检索结果-内蒙古大学图书馆

International Conference on Computer Network, Electronic and Automation (ICCNEA)

作者： Yan Yang Jianguo Wang School of Computer Science and Engineering Xi'an Technological University Xi’an China Research Institute of Artificial Intelligence and Data Science Xi'an Technological University Xi’an China

The concept of iris segmentation was created to increase the accuracy of iris recognition. Past recognition methods used the entire eye image directly for recognition classification, which led to poor recognition results. For the sake of sovling this problem, this paper proposes the ResU-Net (RU-Net) model, which can guide the network to learn more features that distinguish between iris and non-iris pixels. First, based on the U-Net, the backbone network model is changed to ResNet50 in this paper. This has the advantage of reducing the number of parameters and network complexity, and improving the learning capability. For the sake of solving the problem of sample imbalance between iris region and background region, this paper introduces the Focal Loss loss function. focal loss can effectively deal with the case of sample category imbalance and make the network focus more on the pixels that are difficult to classify. In this paper, the proposed RU-Net model is experimentally evaluated on the CASIA-Iris-Thousand dataset. The experimental results demonstrate that RU-Net achieves significant improvements on NIR iris images, reaching 96.22% MIoU and 98.19% MPA. This indicates that the RU-Net method outperforms other representative iris segmentation methods and has better segmentation capability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Rationale-Centric Framework for Human-in-the-loop Machine Learning 60

A Rationale-Centric Framework for Human-in-the-loop Machine ...

引用

60th Annual Meeting of the Association for Computational Linguistics, ACL 2022

作者： Lu, Jinghui Yang, Linyi Namee, Brian Mac Zhang, Yue The Insight Centre for Data Analytics University College Dublin Ireland School of Computer Science University College Dublin Ireland School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study China SenseTime Research

ISBN: (纸本)9781955917216

We present a novel rationale-centric framework with human-in-the-loop - Rationales-centric Double-robustness Learning (RDL) - to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual generation and dynamic human-intervened correction, RDL exploits rationales (i.e. phrases that cause the prediction), human interventions and semi-factual augmentations to decouple spurious associations and bias models towards generally applicable underlying distributions, which enables fast and accurate generalisation. Experimental results show that RDL leads to significant prediction benefits on both in-distribution and out-of-distribution tests compared to many state-of-the-art benchmarks-especially for few-shot learning scenarios. We also perform extensive ablation studies to support in-depth analyses of each component in our framework. © 2022 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

EyeUnderstand: Dashboard for Gaze and Deep-Learning Driven Comprehension Estimation in Online Lectures

引用

IEEE Access 2025年 13卷 102220-102233页

作者： Ko Watanabe Gitesh Gund Jayasankar Santhosh Haruka Sakagami Yuki Matsuda Andreas Dengel Shoya Ishimaru Smart Data and Knowledge Services German Research Center for Artificial Intelligence (DFKI) GmbH Kaiserslautern Germany Department of Computer Science RPTU Kaiserslautern-Landau Kaiserslautern Germany Graduate School of Science and Technology Nara Institute of Science and Technology (NAIST) Nara Japan Faculty of Environmental Life Natural Science and Technology Okayama University Okayama Japan Graduate School of Informatics Osaka Metropolitan University Sakai Japan

Online videos are a potent tool for educators to disseminate knowledge widely to diverse student audiences. However, collecting student feedback remains a significant challenge for lecturers, particularly in the absence of feedback. Understanding students’ subjective comprehension levels during online video lectures with sensor technology is yet to be thoroughly researched. This study uses eye-tracking technology to predict self-reported comprehension levels during video lectures. We recruited 20 participants from Germany and Japan who were invited to watch 50-minute lecture videos in three domains. The participants self-annotate the time segment in each lecture video where they dropout using open-source LabelStudio and answer the survey. We applied Long-Short-Term Memory (LSTM) to the preprocessed dataset and achieved an F1 Score of 0.886 for predicting binary self-annotated comprehension levels. We also introduce EyeUnderstand, the web-based application for visualizing the results of the comprehension estimation. We recruited 28 participants for the user study. As a result, 89.3% of the students and 92.9% of the lecturers confirmed that our application is practical.

关键词： Videos Estimation Gaze tracking Real-time systems Temperature measurement Education data visualization Vocabulary Surveys Pupils

来源：评论

学校读者我要写书评

暂无评论

iControl3D: An Interactive System for Controllable 3D Scene Generation

arXiv

引用

arXiv 2024年

作者： Li, Xingyi Wu, Yizheng Cen, Jun Peng, Juewen Wang, Kewei Xian, Ke Wang, Zhe Cao, Zhiguo Lin, Guosheng School of AIA Huazhong University of Science and Technology Wuhan China S-Lab Nanyang Technological University Singapore Singapore College of Computing and Data Science Nanyang Technological University Singapore Singapore School of EIC Huazhong University of Science and Technology Wuhan China SenseTime Research Hong Kong SAR China

3D content creation has long been a complex and time-consuming process, often requiring specialized skills and resources. While recent advancements have allowed for text-guided 3D object and scene generation, they still fall short of providing sufficient control over the generation process, leading to a gap between the user’s creative vision and the generated results. In this paper, we present iControl3D, a novel interactive system that empowers users to generate and render customizable 3D scenes with precise control. To this end, a 3D creator interface has been developed to provide users with fine-grained control over the creation process. Technically, we leverage 3D meshes as an intermediary proxy to iteratively merge individual 2D diffusion-generated images into a cohesive and unified 3D scene representation. To ensure seamless integration of 3D meshes, we propose to perform boundary-aware depth alignment before fusing the newly generated mesh with the existing one in 3D space. Additionally, to effectively manage depth discrepancies between remote content and foreground, we propose to model remote content separately with an environment map instead of 3D meshes. Finally, our neural rendering interface enables users to build a radiance field of their scene online and navigate the entire scene. Extensive experiments have been conducted to demonstrate the effectiveness of our system. The code will be made available at https://***/xingyi-li/iControl3D. Copyright © 2024, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Correction: Web service location‑allocation using discrete NSGA‑II with matrix based genetic operations and a repair mechanism

引用

Journal of Ambient Intelligence and Humanized computing 2023年第1期15卷 797-798页

作者： Verma, Shanu Pant, Millie Snasel, Vaclav Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee Roorkee India Centre for Artificial Intelligence and Data Science Indian Institute of Technology Roorkee Roorkee India Department of Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic

来源：评论

学校读者我要写书评

暂无评论

WPDA: Frequency-based Backdoor Attack with Wavelet Packet Decomposition

arXiv

引用

arXiv 2024年

作者： Song, Zhengyao Li, Yongqiang Yuan, Danni Liu, Li Wei, Shaokui Wu, Baoyuan School of Instrumentation Science and Engineering Harbin Institute of Technology Heilongjiang Province Harbin150000 China School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen518172 China Guangdong Province Guangzhou511455 China

This work explores backdoor attack, which is an emerging security threat against deep neural networks (DNNs). The adversary aims to inject a backdoor into the model by manipulating a portion of training samples, such that the backdoor could be activated by a particular trigger to make a target prediction at inference. Currently, existing backdoor attacks often require moderate or high poisoning ratios to achieve the desired attack performance, but making them susceptible to some advanced backdoor defenses (e.g., poisoned sample detection). One possible solution to this dilemma is enhancing the attack performance at low poisoning ratios, which has been rarely studied due to its high challenge. To achieve this goal, we propose an innovative frequency-based backdoor attack via wavelet packet decomposition (WPD), which could finely decompose the original image into multiple sub-spectrograms with semantic information. It facilitates us to accurately identify the most critical frequency regions to effectively insert the trigger into the victim image, such that the trigger information could be sufficiently learned to form the backdoor. The proposed attack stands out for its exceptional effectiveness, stealthiness, and resistance at an extremely low poisoning ratio. Notably, it achieves the 98.12% attack success rate on CIFAR-10 with an extremely low poisoning ratio of 0.004% (i.e., only 2 poisoned samples among 50,000 training samples), and bypasses several advanced backdoor defenses. Besides, we provide more extensive experiments to demonstrate the efficacy of the proposed method, as well as in-depth analyses to explain its underlying mechanism. Copyright © 2024, The Authors. All rights reserved.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Blind Omnidirectional Image Quality Assessment Based on Swin Transformer with Scanpath-Oriented 12th

Blind Omnidirectional Image Quality Assessment Based on Swi...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Tang, Xufeng An, Ping Yang, Chao Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai University Shanghai200444 China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai200444 China School of Communication and Information Engineering Shanghai University Shanghai200444 China

ISBN: (纸本)9783031463167

With the emergence of 5th generation mobile communication technology, the demand for Virtual Reality (VR) applications is on the rise worldwide. As one of the technologies related to visual content in VR, the quality evaluation of omnidirectional images has become an important issue. Inspired by the transformer, we propose a novel blind omnidirectional image quality assessment method. Firstly, we predict the path that the human eye follows when viewing omnidirectional images through headsets, and extract the area with the longest gaze duration on the path as the viewport. Then, to consider the intrinsic structural features of each pixel within each viewport, we use the Swin Transformer to extract viewport features. Finally, to establish a general scene perception and accurately evaluate immersive experiences, we construct a spatial viewport map for the entire perceptual scene. The graph structure performs reasoning on the overall relationship based on the spatial perception path. Experimental results demonstrate that our proposed model outperforms the current state-of-the-art Image Quality Assessment metrics, as evidenced by its superior results on two public databases. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

ChatGPT-guided Semantics for Zero-shot Learning

ChatGPT-guided Semantics for Zero-shot Learning

引用

2023 International Conference on Digital Image computing: Techniques and Applications, DICTA 2023

作者： Shubho, Fahimul Hoque Chowdhury, Townim Faisal Cheraghian, Ali Saberi, Morteza Mohammed, Nabeel Rahman, Shafin North South University Dept. of Electrical and Computer Engineering Bangladesh University of Adelaide Australian Institute for Machine Learning Australia Data61 Commonwealth Scientific and Industrial Research Organisation Australia University of Technology Sydney School of Computer Science and Dsi Australia

ISBN: (纸本)9798350382204

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class semantics include manual attributes or automatic word vectors from language models (like word2vec). We know attribute annotation is costly, whereas automatic word vectors are relatively noisy. To address this problem, we explore how ChatGPT, a large language model, can enhance class semantics for ZSL tasks. ChatGPT can be a helpful source to obtain text descriptions for each class containing related attributes and semantics. We use the word2vec model to get a word vector using the texts from ChatGPT. Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT. More specifically, we leverage ChatGPT to provide extra supervision for the class description, eventually benefiting ZSL models. We evaluate our approach on various 2D image (CUB and AwA) and 3D point cloud (ModelNet10, ModelNet40, and ScanObjectNN) datasets and show that it improves ZSL performance. Our work contributes to the ZSL literature by applying ChatGPT for class semantics enhancement and proposing a novel word vector fusion method. © 2023 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Algorithm of Detecting Abnormal data in Geological Disaster System

An Improved Algorithm of Detecting Abnormal Data in Geologic...

引用

International Conference on Computer Network, Electronic and Automation (ICCNEA)

作者： Yupeng Chen Jianguo Wang School of Computer Science and Engineering Xi'an Technological University Xi’an China Research Institute of Artificial Intelligence and Data Science Xi'an Technological University Xi’an China

A large amount of data is collected during geological hazard monitoring, which is extremely valuable for further data mining, hazard monitoring and decision analysis. However, in the process of data collection and transmission may be affected by interference and other factors, resulting in the generation of abnormal data. To extract higher value information from these basic data, it is necessary to improve the quality of source data first, so it is necessary to detect the abnormal data. The monitoring data of the geological disaster are time-series data, which have the characteristics of time-series correlation. The nearest neighbor difference jump anomaly detection algorithm is suitable for monitoring anomalous data of geological disaster system, but there are shortcomings in selecting floating values and correlation perception. To address these problems, the nearest neighbor difference jumping algorithm is improved and a algorithm is proposed to detect anomalous data of geological disasters, i.e., the data series are segmented by using sliding windows, the selection of floating values is improved, the calculation range of difference values is expanded to enhance the correlation of data, and the concept of change speed is incorporated to better perceive the trend of change before and after the data, and finally the anomaly is determined by using the anomaly probability and correlation. After the experimental comparison and analysis, the accuracy and recall rate of the proposed method on the detection of geological disaster data are improved and meet the expected results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Confidence Aware Inverse Constrained Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Subramanian, Sriram Ganapathi Liu, Guiliang Elmahgiubi, Mohammed Rezaee, Kasra Poupart, Pascal Vector Institute for Artificial Intelligence Toronto Canada School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen518172 China Huawei Technologies Canada Canada Cheriton School of Computer Science University of Waterloo Canada

In coming up with solutions to real-world problems, humans implicitly adhere to constraints that are too numerous and complex to be specified completely. However, reinforcement learning (RL) agents need these constraints to learn the correct optimal policy in these settings. The field of Inverse Constraint Reinforcement Learning (ICRL) deals with this problem and provides algorithms that aim to estimate the constraints from expert demonstrations collected offline. Practitioners prefer to know a measure of confidence in the estimated constraints, before deciding to use these constraints, which allows them to only use the constraints that satisfy a desired level of confidence. However, prior works do not allow users to provide the desired level of confidence for the inferred constraints. This work provides a principled ICRL method that can take a confidence level with a set of expert demonstrations and outputs a constraint that is at least as constraining as the true underlying constraint with the desired level of confidence. Further, unlike previous methods, this method allows a user to know if the number of expert trajectories is insufficient to learn a constraint with a desired level of confidence, and therefore collect more expert trajectories as required to simultaneously learn constraints with the desired level of confidence and a policy that achieves the desired level of performance. © 2024, CC BY.

关键词： Reinforcement learning

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：