检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Buettner, Kyle Kovashka, Adriana Intelligent Systems Program University of Pittsburgh PA United States Department of Computer Science University of Pittsburgh PA United States

Vision-language alignment learned from image-caption pairs has been shown to benefit tasks like object recognition and detection. Methods are mostly evaluated in terms of how well object class names are learned, but captions also contain rich attribute context that should be considered when learning object alignment. It is unclear how methods use this context in learning, as well as whether models succeed when tasks require attribute and object understanding. To address this gap, we conduct extensive analysis of the role of attributes in vision-language models. We specifically measure model sensitivity to the presence and meaning of attribute context, gauging influence on object embeddings through unsupervised phrase grounding and classification via description methods. We further evaluate the utility of attribute context in training for open-vocabulary object detection, fine-grained text-region retrieval, and attribution tasks. Our results show that attribute context can be wasted when learning alignment for detection, attribute meaning is not adequately considered in embeddings, and describing classes by only their attributes is ineffective. A viable strategy that we find to increase benefits from attributes is contrastive training with adjective-based negative captions. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Towards focused plan monitoring: a technique and an application to mobile robots

Towards focused plan monitoring: a technique and an applicat...

引用

IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA)

作者： M.E. Pollack C. McCarthy Intelligent Systems Program University of Pittsburgh Pittsburgh PA USA Department of Computer Science University of Pittsburgh Pittsburgh PA USA

Until recently, techniques for AI plan generation relied on highly restrictive assumptions that were almost always violated in real-world environments; consequently, robot designers adopted reactive architectures and avoided AI planning techniques. Some recent research efforts have focused on obviating such assumptions by developing techniques that enable the generation and execution of plans in dynamic, uncertain environments. In this paper, we discuss one such technique, rationale-based monitoring, originally introduced by Veloso, Pollack, and Cox (1998), and describe our use of it in a simple mobile robot environment. We review the original approach, describe how it can be adapted for a causal-link planner, and provide experimental results demonstrating that it can lead to improved plans without consuming excessive overhead. We also describe our use of rationale-based monitoring in a mobile robot office-assistant project currently in progress.

关键词： Mobile robots Artificial intelligence Meeting planning computerized monitoring Application software computer science intelligent systems intelligent robots computer architecture Process planning

来源：评论

学校读者我要写书评

暂无评论

Wood Defect Detection using Grayscale Images and an Optimized Feature Set

Wood Defect Detection using Grayscale Images and an Optimize...

引用

Annual Conference of Industrial Electronics Society

作者： P. Cavalin L. S. Oliveira A. L. Koerich A. S. Britto INVISYS Intelligent Vision Systems Curitiba Brazil Graduate Program in Computer Science Pontifical Catholic University of Paraná Curitiba Brazil

In this paper we address the issue of detecting defects in wood using features extracted from grayscale images. The feature set proposed here is based on the concept of texture and it is computed from the co-occurrence matrices. The features provide measures of properties such as smoothness, coarseness, and regularity. Comparative experiments using a color image based feature set extracted from percentile histograms are carried to demonstrate the efficiency of the proposed feature set. Two different learning paradigms, neural networks and support vector machines, and a feature selection algorithm based on multi-objective genetic algorithms were considered in our experiments. The experimental results show that after feature selection, the grayscale image based feature set achieves very competitive performance for the problem of wood defect detection relative to the color image based features

关键词： Gray-scale Histograms Feature extraction Color Machine learning Neural networks Support vector machines Genetic algorithms Humans Robustness

来源：评论

学校读者我要写书评

暂无评论

The impact of overconfidence bias on practical accuracy of Bayesian network models: An empirical study

The impact of overconfidence bias on practical accuracy of B...

引用

6th UAI Bayesian Modelling Applications Workshop, BMAW 2008

作者： Druzdzel, Marek J. Oniśko, Agnieszka Faculty of Computer Science Bialystok Technical University 15-351 Bialystok Wiejska 45A Poland Decision Systems Laboratory School of Information Sciences and Intelligent Systems Program University of Pittsburgh Pittsburgh PA 15260 United States Magee Womens Hospital University of Pittsburgh Medical Center Pittsburgh PA 15260 United States

In this paper, we examine the influence of overconfidence in parameter specification on the performance of a Bayesian network model in the context of Hepar II, a sizeable Bayesian network model for diagnosis of liver disorders. We enter noise in the parameters in such a way that the resulting distributions become biased toward extreme probabilities. We believe that this offers a systematic way of modeling expert overconfidence in probability estimates. It appears that the diagnostic accuracy of Hepar II is less sensitive to overconfidence in probabilities than it is to underconfidence and to random noise, especially when noise is very large.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Wood defect detection using grayscale images and an optimized feature set

Wood defect detection using grayscale images and an optimize...

引用

IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics

作者： Cavalin, P. Oliveira, L.S. Koerich, A.L. Britto Jr., A.S. Pontifical Catholic University of Parana Graduate Program in Computer Science Rua Imaculada Conceição 1155 Curitiba PR 80215-901 Brazil INVISYS Intelligent Vision Systems Rua Prof. Algacyr Munhoz Mader 3775 Curitiba PR 80350-010 Brazil

ISBN: (纸本)1424401364

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Building an English-Iraqi Arabic machine translation system for spoken utterances with limited resources

Building an English-Iraqi Arabic machine translation system ...

引用

INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP

作者： Riesa, Jason Mohit, Behrang Knight, Kevin Marcu, Daniel Department of Computer Science Johns Hopkins University Baltimore MD 21218 United States Intelligent Systems Program University of Pittsburgh Pittsburgh PA 15260 United States Information Sciences Institute University of Southern California Marina del Rey CA 90292 United States

ISBN: (纸本)9781604234497

This paper presents an English-Iraqi Arabic speech-to-speech statistical machine translation system using limited resources. In it, we explore the constraints involved, how we endeavored to mitigate such problems as a non-standard orthography and a highly inflected grammar, and discuss leveraging existing plentiful resources for Modern Standard Arabic to assist in this task. These combined techniques yield a reduction in unknown words at translation time by over 40% and a +3.65 increase in BLEU score over a previous state-of-the-art system using the same parallel training corpus of spoken utterances.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Scalability in Autoencoder-based OFDM Communication System

Scalability in Autoencoder-based OFDM Communication System

引用

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Seizan Tsugawa Takao Toma Shiho Oshiro Tomohisa Wada Computer Science and Intelligent Systems Program University of the Ryukyus Okinawa Japan Magna Design Net Inc Okinawa Japan Information Technology Center University of the Ryukyus Okinawa Japan Dept. of Engineering Area of Computer Science and Intelligent Systems University of the Ryukyus Okinawa Japan

This paper proposed Scalability in Autoencoder-based Orthogonal Frequency Division Multiplexing(OFDM) communication system. In the previous research, only the comparison between IEEE802.11a and Autoencoder by the conventional OFDM communication system was performed, and it was proved that the communication system created by Autoencoder exceeded the performance of the conventional system. Therefore, in this paper, it uses IEEE802.11n and compare whether it can be improved by expanding the bandwidth and using ***802.11n standard has an FFT length of 128, a subcarrier number of 114 (108 for data), and modulation schemes of Quadrature Phase Shift Keying(QPSK), 16 Quadrature Amplitude Modulation (16QAM). The GI length is 800ns and the symbol length is 4000ns. In the simulation, a computer simulation was performed using a conventional OFDM communication system and a communication system generated by Autoencoder. Assuming that the simulation environment had an Signal-to-Noise Ratio (SNR) of 0 to 30 and an amplitude r of 0.0 to 1.0, the Symbol Error Rate (SER) status for each SNR was output. As a result of computer simulation, QPSK converged at SNR 27 ㏈ at IEEE 802.11a, but was able to reduce SER overwhelmingly to SNR 12 ㏈ at IEEE 802.11n. Also, in 16QAM the convergence at r=0.0 is the same as for SNR22 ㏈, but in IEEE 802.11a it does not converge after r=0.6, but in IEEE 802.11n it does not converge only at r=0.9 and r=1.0 . As a future task, it will use IEEE802.11ac, which enables communication speeds several times faster than IEEE802.11n, examine whether it is possible to further improve accuracy. And it will continue our research to correspond MIMO communication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

intelligent Constellation Generation based on Autoencoder Communication System

Intelligent Constellation Generation based on Autoencoder Co...

引用

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Kaisei Matsumoto Takao Toma Shiho Oshiro Tomohisa Wada Computer Science and Intelligent Systems Program University of the Ryukyus Okinawa Japan Magna Design Net Inc Okinawa Japan Information Technology Center University of the Ryukyus Okinawa Japan Dept. of Engineering Area of Computer Science and Intelligent Systems University of the Ryukyus Okinawa Japan

This paper discusses intelligent constellation generation based on autoencoder communication system. In previous studies, the amplitude was set to fluctuate between r=0.0 and 1.0. However, when checking the generated constellation, distortion was confirmed instead of the conventional symbol arrangement. Therefore, in this paper, it compares the case where the amplitude is constant, the case where the average amplitude within a Minibatch is 1, and the case where the average amplitude is 1 for Interval time. The communication standard used in this research is IEEE 802.11a, assuming wireless Local Area Network (LAN) specifications. The IEEE 802.11a standard has an Fast Fourier Transform (FFT) length of 64, a subcarrier number of 52, and Quadrature Phase Shift Keying (QPSK) and 16 Quadrature Amplitude Modulation (QAM), modulation methods. A guard interval of 800 ns is added and the symbol length is 4000 ns. First, a simulation was performed under the condition that the amplitude was kept constant. QPSK with 4 symbols, constant amplitude model is rounded more than previous research result. 16QAM with 16 symbols is arranged regularly like lined up on a line. Second, the simulation was performed under the condition that the average amplitude within the minibatch was set to 1. QPSK with 4 symbols, appears to rotate clockwise. 16QAM with 16 symbols has a more uniform symbol placement than previous research result. Third, a simulation was performed under the condition that the average amplitude within Interval time was set to 1. QPSK with 4 symbols, is the closest to square among QPSK output results so far. The direction is slightly tilted, but if it can be rotated a little more, it may be possible to reproduce the same symbol arrangement as before. 16QAM with 16 symbols, the symbol arrangement is biased as a whole. However, it can be seen that are arranged in line on the line, perhaps due to regularity. As future work, in addition to the conditions set this time, it will exa

关键词：

来源：评论

学校读者我要写书评

暂无评论

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 2824-2835页

作者： Chiu, Ching-Yu Muller, Meinard Davies, Matthew E. P. Su, Alvin Wen-Yu Yang, Yi-Hsuan National Cheng Kung University Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701401 Taiwan International Audio Laboratories Erlangen Erlangen91058 Germany University of Coimbra Department of Informatics Engineering Centre for Informatics and Systems Coimbra3004-531 Portugal National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Taiwan AI Labs Yating Music Team Taipei103622 Taiwan Academia Sinica Research Center for IT Innovation Taipei11529 Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use 'post-processing trackers' (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called 'predominant local pulses' (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2014 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Towards Scalable Automated Grading: Leveraging Large Language Models for Conceptual Question Evaluation in Engineering 1

Towards Scalable Automated Grading: Leveraging Large Languag...

引用

1st Workshop on Large Foundation Models for Educational Assessment

作者： Gao, Rujun Guo, Xiaosu Li, Xiaodi Narayanan, Arun Balajiee Lekshmi Thomas, Naveen Srinivasa, Arun R. J. Mike Walker’66 Department of Mechanical Engineering Texas A&M University United States Computer Science Department University of Texas Dallas United States Intelligent Systems Program University of Pittsburgh United States Department of Artificial Intelligence and Informatics Mayo Clinic United States

This study explores the feasibility of using large language models (LLMs), specifically GPT-4o (ChatGPT), for automated grading of conceptual questions in an undergraduate Mechanical Engineering course. We compared the grading performance of GPT-4o with that of human teaching assistants (TAs) on ten quiz problems from the MEEN 361 course at Texas A&M University, each answered by approximately 225 students. Both the LLM and TAs followed the same instructor-provided rubric to ensure grading consistency. We evaluated performance using Spearman’s rank correlation coefficient and Root Mean Square Error (RMSE) to assess the alignment between rankings and the accuracy of scores assigned by GPT-4o and TAs under zero- and few-shot grading settings. In the zero-shot setting, GPT-4o demonstrated a strong correlation with TA grading, with Spearman’s rank correlation coefficient exceeding 0.6 in seven out of ten datasets and reaching a high of 0.9387. Our analysis reveals that GPT-4o performs well when grading criteria are straightforward but struggles with nuanced answers, particularly those involving synonyms not present in the rubric. The model also tends to grade more stringently in ambiguous cases compared to human TAs. Overall, ChatGPT shows promise as a tool for grading conceptual questions, offering scalability and consistency. © 2024 R. Gao1, X. Guo2, X. Li4, A.B.L. Narayanan3, N. Thomas1 & A.R. Srinivasa1.

关键词： Mean square error

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：