检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Lin, Zheyuan Ji, Shanshan Wang, Wen Qin, Mengjie Yang, Rong Wan, Minhong Gu, Jason Li, Te Zhang, Chunlong Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Research Center for Intelligent Robotics Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Dalhousie University Department of Electrical and Computer Engineering HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9798350325706

The application of robots in social life, equipped with sensors and actuators and embedded with AI, assists people in all aspects. However, the first perspective of the robot horizon is heavily constrained, which weakens its performance. A joint tracking system is designed and built to deal with this, by integrating a surveillance system with the robot visual, providing a third perspective. This system takes one horizontal view and two top views from various directions as inputs and matches a person among the frames and in time sequence. In order to deal with the identity match with a huge visual feature gap, a special dataset is collected, simultaneously labeling identities from a mobile robot perspective and multiple indoor static surveillance monitors. The experiment shows that such match is a task worth exploring that can be better handled by training on our dataset than existing open source Re-identification (Re-id) datasets. Moreover, in the real scenario, this system improves the performance on issues like in and out of the robot's field of vision and heavy occlusion by people or objects. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Point Octree Encoding Network for Point Cloud Based Place Recognition

Multi-Scale Point Octree Encoding Network for Point Cloud Ba...

引用

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

作者： Zhilong Tang Hanjing Ye Hong Zhang Department of Electrical and Electronic Engineering Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology (SUSTech) SUSTech Shenzhen China

Over the past decades, point cloud-based place recognition has garnered significant attention. This research paper presents a pioneering approach, denoted as the Multi-scale Point Octree Encoding Network (MPOE-Net), designed to acquire a discriminative global descriptor for efficient retrieval of places. The key element of the MPOE-Net is the point octree encoding module, which adeptly captures local information for each point by considering its nearest and farthest neighbors. Further enhancing local relationships, a multi-transformer network is introduced, utilizing a novel grouped offset-attention mechanism. To amalgamate the multi-scale attention maps into a comprehensive global descriptor, a multi-NetVLAD layer is incorporated. Through rigorous experimentation across diverse benchmark datasets, our proposed method unequivocally outperforms existing techniques in the realm of point cloud-based place recognition tasks, achieving state-of-the-art results. Our code is released publicly at https://***/Zhilong-Tang/MPOE-Net.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

Unsupervised Video Domain Adaptation with Masked Pre-Trainin...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Arun Reddy William Paul Corban Rivera Ketul Shah Celso M. de Melo Rama Chellappa Johns Hopkins University Applied Physics Laboratory Department of Electrical & Computer Engineering Johns Hopkins University DEVCOM U.S. Army Research Laboratory

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first employs self-supervised pretraining to promote discriminative feature learning on target domain videos using a teacher-guided masked distillation objective. We then perform self-training on masked target data, using the video student model and image teacher model together to generate improved pseudolabels for unlabeled target videos. Our self-training process successfully leverages the strengths of both models to achieve strong transfer performance across domains. We evaluate our approach on multiple video domain adaptation benchmarks and observe significant improvements upon previously reported results.

关键词： Representation learning Adaptation models computer vision Computational modeling Collaboration Benchmark testing Data models

来源：评论

学校读者我要写书评

暂无评论

HPPS: A Hierarchical Progressive Perception System for Luggage Trolley Detection and Localization at Airports

arXiv

引用

arXiv 2024年

作者： Sun, Zhirui Zhang, Zhe Zhao, Jieting Ye, Hanjing Wang, Jiankun Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Jiaxing Research Institute Southern University of Science and Technology Jiaxing China Shenzhen Key Laboratory of Robotics and Computer Vision Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

The robotic autonomous luggage trolley collection system employs robots to gather and transport scattered luggage trolleys at airports. However, existing methods for detecting and locating these luggage trolleys often fail when they are not fully visible. To address this, we introduce the Hierarchical Progressive Perception System (HPPS), which enhances the detection and localization of luggage trolleys under partial occlusion. The HPPS processes the luggage trolley’s position (x, y) and orientation (θ) separately, which requires only RGB images for labeling and training, eliminating the need for 3D coordinates and alignment. The HPPS can accurately determine the position of the luggage trolley with just one well-detected keypoint and estimate the luggage trolley’s orientation when it is partially occluded. Once the luggage trolley’s initial pose is detected, HPPS updates this information continuously to refine its accuracy until the robot begins grasping. The experiments on detection and localization demonstrate that HPPS is more reliable under partial occlusion compared to existing methods. Its effectiveness and robustness have also been confirmed through practical tests in actual luggage trolley collection tasks. A website about this work is available at HPPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

GEM: Context-Aware Gaze EstiMation with Visual Search Behavior Matching for Chest Radiograph

arXiv

引用

arXiv 2024年

作者： Liu, Shaonan Chen, Wenting Liu, Jie Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China Department of Electrical Engineering City University of Hong Kong Hong Kong AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Gaze estimation is pivotal in human scene comprehension tasks, particularly in medical diagnostic analysis. Eye-tracking technology facilitates the recording of physicians’ ocular movements during image interpretation, thereby elucidating their visual attention patterns and information-processing strategies. In this paper, we initially define the context-aware gaze estimation problem in medical radiology report settings. To understand the attention allocation and cognitive behavior of radiologists during the medical image interpretation process, we propose a context-aware Gaze EstiMation (GEM) network that utilizes eye gaze data collected from radiologists to simulate their visual search behavior patterns throughout the image interpretation process. It consists of a context-awareness module, visual behavior graph construction, and visual behavior matching. Within the context-awareness module, we achieve intricate multimodal registration by establishing connections between medical reports and images. Subsequently, for a more accurate simulation of genuine visual search behavior patterns, we introduce a visual behavior graph structure, capturing such behavior through high-order relationships (edges) between gaze points (nodes). To maintain the authenticity of visual behavior, we devise a visual behavior-matching approach, adjusting the high-order relationships between them by matching the graph constructed from real and estimated gaze points. Extensive experiments on four publicly available datasets demonstrate the superiority of GEM over existing methods and its strong generalizability, which also provides a new direction for the effective utilization of diverse modalities in medical image interpretation and enhances the interpretability of models in the field of medical imaging. https://***/Tiger-SN/GEM. Copyright © 2024, The Authors. All rights reserved.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Privacy-protected object detection through trustworthy image fusion

Privacy-protected object detection through trustworthy image...

引用

作者： Zhang, Chao Zhang, Jinmei Yun, Lijun Zhang, Jun Su, Junbo Yunnan Key Laboratory of Optoelectronic Information Technology Yunnan Normal University Kunming China School of Physics and Electronic Information Yunnan Normal University Kunming China Engineering Research Center of Computer Vision and Intelligent Control Technology Department of Education of Yunnan Province Yunnan Normal University Kunming China Kunming Institute of Physics Ordnance Science and Research Academy of China Kunming China

The neural network-based technologies have emerged as a potent method for image fusion, object detection, and other computer vision tasks as the rapid development of deep learning. Multi-band infrared images, in particular, capture a more extensive range of radiation details and information compared to conventional single-band infrared images. Consequently, the fusion of multi-band infrared images can provide more features for object detection. However, it is crucial to consider that infrared images may contain sensitive information, potentially leading to privacy concerns. Ensuring datasets privacy protection plays a crucial role in the fusion and tracking process. To address both the need for improved detection performance and the necessity for privacy protection in the infrared environment, we proposed a procedure for object detection based on multi-band infrared image datasets and utilized the transfer learning technique to migrate knowledge learned from external infrared data to internal infrared data, thereby training the infrared image fusion model and detection model. The procedure consists of several steps: (1) data preprocessing of multi-band infrared images, (2) multi-band infrared image fusion, and (3) object detection. Standard evaluation metrics for image fusion and object detection ensure the authenticity of the experiments. The comprehensive validation experiments demonstrate the effectiveness of the proposed procedure in object detection tasks. Furthermore, the transfer learning can train our datasets and update the model without exposing the original data. This aspect of transfer learning is particularly beneficial for maintaining the privacy of multi-band infrared images during the fusion and detection processes. © 2024 John Wiley & Sons Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Mini-InternVL: a flexible-transfer pocket multi-modal model with 5% parameters and 90% performance

引用

Visual Intelligence 2024年第1期2卷 1-17页

作者： Gao, Zhangwei Chen, Zhe Cui, Erfei Ren, Yiming Wang, Weiyun Zhu, Jinguo Tian, Hao Ye, Shenglong He, Junjun Zhu, Xizhou Lu, Lewei Lu, Tong Qiao, Yu Dai, Jifeng Wang, Wenhai Shanghai AI Laboratory Shanghai 200232 China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Computer Science Nanjing University Nanjing 210023 China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen 518055 China School of Computer Science Fudan University Shanghai 200433 China SenseTime Research Shanghai 200233 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Beijing National Research Center for Information Science and Technology Department of Automation Tsinghua University Beijing 100084 China Department of Information Engineering The Chinese University of Hong Kong 999077 Hong Kong

Multi-modal large language models (MLLMs) have demonstrated impressive performance in vision-language tasks across a wide range of domains. However, the large model scale and associated high computational cost pose significant challenges for training and deploying MLLMs on consumer-grade GPUs or edge devices, thereby hindering their widespread application. In this work, we introduce Mini-InternVL, a series of MLLMs with parameters ranging from 1 billion to 4 billion, which achieves 90% of the performance with only 5% of the parameters. This significant improvement in efficiency and effectiveness makes our models more accessible and applicable in various real-world scenarios. To further promote the adoption of our models, we are developing a unified adaptation framework for Mini-InternVL, which enables our models to transfer and outperform specialized models in downstream tasks, including autonomous driving, medical image processing, and remote sensing. We believe that our models can provide valuable insights and resources to advance the development of efficient and effective MLLMs. © The Author(s) 2024.

关键词： Knowledge distillation Lightweight multi-modal large language model vision-language model Visual instruction tuning

来源：评论

学校读者我要写书评

暂无评论

Autonomous Patrol and Threat Detection Through Integrated Mapping and computer vision

Autonomous Patrol and Threat Detection Through Integrated Ma...

引用

IEEE International Conference on Electro-Information Technology

作者： Robert Soler Alae Moudni Gabriel Roskowski Xinrui Yu Mikhail Gormov Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing (ECASP) Research Laboratory Illinois Institute of Technology Chicago IL U.S.A.

ISBN: (数字)9798350330649

ISBN: (纸本)9798350330656

This paper presents the creation of an innovative autonomous security robot designed to perform security functions with efficiency and reliability. The robot boasts mapping capabilities, which it utilizes to facilitate autonomous patrol in designated areas. Its primary operations involve the use of computer vision to detect violence, identify weapons and dangerous items, and recognize individuals. Critical incidents are met with an immediate alarm and the subsequent transmission of data to a central security server, which then generates comprehensive reports displayed through a web application for security personnel. The application itself features remote control of the robot, incident report management, status updates, and incident analytics. The robot demonstrates substantial real-world application potential, particularly in crowded environments where it could outperform conventional surveillance. The project combines concepts of engineering, computer science, and cybersecurity, functioning per design but with considerable potential for future refinement and expansion, embodying the concept of an evolving technological solution.

关键词： computer science computer vision Technological innovation Surveillance Weapons Reliability engineering Threat assessment

来源：评论

学校读者我要写书评

暂无评论

Diagnostic Accuracy and Reliability of Deep Learning-Based Human Papillomavirus Status Prediction in Oropharyngeal Cancer

Diagnostic Accuracy and Reliability of Deep Learning-Based H...

引用

International Conference on Medical Imaging and computer-Aided Diagnosis, MICAD 2022

作者： La Greca Saint-Esteven, Agustina Marchiori, Chiara Bogowicz, Marta Barranco-García, Javier Khodabakhshi, Zahra Konukoglu, Ender Riesterer, Oliver Balermpas, Panagiotis Hüllner, Martin Malossi, A. Cristiano I. Guckenberger, Matthias van Timmeren, Janita E. Tanadini-Lang, Stephanie Department of Radiation Oncology University Hospital Zurich and the University of Zurich Rämistrasse 100 Zurich8091 Switzerland Computer Vision Laboratory Department of Information Technology and Electrical Engineering ETH Zurich Sternwartstrasse 7 Zurich8092 Switzerland IBM Research Zurich Säumerstrasse 4 Rüschlikon8803 Switzerland Department of Nuclear Medicine University Hospital Zurich and the University of Zurich Rämistrasse 100 Zurich8091 Switzerland

ISBN: (纸本)9789811667749

Oropharyngeal cancer (OPC) patients with associated human papillomavirus (HPV) infection generally present more favorable outcomes than HPV-negative patients and, consequently, their treatment with radiation therapy may be potentially de-escalated. The diagnostic accuracy of a deep learning (DL) model to predict HPV status on computed tomography (CT) images was evaluated in this study, together with its ability to perform unsupervised heatmap-based localization of relevant regions in OPC and HPV infection, i.e., the primary tumor and lymph nodes, as a measure of its reliability. The dataset consisted of 767 patients from one internal and two public collections from The Cancer Imaging Archive and was split into training, validation and test sets using the ratio 60–20–20. Images were resampled to a resolution of 2 mm3 and a sub-volume of 96 pixels3 was automatically cropped, which spanned from the nose until the start of the lungs. Models Genesis was fine-tuned for the classification task. Grad-CAM and Score-CAM were applied to the test subjects that belonged to the internal cohort (n = 24), and the overlap and Dice coefficients between the resulting heatmaps and the planning target volumes (PTVs) were calculated. Final train/validation/test area-under-the-curve (AUC) values of 0.9/0.87/0.87, accuracies of 0.83/0.82/0.79, and F1-scores of 0.83/0.79/0.74 were achieved. The reliability analysis showed an increased focus on dental artifacts in HPV-positive patients, whereas promising overlaps and moderate Dice coefficients with the PTVs were obtained for HPV-negative cases. These findings prove the necessity of performing reliability studies before a DL model is implemented in a real clinical setting, even if there is optimal diagnostic accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Synthetic Thermal and RGB Videos for Automatic Pain Assessment Utilizing a vision-MLP Architecture

Synthetic Thermal and RGB Videos for Automatic Pain Assessme...

引用

International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)

作者： Stefanos Gkikas Manolis Tsiknakis Department of Electrical & Computer Engineering Hellenic Mediterranean University Heraklion Greece Affiliated Researcher at the Computational Biomedicine Laboratory of the Foundation for Research and Technology (FORTH) Heraklion Greece

ISBN: (数字)9798331516451

ISBN: (纸本)9798331516468

Pain assessment is essential in developing optimal pain management protocols to alleviate suffering and prevent functional decline in patients. Consequently, reliable and accurate automatic pain assessment systems are essential for continuous and effective patient monitoring. This study presents synthetic thermal videos generated by Generative Adversarial Networks integrated into the pain recognition pipeline and evaluates their efficacy. A framework consisting of a vision-MLP and a Transformer-based module is utilized, employing RGB and synthetic thermal videos in unimodal and multimodal settings. Experiments conducted on facial videos from the BioVid database demonstrate the effectiveness of synthetic thermal videos and underline the potential advantages of it.

关键词： Temperature Protocols Pain Infrared imaging Transformer cores Transformers Generative adversarial networks Thermal conductivity Reliability Videos

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：