liu, Quan School of Computer Science and Technology Soochow University Soochow China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Jilin University Jilin China

Imitation learning (IL) is a framework that learns to imitate expert behavior from demonstrations. Recently, IL shows promising results on high dimensional and control tasks. However, IL typically suffers from sample inefficiency in terms of environment interaction, which severely limits their application to simulated domains. In industrial applications, learner usually have a high interaction cost, the more interactions with environment, the more damage it causes to the environment and the learner itself. In this article, we make an effort to improve sample efficiency by introducing a novel scheme of inverse reinforcement learning. Our method, which we call Model Reward Function Based Imitation Learning (MRFIL), uses an ensemble dynamic model as a reward function, what is trained with expert demonstrations. The key idea is to provide the agent with an incentive to match the demonstrations over a long horizon, by providing a positive reward upon encountering states in line with the expert demonstration distribution. In addition, we demonstrate the convergence guarantee for new objective function. Experimental results show that our algorithm reaches the competitive performance and significantly reducing the environment interactions compared to IL methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

DM-YOLOv5:An Improved Safety Helmet Detection Algorithm at Complex Construction Scenes

DM-YOLOv5:An Improved Safety Helmet Detection Algorithm at C...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Dexu Yao Aimin Li Deqi Liu Mengfan Cheng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

At complex construction sites, detecting whether workers are wearing safety helmets is often affected by occlusion and sunlight change. In addition, the helmets are relatively small, which can easily lead to missed detection and false detection. This paper proposes an improved YOLOv5 model. Firstly, we added a 152×152 detection layer for scale of small objects, enhancing its feature extraction capabilities. Secondly, we added the Multi-Spectral Channel Attention (MSCA) mechanism to enhance feature learning for small objects, addressing the information loss problem caused by Global Average Pooling (GAP). Finally, different activation functions, bounding box regression loss functions, and post-processing methods were adopted for YOLOv5. The Mish function serves as the activation function to enhance the model’s generalization ability and mitigate the gradient vanishing problem associated with the Leaky Relu function. The CIoU loss was employed as the loss function to improve bounding box regression accuracy and accelerate prediction convergence. DIoU-NMS, instead of NMS, was used as the post-processing method to enhance the filtering ability for prediction boxes of occluded small objects. We tested our algorithm on a dataset with 7000 images and achieved an mAP of 95.1%, surpassing the YOLOv5 model by 2.9%. Our method significantly improves safety helmet detection performance at complex construction scenes.

关键词： YOLO Representation learning Head Filtering Federated learning Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model

arXiv

引用

arXiv 2024年

作者： Xing, Yinghui Qu, Litao Zhang, Shizhou Zhang, Kai Zhang, Yanning Ran, Lingyan Zhang, Xiuwei Yin, Hanlin The Shaanxi Provincial Key Laboratory of Speech and Image Information Processing The National Engineering Laboratory for Integrated Aerospace-GroundOcean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi’an710072 China The Research Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution. When taking original MS and PAN images as inputs, they always obtain sub-optimal results due to the scale variation. In this paper, we propose to explore the self-supervised representation of pansharpening by designing a cross-predictive diffusion model, named CrossDiff. It has two-stage training. In the first stage, we introduce a cross-predictive pretext task to pre-train the UNet structure based on conditional DDPM, while in the second stage, the encoders of the UNets are frozen to directly extract spatial and spectral features from PAN and MS, and only the fusion head is trained to adapt for pansharpening task. Extensive experiments show the effectiveness and superiority of the proposed model compared with state-of-the-art supervised and unsupervised methods. Besides, the cross-sensor experiments also verify the generalization ability of proposed self-supervised representation learners for other satellite’s datasets. We will release our code for reproducibility. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DanceFix: An Exploration in Group Dance Neatness Assessment Through Fixing Abnormal Challenges of Human Pose 39

DanceFix: An Exploration in Group Dance Neatness Assessment ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Huangbiao Ke, Xiao Wu, Huanqi Xu, Rui Li, Yuezhou Xu, Peirong Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

ISBN: (纸本)157735897X

The fair and objective assessment of performances and competitions is a common pursuit and challenge in human society. The application of computer vision technology offers hope for this purpose, but it still faces obstacles such as occlusion and motion blur. To address these hindrances, our DanceFix proposes a bidirectional spatial-temporal context optical flow correction (BOFC) method. This approach leverages the consistency and complementarity of motion information between two modalities: optical flow, which excels at pixel capture, and lightweight skeleton data. It enables the extraction of pixel-level motion changes and the correction of abnormal skeleton data. Furthermore, we propose a part-level dance dataset (Dancer Parts) and part-level motion feature extraction based on task decoupling (PETD). This aims to decouple complex whole-body parts tracking into fine-grained limb-level motion extraction, enhancing the confidence of temporal information and the accuracy of correction for abnormal data. Finally, we present the DNV dataset, which simulates fully neat group dance scenes and provides reliable labels and validation methods for the newly introduced group dance neatness assessment (GDNA). To the best of our knowledge, this is the first work to develop quantitative criteria for assessing limb and joint neatness in group dance. We conduct experiments on DNV and video-based public JHMDB datasets. Our method effectively corrects abnormal skeleton points, flexibly embeds, and improves the accuracy of existing pose estimation algorithms. Copyright © 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

A study on the prediction model of dam seepage volume based on isolated forest-multiple stepwise linear regression 4

A study on the prediction model of dam seepage volume based ...

引用

4th International Conference on computer Engineering and Application, ICCEA 2023

作者： Chen, Guanyu Zhang, Suli Zhang, Chenlin Qian, XiaoChun Changchun University of Technology School of Computer Science & Engineering Jilin Provincial Key Laboratory of Changbai Historical Culture and Vr Reconstruction Technology Jilin Prov. Changbai Mt. Ecol. Culture and Virtual Reality Simulation Engineering Research Center Changchun China Jilin Institute of Chemical Technology School of Information and Control Engineering Jilin Provincial Key Laboratory of Changbai Historical Culture and Vr Reconstruction Technology Jilin Prov. Changbai Mt. Ecol. Culture and Virtual Reality Simulation Engineering Research Center Changchun China

ISBN: (纸本)9798350347548

In the study of hydraulic seepage prediction, it is often necessary to target multiple feature dimensions. In this paper, a variety of traditional machine learning algorithms based on stepwise regression filtering features are used to train a dam seepage prediction model based on isolated forest processing of data outliers. The results show that the algorithm can be applied to predict the seepage data of a reservoir more accurately, and further suggest improvements to the dam's seepage control function and observation facilities. The experimental results show that the correlation coefficient of the linear regression model is significantly improved when the training sample ratio is 0.8 after the isolated forest treatment of outliers and stepwise regression screening features. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Goods Anomaly Detection Based on Multi-Branch Feature Extraction and Foreground Mining

Goods Anomaly Detection Based on Multi-Branch Feature Extrac...

引用

IEEE International Symposium on information (IT) in Medicine and Education, ITME

作者： Zhiqian Jia Wei Li Zuoyong Li Zhipeng Mu Lihui Lin Shenghua Teng College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Xiamen Air Traffic Management Station of CAAC Xiamen China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science MinjiangUniversity Fuzhou China Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry School of Mathematics and Computer Science Wuyi University Fujian China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

In recent years, significant advancements have been made in the field of anomaly detection. Expanding anomaly detection tasks to new scenarios has become a development avenue. Anomaly detection for the outer packaging of supermarket goods is a challenging task due to the diversity of goods’ appearances, which results in some detection methods suffering from limited sensitivity to anomalies and inadequate target mining. To address these issues, we propose a novel unsupervised anomaly detection method based on multi-branch feature extraction and foreground cosine structure mining strategy. Firstly, we use anomaly synthesis technique to enhance the model’s perception of anomalies and construct more precise decision boundaries in the feature space. Secondly, a multi-branch feature extractor extracts and integrates multi-level and multi-scale features, providing rich texture and semantic information to improve the model’s adaptability in real-world scenarios. Finally, the foreground cosine loss focuses on target mining while supplementing local structural information, further enhancing the model’s ability to detect subtle anomalies. To validate the effectiveness of the proposed method, extensive experiments were conducted on the GoodsAD dataset, sampled from supermarket scenarios. Experimental results show that this method achieves significant performance in image-level detection and pixel-level localization.

关键词： Location awareness Adaptation models Sensitivity Semantics Education Packaging Feature extraction information technology Anomaly detection Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Recognizing Human-object Interactions for a Home Assistive Robot

Recognizing Human-object Interactions for a Home Assistive R...

引用

Automation, Control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Guanglei Huo Xinwei Chen Chengxi Huang School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

To enable robots to understand a specific assistive task during human-robot interactions under complex home scenes, at the center is the problem of human-object interaction (HOI) recognition. In particular, aiming at identifying efficiently, this paper proposes a graph convolutional network (GCN) by considering the similarity and proximity of human and object nodes, based on which the geometric positions and morphological relationships are explored. Also, a supplementary convolutional neural network (CNN) is fused to GCN to extract the global semantic features, which also ensures the recognition applicability for the cases where detectors fall into failure. Experiments on V-COCO demonstrate our approach, and results in real-world scenes on our assistive robot – Xiaozhi II verify its robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Identification for Projector Brand and Model Number 1

引用

6th International Conference on Data Mining and Big Data, DMBD 2021

作者： Li, Zuoyong Wang, Weice Zhang, Fuquan Fan, Haoyi Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou350002 China School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China

ISBN: (数字)9789811674761

ISBN: (纸本)9789811674754

The projector production process needs to pack manufactured projectors. The key step of projector packing is to check whether the brand and model number of the projector is correct or not, for avoiding the projector’s packing error. To achieve automation of identifying projector brand and model number for improving the efficiency of the projector packing, we proposed an automatic identification method by using image processing, character recognition, and string matching. Specifically, image grayscale processing, image gradient calculation, morphological operations, and image thresholding are sequentially performed to determine candidate target regions located by a projector's brand and model number. Then, two shape prior-based image features are designed to perform target region screening, i.e., excluding fake target regions as far as possible. Next, the character recognition technology is used to extract the texts in the target regions. Finally, string matching is performed to obtain identification results of the projector's brand and model number. Experimental results on several projectors demonstrate the effectiveness of the proposed method on automatic identification of projector brand and model number. The proposed method provides a general framework for identifying the brand and model number of other similar electronic products. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Clustering Framework for Fine-grained Scene Graph Generation 39

Semi-Supervised Clustering Framework for Fine-grained Scene ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yang, Jiarui Wang, Chuan Zhang, Jun Wu, Shuyi Jinjing, Zhao Liu, Zeming Yang, Liang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Institute of Information Engineering CAS China School of Computer Science and Technology Beijing JiaoTong University China Guangdong Provincial Key Lab of Intell. Info. Processing & Shenzhen Key Lab of Media Security Shenzhen University China Information Research Center of Military Science PLA Academy of Military Science China National Key Laboratory of Science and Technology on Information System Security China School of Computer Science and Engineering Beihang University China School of Artificial Intelligence Hebei University of Technology China

ISBN: (纸本)157735897X

Scene Graph Generation (SGG) aims to detect all objects and identify their pairwise relationships existing in the scene. Considering the substantial human labor costs, existing scene graph annotations are often sparse and biased, which result in confusion training with low-frequency predicates. In this work, we design a Semi-Supervised Clustering framework for Scene Graph Generation (SSC-SGG) that uses the sparse labeled data to guide the generation of effective pseudo-labels from unlabeled object pairs, thus enriching the labeled sample space, especially for low-frequency interaction samples. We approach from the perspective of clustering, reducing the problem of confirmation bias in a self-training manner. Specifically, we first enhance the model’s robustness to feature extraction via prototype-based clustering, aggregating different relationship augmented features onto the same prototype. Secondly, we design a dynamic pseudo-label assignment algorithm based on a mini-batch, which adjusts the detection sensitivity to different frequency samples from the historical assignment. Finally, we conduct joint training on the pseudo-labels and the labeled data. We conduct experiments on various SGG models and achieve substantial overall performance improvements, demonstrating the effectiveness of SSC-SGG. Copyright © 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

Heterogeneous Graph Convolutional Network for Visual Reinforcement Learning of Action Detection

Heterogeneous Graph Convolutional Network for Visual Reinfor...

引用

Automation, Control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Chengxi Huang Xinwei Chen School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

Existing action detection approaches do not take spatio-temporal structural relationships of action clips into account, which leads to a low applicability in real-world scenarios and can benefit detecting if exploited. To this end, this paper proposes to formulate the action detection problem as a reinforcement learning process which is rewarded by observing both the clip sampling and classification results via adjusting the detection schemes. In particular, our framework consists of a heterogeneous graph convolutional network to represent the spatio-temporal features capturing the inherent relation, a policy network which determines the probabilities of a predefined action sampling spaces, and a classification network for action clip recognition. We accomplish the network joint learning by considering the temporal intersection over union and Euclidean distance between detected clips and ground-truth. Experiments on ActivityNet v1.3 and THUMOS14 demonstrate our method.

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：