检索结果-内蒙古大学图书馆

IEEE Visual Communications and Image Processing (VCIP)

作者： Hao Wei Chenyang Ge Xin Qiao Pengchao Deng Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

In this paper, we propose a two-branch deblurring framework. Given a blurred image, we first extract the edge map and employ an edge refinement network to recover the structure. Then the refined edge map is utilized to guide the subsequent deblurring process for correct structure recovery. Specifically, we develop a lightweight omni-dimensional attention module for long-range dependencies modeling and plug it into the edge refinement network, which effectively handles blur patterns with high variation. Furthermore, we propose a dynamic feature upsample module, which integrates dynamic convolution with upsampling and adaptively deals with the non-uniform blur. Extensive experiments show that our method outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction

arXiv

引用

arXiv 2025年

作者： Rotondi, Dennis Scaparro, Fabio Blum, Hermann Arras, Kai O. Socially Intelligent Robotics Lab Institute for Artificial Intelligence University of Stuttgart Germany Robot Perception and Learning Lab LAMARR Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

The concept of 3D scene graphs is increasingly recognized as a powerful semantic and hierarchical representation of the environment. Current approaches often address this at a coarse, object-level resolution. In contrast, our goal is to develop a representation that enables robots to directly interact with their environment by identifying both the location of functional interactive elements and how these can be used. To achieve this, we focus on detecting and storing objects at a finer resolution, focusing on affordance-relevant parts. The primary challenge lies in the scarcity of data that extends beyond instance-level detection and the inherent difficulty of capturing detailed object features using robotic sensors. We leverage currently available 3D resources to generate 2D data and train a detector, which is then used to augment the standard 3D scene graph generation pipeline. Through our experiments, we demonstrate that our approach achieves functional element segmentation comparable to state-of-the-art 3D models and that our augmentation enables task-driven affordance grounding with higher accuracy than the current solutions. © 2025, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Object-Centric Image to Video Generation with Language Guidance

arXiv

引用

arXiv 2025年

作者： Villar-Corrales, Angel Plepi, Gjergj Behnke, Sven Autonomous Intelligent Systems Computer Science Institute VI – Intelligent Systems and Robotics Center for Robotics Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Accurate and flexible world models are crucial for autonomous systems to understand their environment and predict future events. Object-centric models, with structured latent spaces, have shown promise in modeling object dynamics and interactions, but often face challenges in scaling to complex datasets and incorporating external guidance, limiting their applicability in robotics. To address these limitations, we propose TextOCVP, an object-centric model for image-to-video generation guided by textual descriptions. TextOCVP parses an observed scene into object representations, called slots, and utilizes a text-conditioned transformer predictor to forecast future object states and video frames. Our approach jointly models object dynamics and interactions while incorporating textual guidance, thus leading to accurate and controllable predictions. Our method’s structured latent space offers enhanced control over the prediction process, outperforming several image-to-video generative baselines. Additionally, we demonstrate that structured object-centric representations provide superior controllability and interpretability, facilitating the modeling of object dynamics and enabling more precise and understandable predictions. Videos and code are available at https://***/TextOCVP/. © 2025, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

A Study on the Necessity to Manage the Psychological States of Workers in Shipyard 13

A Study on the Necessity to Manage the Psychological States ...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Hwang, Yoonsook Jung, Woo-Sung Yoo, Dae Seung Artificial Intelligence Research Laboratory Electronics and Telecommunications Research Institute Intelligent Robotics Research Division Daejeon Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

The purpose of this study tried to examine the need to understand and manage the psychological states (e.g., fatigue, workload, job stress, and anxiety, etc.) of shipyard workers through a review of related studies. As a result of the review, it was confirmed that the psychological state of workers affects not only their health but also their work performance. Also, this suggests that it is necessary to carefully examine not only the safety of the physical environment itself, but also the safety measures for workers who move in real time at the field of shipyard. © 2022 IEEE.

关键词： Shipyards

来源：评论

学校读者我要写书评

暂无评论

Two-Stream (2+1)D CNN Based on Frame Difference Attention for Driver Behavior Recognition 10

Two-Stream (2+1)D CNN Based on Frame Difference Attention fo...

引用

10th International Conference on Dependable Systems and Their Applications, DSA 2023

作者： Zou, Yang Du, Shaoyi Han, Hongcheng Liu, Yuying Tian, Zhiqiang Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Shaanxi Xi'an China Shunan Academy of Artificial Intelligence Zhejiang Ningbo China Xi'an Jiaotong University School of Software Engineering Shaanxi Xi'an China

ISBN: (纸本)9798350304770

Driving behavior recognition is a key technology in human-machine cooperative driving, which plays an important role in the construction of an intelligent transportation environment. Due to the similarity of drivers ' actions and backgrounds in driving environments, it's challenging for existing behavior recognition methods to recognize behaviors in driving environments precisely. To solve these problems, we propose the two-stream (2+1)D CNN with Frame Difference Attention Module. First, we use two streams to process the information captured from the face camera and road camera and use the Squeeze and Excitation attention module to fuse the stream information. Second, we propose the Frame Difference Attention Module to enhance the changes between adjacent frames so that the subtle actions in driving environments can be captured easier. We test our network on the Brain4Cars dataset and have a good performance on it. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Accelerated gradient tracking over time-varying graphs for decentralized optimization

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 13187-13238页

作者： Huan Li Zhouchen Lin Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin China State Key Lab of General AI School of Intelligence Science and Technology Institute for Artificial Intelligence Peking University Beijing China and Pazhou Laboratory (Huangpu) Guangzhou China

Decentralized optimization over time-varying graphs has been increasingly common in modern machine learning with massive data stored on millions of mobile devices, such as in federated learning. This paper revisits the widely used accelerated gradient tracking and extends it to time-varying graphs. We prove that the practical single loop accelerated gradient tracking needs $O((\frac{\gamma}{1-\sigma_{\gamma}})^2\sqrt{\frac{L}{\epsilon}})$ and $O((\frac{\gamma}{1-\sigma_{\gamma}})^{1.5}\sqrt{\frac{L}{\mu}} log{\frac{1}{\epsilon}})$ iterations to reach an ε-optimal solution over time-varying graphs when the problems are nonstrongly convex and strongly convex, respectively, where γ and σγ are two common constants charactering the network connectivity, L and µ are the smoothness and strong convexity constants, respectively, and one iteration corresponds to one gradient oracle call and one communication round. Our convergence rates improve significantly over the ones of $O(\frac{1}{\epsilon^{5/7}})$ and $O((\frac{L}{\mu})^{5/7}\frac{1}{(1-\sigma)^{1.5}}\log\frac{1}{\epsilon})$, respectively, which were proved in the original literature of accelerated gradient tracking only for static graphs, where $\frac{\gamma}{1-\sigma_{\gamma}}$ equals 1/1-σ when the network is time-invariant. When combining with a multiple consensus subroutine, the dependence on the network connectivity constants can be further improved to O(1) and $O(\frac{\gamma}{1-\sigma_{\gamma}})$ for the gradient oracle and communication round complexities, respectively. When the network is static, by employing the Chebyshev acceleration, our complexities exactly match the lower bounds without hiding any poly-logarithmic factor for both nonstrongly convex and strongly convex problems.

关键词： decentralized optimization accelerated gradient tracking time-varying graphs

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Application of Internet+ BIM Technology in Smart Site

Research on Intelligent Application of Internet+ BIM Technol...

引用

作者： Han, Ting Alturjman, Sinem Fuzhou University of International Studies and Trade Fujian Fuzhou350202 China Artificial Intelligence Engineering Department AI and Robotics Institute Near East University Mersin 10 Turkey

Based on the model of "Internet+ BIM technology", Smart site can improve the construction Productivity and scientific management. This thesis mainly studied the effective method of building smart site in the context of "Internet+ BIM technology". It introduced the current situation of smart site, and the relationship between Internet, BIM technology and smart construction site. In view of the existing problems, the intelligent management mode based on Internet+ BIM technology was put forward. Applying BIM technology the concrete application of intelligent site management system was *** provided a new idea for the realization of construction project management. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

SAMPLE EFFICIENT DEEP REINFORCEMENT LEARNING VIA UNCERTAINTY ESTIMATION 10

SAMPLE EFFICIENT DEEP REINFORCEMENT LEARNING VIA UNCERTAINTY...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Mai, Vincent Mani, Kaustubh Paull, Liam Robotics and Embodied AI Lab Mila - Quebec Institute of Artificial Intelligence Université de Montréal QC Canada

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As this noise is heteroscedastic, its effects can be mitigated using uncertainty-based weights in the optimization process. Previous methods rely on sampled ensembles, which do not capture all aspects of uncertainty. We provide a systematic analysis of the sources of uncertainty in the noisy supervision that occurs in RL, and introduce inverse-variance RL, a Bayesian framework which combines probabilistic ensembles and Batch Inverse Variance weighting. We propose a method whereby two complementary uncertainty estimation methods account for both the Q-value and the environment stochasticity to better mitigate the negative impacts of noisy supervision. Our results show significant improvement in terms of sample efficiency on discrete and continuous control tasks. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Industrial Humanless Monitoring System over 5G Networks in the Shipyard Environment 13

Industrial Humanless Monitoring System over 5G Networks in t...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Jung, Woo-Sung Yoo, Dae Seung Electronics and Telecommunications Research Institute Intelligent Robotics Research Division Artificial Intelligence Research Laboratory Daejeon Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

As the development of hardware technology and the application of AI technology become popular, efforts to apply image-based services to real industrial sites are increasing. In particular, the development of image-based worker recognition technology is a field in which various studies are being conducted as a base technology that can be widely used in many industrial fields, such as industrial health, safety monitoring, work process management, and collaboration between humans and robots. However, opposition from labor unions due to workers' privacy protection issues and outdated on-site network facilities are acting as obstacles to the application of video-based application services in actual industrial sites. To solve this privacy problem, we introduced a technology that recognizes a worker at the end device where an image sensor is installed and replaces the recognized worker with an existing background image. In this paper, we introduce the previously proposed worker deletion technology [1] and analyze the problems that occurred in field experiments. In addition, the structure linked with the 5G network is additionally presented, and advanced performance improvement techniques are presented. The performance of the implemented algorithm is applied to various hardware platforms to find out its performance and applicability. © 2022 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

FaRo-PPF: Fast and Robust Point Pair Feature for 6D Pose Estimation in Industrial Stamping 8

FaRo-PPF: Fast and Robust Point Pair Feature for 6D Pose Est...

引用

8th IEEE International Conference on Advanced robotics and Mechatronics, ICARM 2023

作者： He, Cheng Zhang, Xuebo Zhao, Zhenjie Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin300350 China School of Computer Science Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (纸本)9798350300178

Estimating 6D poses of targets efficiently is critical for industrial stamping tasks, in which the Point Pair Feature (PPF) method has been widely used. Based on PPF, this paper proposes Fast and Robust PPF, i.e. FaRo-PPF, which improves PPF in the following three key aspects: adaptive down-sampling based on surface features, point pair matching based on voting ball, and normal-based pose verification. The three designs alleviate existing problems of the local matching stage in PPF, and make FaRo-PPF a stronger method of 6D pose estimation in industrial stamping. To demonstrate the effectiveness of FaRo-PPF, we compare it with PPF on five publically available datasets. Experiment results showed that FaRo-PPF is able to significantly improve accuracy by about 15% and reduce the execution time by about 40% across all test data. We further conduct a grasping and assembly experiment on a physical robot arm, and similar improvement can be observed. FaRo-PPF achieves a higher success rate of assembly and reduces the execution time by about 50%. © 2023 IEEE.

关键词： Stamping

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：