检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lee, Nahyuk Min, Juhong Lee, Junha Kim, Seungwook Lee, Kanghee Park, Jaesik Cho, Minsu Department of Computer Science and Engineering POSTECH Pohang Korea Republic of Graduate School of Artificial Intelligence POSTECH Pohang Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and computation. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://***/pmtr. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

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

MathReader : Text-to-Speech for Mathematical Documents

MathReader : Text-to-Speech for Mathematical Documents

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sieun Hyeon Kyudan Jung Nam-Joon Kim Hyun Gon Ryu Jaeyoung Do Department of Electrical and Computer Engineering Seoul National University Department of Mathematics Chung-Ang University NVIDIA Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

TTS (Text-to-Speech) document reader from Microsoft, Adobe, Apple, and OpenAI have been serviced worldwide. They provide relatively good TTS results for general plain text, but sometimes skip contents or provide unsatisfactory results for mathematical expressions. This is because most modern academic papers are written in LaTeX, and when LaTeX formulas are compiled, they are rendered as distinctive text forms within the document. However, traditional TTS document readers output only the text as it is recognized, without considering the mathematical meaning of the formulas. To address this issue, we propose MathReader, which effectively integrates OCR, a fine-tuned T5 model, and TTS. MathReader demonstrated a lower Word Error Rate (WER) than existing TTS document readers, such as Microsoft Edge and Adobe Acrobat, when processing documents containing mathematical formulas. MathReader reduced the WER from 0.510 to 0.281 compared to Microsoft Edge, and from 0.617 to 0.281 compared to Adobe Acrobat. This will significantly contribute to alleviating the inconvenience faced by users who want to listen to documents, especially those who are visually impaired. The code is available at https://***/hyeonsieun/MathReader.

关键词： Text recognition Error analysis Pipelines Optical character recognition Graphics processing units Signal processing Real-time systems Mathematical models Text to speech Speech processing

来源：评论

学校读者我要写书评

暂无评论

Audio-aided Character Control for Inertial Measurement Tracking

Audio-aided Character Control for Inertial Measurement Track...

引用

46th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2025

作者： Jang, Hojun Bae, Jinseok Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

ISBN: (纸本)9783038682684

Physics-based character control generates realistic motion dynamics by leveraging kinematic priors from large-scale data within a simulation engine. The simulated motion respects physical plausibility, while dynamic cues like contacts and forces guide compelling human-scene interaction. However, leveraging audio cues, which can capture physical contacts in a costeffective way, has been less explored in animating human motions. In this work, we demonstrate that audio inputs can enhance accuracy in predicting footsteps and capturing human locomotion dynamics. Experiments validate that audio-aided control from sparse observations (e.g., an IMU sensor on a VR headset) enhances the prediction accuracy of contact dynamics and motion tracking, offering a practical auxiliary signal for robotics, gaming, and virtual environments. © 2025 The Authors.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

DEAL: Decoupled Classifier with Adaptive Linear Modulation for Group Robust Early Diagnosis of MCI to AD Conversion

arXiv

引用

arXiv 2024年

作者： Lee, Donggyu Park, Juhyeon Moon, Taesup The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of The Department of Electrical and Computer Engineering Automation and Systems Research Institute Institute of New Media and Communications Interdisciplinary Program in Artificial Intelligence Artificial Intelligent Institute Seoul National University Seoul08826 Korea Republic of

While deep learning-based Alzheimer's disease (AD) diagnosis has recently made significant advancements, particularly in predicting the conversion of mild cognitive impairment (MCI) to AD based on MRI images, there remains a critical gap in research regarding the group robustness of the diagnosis. Although numerous studies pointed out that deep learning-based classifiers may exhibit poor performance in certain groups by relying on unimportant attributes, this issue has been largely overlooked in the early diagnosis of MCI to AD conversion. In this paper, we present the first comprehensive investigation of the group robustness in the early diagnosis of MCI to AD conversion using MRI images, focusing on disparities in accuracy between groups, specifically sMCI and pMCI individuals divided by age. Our experiments reveal that standard classifiers consistently underperform for certain groups across different architectures, highlighting the need for more tailored approaches. To address this, we propose a novel method, dubbed DEAL (DEcoupled classifier with Adaptive Linear modulation), comprising two key components: (1) a linear modulation of features from the penultimate layer, incorporating easily obtainable age and cognitive indicative tabular features, and (2) a decoupled classifier that provides more tailored decision boundaries for each group, further improving performance. Through extensive experiments and evaluations across different architectures, we demonstrate the efficacy of DEAL in improving the group robustness of the MCI to AD conversion prediction. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning 3D Scene Analogies with Neural Contextual Scene Maps

arXiv

引用

arXiv 2025年

作者： Kim, Junho Bae, Gwangtak Lee, Eun Sun Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to comprehensively encapsulate diverse ranges of layouts and open spaces, we propose teaching machines to identify relational commonalities in 3D spaces. Instead of focusing on point-wise or object-wise representations, we introduce 3D scene analogies, which are smooth maps between 3D scene regions that align spatial relationships. Unlike well-studied single instance-level maps, these scene-level maps smoothly link large scene regions, potentially enabling unique applications in trajectory transfer in AR/VR, long demonstration transfer for imitation learning, and context-aware object rearrangement. To find 3D scene analogies, we propose neural contextual scene maps, which extract descriptor fields summarizing semantic and geometric contexts, and holistically align them in a coarse-to-fine manner for map estimation. This approach reduces reliance on individual feature points, making it robust to input noise or shape variations. Experiments demonstrate the effectiveness of our approach in identifying scene analogies and transferring trajectories or object placements in diverse indoor scenes, indicating its potential for robotics and AR/VR applications. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Using Real-Time Integrated computer Vision and Deep Learning for Advanced Factory Safety 4

Using Real-Time Integrated Computer Vision and Deep Learning...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Tsai, Shang-Te Chang, Yu-Cheng Huang, Chao-Yi Yang, Fang-Yuan Chien, Wei Wu, Zong-Rong School Art and Design Sanming University Fujian China National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan National Yunlin University of Science and Technology Department of Information Management Yunlin Taiwan Lunghwa University of Science and Technology Department of Computer Information and Network Engineering Taoyuan Taiwan National Yunlin University of Science and Technology Department of Technical and Vocational Program in Artificial Intelligence Yunlin Taiwan

ISBN: (纸本)9798350360721

Innovative safety in the workplace is vital as the high safety risks associated with electrical engineering construction can lead to injuries or even fatalities. Using computer vision technology, we experimented with scenarios such as 'normal operations' and 'unexpected incidents' to enhance safety measures. We integrated an Internet of Things system into the setup, enabling the system to quickly detect and alert to unexpected events in real-time, thereby improving workplace safety. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

On the powerfulness of textual outlier exposure for visual OoD detection 23

On the powerfulness of textual outlier exposure for visual O...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Sangha Park Jisoo Mok Dahuin Jung Saehyung Lee Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Department of Electrical and Computer Engineering Seoul National University and Interdisciplinary Program in Artificial Intelligence Seoul National University

Successful detection of Out-of-Distribution (OoD) data is becoming increasingly important to ensure safe deployment of neural networks. One of the main challenges in OoD detection is that neural networks output overconfident predictions on OoD data, make it difficult to determine OoD-ness of data solely based on their predictions. Outlier exposure addresses this issue by introducing an additional loss that encourages low-confidence predictions on OoD data during training. While outlier exposure has shown promising potential in improving OoD detection performance, all previous studies on outlier exposure have been limited to utilizing visual outliers. Drawing inspiration from the recent advancements in vision-language pre-training, this paper venture out to the uncharted territory of textual outlier exposure. First, we uncover the benefits of using textual outliers by replacing real or virtual outliers in the image-domain with textual equivalents. Then, we propose various ways of generating preferable textual outliers. Our extensive experiments demonstrate that generated textual outliers achieve competitive performance on large-scale OoD and hard OoD benchmarks. Furthermore, we conduct empirical analyses of textual outliers to provide primary criteria for designing advantageous textual outliers: near-distribution, descriptiveness, and inclusion of visual semantics. Code is available at https://***/wiarae/TOE

关键词：

来源：评论

学校读者我要写书评

暂无评论

PUCA: patch-unshuffle and channel attention for enhanced self-supervised image denoising 23

PUCA: patch-unshuffle and channel attention for enhanced sel...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Hyemi Jang Junsung Park Dahuin Jung Jaihyun Lew Ho Bae Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Cyber Security Ewha Womans University Department of Electrical and Computer Engineering Seoul National University and Interdisciplinary Program in Artificial Intelligence Seoul National University

Although supervised image denoising networks have shown remarkable performance on synthesized noisy images, they often fail in practice due to the difference between real and synthesized noise. Since clean-noisy image pairs from the real world are extremely costly to gather, self-supervised learning, which utilizes noisy input itself as a target, has been studied. To prevent a self-supervised denoising model from learning identical mapping, each output pixel should not be influenced by its corresponding input pixel; This requirement is known as J-invariance. Blind-spot networks (BSNs) have been a prevalent choice to ensure J-invariance in self-supervised image denoising. However, constructing variations of BSNs by injecting additional operations such as downsampling can expose blinded information, thereby violating J-invariance. Consequently, convolutions designed specifically for BSNs have been allowed only, limiting architectural flexibility. To overcome this limitation, we propose PUCA, a novel J-invariant U-Net architecture, for self-supervised denoising. PUCA leverages patch-unshuffle/shuffle to dramatically expand receptive fields while maintaining J-invariance and dilated attention blocks (DABs) for global context incorporation. Experimental results demonstrate that PUCA achieves state-of-the-art performance, outperforming existing methods in self-supervised image denoising.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cell segmentation in fluorescence microscopy images

Cell segmentation in fluorescence microscopy images

引用

IET International Conference on engineering Technologies and Applications (ICETA 2024)

作者： Shao-Yun Yin Wei-Wen Hsu Chih-Hsien Hsia Master Program of Artificial Intelligence National Ilan University Ilan Taiwan Department of Computer Science and Information Engineering National Taitung University Taitung Taiwan

ISBN: (数字)9781837242252

For microscopic cells images, cells’ morphologies are widely varied among different imaging modalities and staining methods. For fluorescence microscopy images, Poisson noises present in images due to the lightening, causing photobleaching, which makes it challenging in analysis with the deep learning models. Traditionally, median filtering can be applied to the original image for denoising, however, it also results in a blurry image, which is harmful to segmentation. In this study, the Haar Wavelet Transform is used to alleviate the photobleaching problem for cell segmentation, integrated to the framework without interfering with feature extraction by the backbone model. For our experiments, instance segmentation for fluorescence-stained cells was performed based on U-Net architecture with the method of gradient flow tracking proposed by Cellpose. And the Haar wavelet downsampling is embedded in the skip connections to verify if it can improve the segmentation performance for fluorescence images. The experimental results show that the approach of Haar wavelet downsampling embedded in the skip connections achieve superior performance among the other settings. Compared with the performance of the baseline model, the performance of the proposed model reached 0.732 in F1-score, which surpassed the one of baseline model (0.6341) by almost 0.1.

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：