检索结果-内蒙古大学图书馆

ieee workshop on Applications of Computer vision (WACV)

作者： Yao Zhang Haokun Chen Ahmed Frikha Denis Krompass Gengyuan Zhang Jindong Gu Volker Tresp LMU Munich Germany Munich Center for Machine Learning (MCML) Germany Siemens AG Germany Torr Vision Group University of Oxford England

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Visual Question Answering (VQA) systems witnessed a significant advance in recent years due to the development of large-scale vision-Language Pre-trained Models (VLPMs). As the application scenario and user demand change over time, an advanced VQA system is expected to be capable of continuously expanding its knowledge and capabilities over time, not only to handle new tasks (i.e., new question types or visual scenes) but also to answer questions in new specialized domains without forgetting previously acquired knowledge and skills. Existing works studying CL on VQA tasks primarily consider answer-and question-type incremental learning or sceneand function-incremental learning, whereas how VQA systems perform when they encounter new domains and increasing user demands has not been studied. Motivated by this, we introduce CL-CrossVQA, a rigorous Continual Learning benchmark for Cross-domain Visual Question Answering, through which we conduct extensive experiments on 4 VLPMs, 5 CL approaches, and 5 VQA datasets from different domains. In addition, by probing the forgetting phenomenon of the intermediate layers, we provide insights into how model architecture affects CL performance, why CL approaches can help mitigate forgetting in VLPMs, and how to design CL approaches suitable for VLPMs in this challenging continual learning environment. To facilitate future work on developing an advanced All-in-One VQA system, we will release our datasets and code.

关键词： Continuing education visualization Computer vision Analytical models Incremental learning Codes Computer architecture Benchmark testing Question answering (information retrieval) Sparks

来源：评论

学校读者我要写书评

暂无评论

Flux Real-Time Imaging System: High-Speed, High-Throughput Automated Visual Inspection and Defect Detection for Monitoring Flux Dispense

Flux Real-Time Imaging System: High-Speed, High-Throughput A...

引用

ieee/SEMI Conference and workshop on Advanced Semiconductor Manufacturing

作者： Chris Edwards Robin Wilcox Darren Vance Meghana Swamy Nancy Xu Package and Test Automation Metrology Systems Analytics & Technology Automation Chandler Arizona Thermal Compression Bond Equipment Assembly & Test Technology Development Chandler Arizona

We present our new Flux Real-Time Imaging System which includes a new machine vision system, calibration utility, user interface, and inspection algorithm. The machine vision system was designed to optimize contrast between flux and no flux regions across various product types and fit within the compact footprint of the existing tool. The calibration utility provides a user interface that walks the user through the tool setup and matching procedure, enabling consistent inspection across tools. The user interface allows the user to create recipes and control the lighting and camera for tool setup as well as live inspection. An advanced machine learning algorithm was developed to identify good, partial flux, and no flux regions for units within the region of interest and alert the user in real-time if the flux deposition quality is not within the acceptable tolerances.

关键词： visualization machine vision Lighting Inspection User interfaces Throughput Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?

Can Multimodal Large Language Models Truly Perform Multimoda...

引用

ieee workshop on Applications of Computer vision (WACV)

作者： Shuo Chen Zhen Han Bailan He Jianzhe Liu Mark Buckley Yao Qin Philip Torr Volker Tresp Jindong Gu LMU Munich Siemens AG Technical University of Munich University of California Santa Barbara University of Oxford Munich Center for Machine Learning (MCML)

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Large Language Models (LLMs) with in-context learning (ICL) ability can quickly adapt to a specific context given a few demonstrations (demos). Recently, Multimodal Large Language Models (MLLMs) built upon LLMs have also shown multimodal ICL ability, i.e., responding to queries given a few multimodal demos, including images, queries, and answers. While ICL has been extensively studied on LLMs, its research on MLLMs remains limited. One essential question is whether these MLLMs can truly conduct multimodal ICL, or if only the textual modality is necessary. We investigate this question by examining two primary factors that influence ICL: 1) Demo content, i.e., understanding the influences of demo content in different modalities. 2) Demo selection strategy, i.e., how to select better multimodal demos for improved performance. Experiments revealed that multimodal ICL is predominantly driven by the textual content whereas the visual information in the demos has little influence. Interestingly, visual content is still necessary and useful for selecting demos to increase performance. Motivated by our analysis, we propose a simple yet effective approach, termed Mixed Modality In-Context Example Selection (MMICES), which considers both visual and language modalities when selecting demos. Extensive experiments are conducted to support our findings and verify the improvement brought by our method.

关键词： visualization Computer vision Large language models Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Potential of Artificial Intelligence in Plant Phenotyping and Disease Detection: A Survey

Unveiling the Potential of Artificial Intelligence in Plant ...

引用

Mechatronic Systems Supervision (IW_MSS), ieee International workshop on

作者： Boukouba Riheb Amira Guidara Chantal Ebel Smaoui Nadia Dalenda Benaissa Electrical Engineering Departement Research Laboratory in Electronics and Microwaves FST Tunis Tunisia ATMSTechnologies of medecine and Signals National Engineering School of Sfax Sfax Tunisia Plant Physiology and Functional Genomics Research Unit Higher Institute of Biotechnology Sfax Tunisia Control and Energy Management Laboratory National Engineering School of Sfax Sfax Tunisia Leti Research Laboratory of Electronics and Information Technologies National Engineering School of Sfax Sfax Tunisia

ISBN: (数字)9798350378382

ISBN: (纸本)9798350378399

In recent years, advanced plant phenotyping techniques have gained significant attention in the identification of plant diseases and the assessment of plant characteristics. These techniques involve machine vision, machine learning, and deep learning methods applied to non-invasive and non-destructive imaging. To accurately capture the plant's condition, efficient systems and equipment are required in the field of plant phenotyping. Unlike previous studies, which often focused on individual imaging methods; this work extensively investigates a wide range of imaging methods, such as visible imaging (RGB camera), multi or hyperspectral imaging, thermal imaging, chlorophyll fluorescence imaging (CFIM), hyperspectral imaging, and 3-dimensional imaging. This article provides an overview of these imaging techniques and their applications in plant phenotyping. The paper also presents a comprehensive survey of cutting- edge artificial intelligence for analyzing plant leaves or roots, including segmentation, trait estimation, and classification and using statistical analysis, machine learning, and deep learning algorithms Furthermore, it introduces an image pipeline that combines both analogical and numerical tools to detect visual plant traits and monitor environmental changes. This survey provides valuable insights into the advancements in imaging techniques for plant phenotyping and disease detection. It also encompasses all key aspects of machine learning, deep learning and statistical methods used in plant phenotyping including preprocessing, segmentation, feature extraction, classification and categorizing. Compared to earlier works, this survey provides a more exhaustive exploration of imaging techniques, combined with the latest advancements in AI-driven plant phenotyping, offering critical perspectives into both technological and practical developments in plant disease detection and phenotyping.

关键词： Surveys Deep learning Image segmentation Plant diseases visualization Statistical analysis Pipelines Imaging Object segmentation Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Codomain Transformation to Represent Abstract Information for machine Learning in Visual Scenes

Codomain Transformation to Represent Abstract Information fo...

引用

Applied Imagery Pattern Recognition workshop (AIPR)

作者： Andrew Kalukin Booz Allen Hamilton Alexandria VA

Convolutional Neural Networks (CNNs) succeed well in learning to recognize spatial and spectral image features which are easily distinguished by convolutional operations; for example, visual cues based on shape and color of isolated objects. However, they are challenged in learning features which are rule-based and abstract; for example, the number of elements in a scene (cardinality), and other relationships within a scene that have to do with subtle criteria of order and relative position, especially when essential cues occupy a small fraction of the spatial and spectral search space and can vary significantly in appearance. The computational experiment reported in this paper demonstrates the efficacy of codomain transformation to help CNNs recognize the abstract concept of cardinality for artificially generated geometric objects of various shapes, sizes, and colors.

关键词： visualization Computer vision Image recognition Shape Image color analysis Conferences machine learning

来源：评论

学校读者我要写书评

暂无评论

Fusion of Inertial Sensor Suit and Monocular Camera for 3D Human Pelvis Pose Estimation

Fusion of Inertial Sensor Suit and Monocular Camera for 3D H...

引用

ieee International workshop on Robot and Human Communication (ROMAN)

作者： Mihaela Popescu Kashmira Shinde Proneet Sharma Lisa Gutzeit Frank Kirchner Robotics Group Faculty of Mathematics and Computer Science University of Bremen Bremen Germany Robotics Innovation Center German Research Center for Artificial Intelligence (DFKI GmbH) Bremen Germany

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

In real-world scenarios, robots come closer to humans in many applications, sharing the same workspace or even manipulating the same objects. To ensure safe and intuitive collaboration, it is crucial to have an accurate knowledge of the human’s 3D position in space, which should be estimated with high precision, high frequency and low latency. However, individual sensors such as inertial measurement units (IMUs) or cameras cannot meet all requirements for reliable human pose estimation under conditions such as long operating times, large distances and occlusions. In this study, we highlight the limitations of different visual pose methods and present a fused approach for real-time estimation of the 3D position of the human pelvis using machine learning-based visual pose from a monocular camera and an IMU sensor suit. The multimodal fusion is based on the Invariant Extended Kalman filter (InEKF) on Lie Groups, which fuses drift-free visual poses with high-frequency inertial measurements in a loosely-coupled manner. The evaluation is performed on a recorded dataset of multiple subjects performing various experimental scenarios. The results show that the fused approach can increase the accuracy and robustness of the estimates, taking a step closer towards smooth human-robot collaboration.

关键词： visualization Three-dimensional displays Accuracy Pose estimation Robot vision systems Sensor fusion Cameras Real-time systems Pelvis Robots

来源：评论

学校读者我要写书评

暂无评论

Error Detection using Augmented Reality in the Subtractive Manufacturing Process 10

Error Detection using Augmented Reality in the Subtractive M...

引用

10th Annual Computing and Communication workshop and Conference (CCWC)

作者： Sreekanta, Meghashree Hulkood Sarode, Abhishek George, Kiran Calif State Univ Fullerton Comp Engn Fullerton CA 92831 USA Calif State Univ Fullerton Elect Engn Fullerton CA 92831 USA

ISBN: (纸本)9781728137834

A small error in subtractive manufacturing can adversely impact an entire production if not caught right away. By utilizing an Augmented Reality (AR) simulation, workers can view in real-time when the machine malfunctions, stop the process and correct it. AR will also improve the visualization of the object. This paper sets the initial stage for our future work in which the manufacturing defects can be detected in real-time. In this paper, error detection in dimensions was tested using OpenCV- Python and compared using a single web camera and intel real-sense D435i stereo camera, Augmenting AR block over the original block using Unity software in real-time, and operation of the switch to control the machine using AR was successfully tested.

关键词： Augmented Reality Intel Real-Sense D435i Camera OpenCV Computer vision Error Detection Unity Python Subtractive Manufacturing Error Detection

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Image and Video Inpainting and Denoising

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND machine INTELLIGENCE 2020年第5期42卷 1021-1024页

作者： Escalera, Sergio Escalante, Hugo Jair Baro, Xavier Guyon, Isabelle Madadi, Meysam Wan, Jun Ayache, Stephane Gucluturk, Yagmur Guclu, Umut Univ Barcelona E-08007 Barcelona Spain Comp Vis Ctr Barcelona 08007 Spain Inst Nacl Astrofis Opt & Eect Puebla Mexico CINVESTAV Zacatenco Comp Sci Dept Mexico City 07360 DF Mexico Univ Oberta Catalunya Barcelona 08018 Spain Comp Vis Ctr Barcelona 08018 Spain Univ Paris Saclay INRIA UPSud F-91190 Essonne France ChaLearn Berkeley CA USA Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Aix Marseille Univ Lab Informat & Syst F-13007 Marseille France Radboud Univ Nijmegen Donders Inst Brain Cognit & Behaviour NL-6525 XZ Nijmegen Netherlands

The papers in this special issue comprise all aspects of computer vision and pattern recognition devoted to image and video inpainting, including related tasks like denoising, debluring, sampling, super-resolutkon enhancement, restoration, hallucination, etc. The special issue was associated to the 2018 Chalearn Looking at People Satellite ECCV workshop1 and the 2018 ChaLearn Challenges on Image and Video Inpainting.

关键词： Special issues and sections Computer vision Pattern recognition visualization Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Performance of Single Board Computers for vision Processing

Performance of Single Board Computers for Vision Processing

引用

ieee Annual Computing and Communication workshop and Conference (CCWC)

作者： Curtis Manore Pratheek Manjunath Dominic Larkin United States Military Academy West Point New York

ISBN: (数字)9781665414906

ISBN: (纸本)9781665430586

With the increasing complexity of machine vision algorithms and growing applications of image processing, how do computers without a dedicated graphics processor perform? This research discusses the computational abilities of two low-cost single board computers (SBCs) by subjecting them to various Visual Inertial Odometry (VIO) algorithms. The end goal of this research is to identify a SBC which meets the requirements of being employed on an Unmanned Aerial System for autonomous navigation.

关键词： Computers visualization Architecture Random access memory Computer architecture Complexity theory Sensors

来源：评论

学校读者我要写书评

暂无评论

"All Right, Mr. DeMille, I'm Ready for My Closeup:" Adding Meaning to User Actions from Video for Immersive Analytics

"All Right, Mr. DeMille, I'm Ready for My Closeup:" Adding M...

引用

ieee workshop on machine Learning from User Interaction for visualization and Analytics (MLUI)

作者： Batch, Andrea Elmqvist, Niklas Univ Maryland Coll Informat Studies College Pk MD 20742 USA

ISBN: (纸本)9781665440646

While the use of machine learning and computer vision to classify human behavior has grown into a large, well-established, interdisciplinary area of research, one area that is somewhat overlooked is the intersection of computer vision as a tool for evaluating user behavior in Virtual Reality, particularly in the context of immersive analytics and visualization. We draw on the literature from pattern recognition, computer vision, and machine learning to compose a simple, comparatively resource-cheap pipeline for camera-based extraction of features of professional analyst users and of their sessions in an existing VR visualization system, ImAxes. Our results show high accuracy in predicting self-reported features of the users, even as survey responses about user experience with the immersive interface are somewhat ambiguous in varying based on these features.

关键词： visualization visual analytics ubiquitous analytics evaluation video analytics machine learning deep 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：