检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lee, Saehyung Yoon, Seunghyun Bui, Trung Shi, Jing Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Adobe Research Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. Our analysis reveals that existing hallucination detection methods struggle with detailed captions. We attribute this to the increasing reliance of MLLMs on their generated text, rather than the input image, as the sequence length grows. To address this issue, we propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions. Additionally, we introduce an evaluation framework and a benchmark dataset to facilitate the systematic analysis of detailed captions. Our experiments demonstrate that our proposed evaluation method better aligns with human judgments of factuality than existing metrics and that existing approaches to improve the MLLM factuality may fall short in hyper-detailed image captioning tasks. In contrast, our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V. Finally, we highlight a limitation of VQA-centric benchmarking by demonstrating that an MLLM’s performance on VQA benchmarks may not correlate with its ability to generate detailed image captions. © 2024, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Towards cross-modal causal structure and representation learning 2

Towards cross-modal causal structure and representation lear...

引用

2nd Machine Learning for Health Symposium, ML4H 2022

作者： Mao, Haiyi Liu, Hongfu Xiaotian Dou, Jason Benos, Panayiotis V. Joint CMU-Pitt PhD Program in Computational Biology University of Pittsburgh United States Michtom School of Computer Science Brandeis University United States Department of Electrical and Computer Engineering University of Pittsburgh United States Department of Epidemiology University of Florida United States

Does the SARS-CoV-2 virus cause patients' chest X-Rays ground-glass opacities? Does an IDH-mutation cause differences in patients' MRI images? Conventional causal discovery algorithms, although well developed to uncover the cause-effect relationships on structured data, cannot elucidate causal relations between unstructured images and structured scalar variables due to the complexity of the former. In this paper, we consider causal discovery between images and structured (scalar) variables. Specifically, we derive low dimensional image representations to analyze with structured variables. We propose a two-module amortized variational algorithm named Cross-Modal Variational Causal representation and structure Learning (CMCL). CMCL jointly learns identifiable representations given a set of independent structured variables and causal relations via formulating latent representations and structured variables into a direct acyclic graph. Moreover, we further enforce counterfactual invariance/variance onto representations. We demonstrate that CMCL outperforms other related methods on synthetic datasets and validate causal relations on semi-synthetic datasets by visualization. © 2022 P.N. Argaw, E. Healey & I.S. Kohane.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Precision Oral Medicine: A DPR Segmentation and Transfer Learning Approach for Detecting Third Molar Compress Inferior Alveolar Nerve

引用

IEEE Journal of Translational engineering in Health and Medicine 2025年 13卷 286-298页

作者： Lin, Yuan-Jin Chen, Shih-Lun Mao, Yi-Cheng Chen, Tsung-Yi Peng, Cheng-Hao Tsai, Tzu-Hsiang Li, Kuo-Chen Chen, Chiung-An Tu, Wei-Chen Abu, Patricia Angela R. National Cheng Kung University Department of Program on Semiconductor Manufacturing Technology Academy of Innovative Semiconductor and Sustainable Manufacturing Tainan City701401 Taiwan Chung Yuan Christian University Department of Electronic Engineering Taoyuan City32023 Taiwan Taoyuan Chang Gang Memorial Hospital Department of Operative Dentistry Taoyuan City33305 Taiwan Feng Chia University Department of Electronic Engineering Taichung city40724 Taiwan Chung Yuan Christian University Taoyuan City32023 Taiwan Chung Yuan Christian University Department of Information Management Taoyuan City32023 Taiwan Ming Chi University of Technology Department of Electronic Engineering New Taipei City243303 Taiwan National Cheng Kung University Department of Electrical Engineering Tainan city701401 Taiwan Ateneo de Manila University Department of Information Systems and Computer Science Quezon City Philippines

Objective: Extraction of the third molar of the mandible is one of the most common oral surgical procedures. Preoperative monitoring and assessment are crucial to mitigate neurological risks. Identifying whether the third molar in the mandible compresses the inferior alveolar nerve still relies on dental professionals, a task that is repetitive and time-consuming. Thus, the primary objective is to utilize dental panoramic radiography for image processing and classify whether the third molar compresses the inferior alveolar nerve, aiming to reduce the demand for CT images in symptom diagnosis and mitigate the risks associated with high-dose radiation. Technology or Method: This study proposes an innovative dental panoramic radiography segmentation technique to locate the third molar position. Subsequently, an innovative edge masking enhancement method is used to extract features of the inferior alveolar nerve and the third molar. Moreover, a transformer-based image detection model to consider whether the third molar compresses the inferior alveolar nerve. Results: The third molar position localization method achieved an accuracy rate of 97.92%, compared to recent research at least improved by 3.6% accuracy. Subsequently, innovative edge masking and image enhancement methods improve classification accuracy by 4.3%, when supplemented with computed tomography scan images for further evaluation, the maximum accuracy reached 98.45%, representing a 4.5% improvement compared to previous studies. Conclusions: The third molar position detection results will impact the identification of the inferior alveolar nerve compressed by the third molar. Through the innovative edge region segmentation algorithm can effectively distinguish this object, and the overall evaluation accuracy can be improved by approximately 3.8%. © 2013 IEEE.

关键词： Neurophysiology

来源：评论

学校读者我要写书评

暂无评论

Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards

Safe CoR: A Dual-Expert Approach to Integrating Imitation Le...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hyeokjin Kwon Gunmin Lee Junseo Lee Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Seoul Korea Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations—reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real-world Jackal platform. Our proposed framework improves algorithm performance by 39% and reduces constraint violations by 88% on the real-world Jackal platform, highlighting its effectiveness. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents.

关键词： Navigation Imitation learning Focusing Reinforcement learning Autonomous agents Safety Reliability Optimization Intelligent robots Faces

来源：评论

学校读者我要写书评

暂无评论

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

arXiv

引用

arXiv 2024年

作者： Jang, Hojun 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

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP. Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

RN-SDEs: Limited-Angle CT Reconstruction with Residual Null-Space Diffusion Stochastic Differential Equations

arXiv

引用

arXiv 2024年

作者： Guo, Jiaqi Lopez-Tapia, Santiago Li, Wing Shun Wu, Yunnan Carignano, Marcelo Backman, Vadim Dravid, Vinayak P. Katsaggelos, Aggelos K. The Department of Electrical and Computer Engineering Northwestern University IL60201 United States The Applied Physics Program Northwestern University EvanstonIL60201 United States

Computed tomography is a widely used imaging modality with applications ranging from medical imaging to material analysis. One major challenge arises from the lack of scanning information at certain angles, leading to distorted CT images with artifacts. This results in an ill-posed problem known as the Limited Angle Computed Tomography (LACT) reconstruction problem. To address this problem, we propose Residual Null-Space Diffusion Stochastic Differential Equations (RN-SDEs), which are a variant of diffusion models that characterize the diffusion process with mean-reverting (MR) stochastic differential equations. To demonstrate the generalizability of RN-SDEs, our experiments are conducted on two different LACT datasets, i.e., ChromSTEM and C4KC-KiTS. Through extensive experiments, we show that by leveraging learned Mean-Reverting SDEs as a prior and emphasizing data consistency using Range-Null Space Decomposition (RNSD) based rectification, RN-SDEs can restore high-quality images from severe degradation and achieve state-of-the-art performance in most LACT tasks. Additionally, we present a quantitative comparison of computational complexity and runtime efficiency, highlighting the superior effectiveness of our proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Assessing Distributed Energy Resource Hosting Capacity Under Different Grid-Tie Inverter Control Strategies

Assessing Distributed Energy Resource Hosting Capacity Under...

引用

Workshop on Communication Networks and Power Systems (WCNPS)

作者： Brenda L. M. Santos Luciano S. Barros Daniel Barbosa Fernando A. Moreira Graduate Program in Electrical Engineering Federal University of Bahia Salvador Brazil Computer Systems Department Federal University of Paraíba João Pessoa Brazil Department of Electrical and Computer Engineering Federal University of Bahia Salvador Brazil

Despite the potential benefits that the integration of distributed energy resources (DERs) can bring to the system, it may cause problems related to power quality constraints, such $as$ reverse power flow in substation and overvoltages. An effective approach to address these problems involves the adoption of reactive and active power control in grid-tie inverters associated with DER. Therefore, this paper assesses the impacts of grid-tie inverter control modes, including both Volt-Var and Volt-Watt strategies, on the DER hosting capacity. In order to improve the overall system operation, modifications in the Volt-Var and Volt-Watt curves were proposed. It is noteworthy that these control strategies can have adverse effects on certain distribution system performance indicators, such $as$ voltage deviation and power losses; for this reason, these indicators are also evaluated in this study. A stochastic approach was adopted to deal with the uncertainties associated with DERs and loads. Finally, from tests conducted in the IEEE 33-bus test system, it was concluded that the proper adjustment of the Volt-Var and Volt-Watt control curves significantly influences DER hosting capacity, $as$ well $as$ voltage deviation and power losses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Calibrating Panoramic Depth Estimation for Practical Localization and Mapping

Calibrating Panoramic Depth Estimation for Practical Localiz...

引用

International Conference on computer Vision (ICCV)

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

The absolute depth values of surrounding environments provide crucial cues for various assistive technologies, such as localization, navigation, and 3D structure estimation. We propose that accurate depth estimated from panoramic images can serve as a powerful and light-weight input for a wide range of downstream tasks requiring 3D information. While panoramic images can easily capture the surrounding context from commodity devices, the estimated depth shares the limitations of conventional image-based depth estimation; the performance deteriorates under large domain shifts and the absolute values are still ambiguous to infer from 2D observations. By taking advantage of the holistic view, we mitigate such effects in a self-supervised way and fine-tune the network with geometric consistency during the test phase. Specifically, we construct a 3D point cloud from the current depth prediction and project the point cloud at various viewpoints or apply stretches on the current input image to generate synthetic panoramas. Then we minimize the discrepancy of the 3D structure estimated from synthetic images without collecting additional data. We empirically evaluate our method in robot navigation and map-free localization where our method shows large performance enhancements. Our calibration method can therefore widen the applicability under various external conditions, serving as a key component for practical panorama-based machine vision systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LDL: Line Distance Functions for Panoramic Localization

LDL: Line Distance Functions for Panoramic Localization

引用

International Conference on computer Vision (ICCV)

作者： Junho Kim Changwoon Choi Hojun Jang Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

We introduce LDL, a fast and robust algorithm that localizes a panorama to a 3D map using line segments. LDL focuses on the sparse structural information of lines in the scene, which is robust to illumination changes and can potentially enable efficient computation. While previous line-based localization approaches tend to sacrifice accuracy or computation time, our method effectively observes the holistic distribution of lines within panoramic images and 3D maps. Specifically, LDL matches the distribution of lines with 2D and 3D line distance functions, which are further decomposed along principal directions of lines to increase the expressiveness. The distance functions provide coarse pose estimates by comparing the distributional information, where the poses are further optimized using conventional local feature matching. As our pipeline solely leverages line geometry and local features, it does not require costly additional training of line-specific features or correspondence matching. Nevertheless, our method demonstrates robust performance on challenging scenarios including object layout changes, illumination shifts, and large-scale scenes, while exhibiting fast pose search terminating within a matter of milliseconds. We thus expect our method to serve as a practical solution for line-based localization, and complement the well-established point-based paradigm. The code for LDL is available through the following link: https://***/82magnolia/panoramic-localization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing Classical Header Bits for Quantum Wrapper Networking with O-band Quantum Signal

Designing Classical Header Bits for Quantum Wrapper Networki...

引用

Frontiers in Optics + Laser Science 2023, FiO, LS 203: Part of Frontiers in Optics + Laser Science 2023

作者： Gül, G. Berkay On, M. Singh, S.K. Proietti, R. Kanter, G.S. Yoo, S.J.B. Kumar, P. Graduate Program in Applied Physics Northwestern University 2145 Sheridan Road EvanstonIL60208 United States Department of Electrical and Computer Engineering University of California Davis DavisCA95616 United States Department of Electronics and Communication Eng. Indian Institute of Technology Roorkee247667 India Department of Electronics and Telecommunications Engineering Politecnico di Torino Italy Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States

We investigate the impact of wavelength choice for the classical headers in quantum wrapper networking with O-band quantum payload. We show that a C-band header performs substantially better than an O-band header. ... 详细信息

ISBN: (纸本)9781957171296

关键词： Bandpass filters Beam splitters Bit error rate Entanglement distribution Quantum teleportation Raman scattering

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：