检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Fu, Jiyuan Chen, Zhaoyu Jiang, Kaixun Guo, Haijing Wang, Jiafeng Gao, Shuyong Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models, resulting in a substantial performance gap from white-box attacks. We observe that prior work overlooks the interaction mechanisms between modalities, which plays a crucial role in understanding the intricacies of VLP models. In response, we propose a novel attack, called Collaborative Multimodal Interaction Attack (CMI-Attack), leveraging modality interaction through embedding guidance and interaction enhancement. Specifically, attacking text at the embedding level while preserving semantics, as well as utilizing interaction image gradients to enhance constraints on perturbations of texts and images. Significantly, in the image-text retrieval task on Flickr30K dataset, CMI-Attack raises the transfer success rates from ALBEF to TCL, CLIPViT and CLIPCNN by 8.11%-16.75% over state-of-the-art methods. Moreover, CMI-Attack also demonstrates superior performance in cross-task generalization scenarios. Our work addresses the underexplored realm of transfer attacks on VLP models, shedding light on the importance of modality interaction for enhanced adversarial robustness. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation

ADAPT: Efficient Multi-Agent Trajectory Prediction with Adap...

引用

International Conference on computer Vision (ICCV)

作者： Görkay Aydemir Adil Kaan Akan Fatma Güney KUIS AI Center Department of Computer Engineering Koç University

Forecasting future trajectories of agents in complex traffic scenes requires reliable and efficient predictions for all agents in the scene. However, existing methods for trajectory prediction are either inefficient or sacrifice accuracy. To address this challenge, we propose ADAPT, a novel approach for jointly predicting the trajectories of all agents in the scene with dynamic weight learning. Our approach outperforms state-of-the-art methods in both single-agent and multi-agent settings on the Argoverse and Interaction datasets, with a fraction of their computational overhead. We attribute the improvement in our performance: first, to the adaptive head augmenting the model capacity without increasing the model size; second, to our design choices in the endpoint-conditioned prediction, reinforced by gradient stopping. Our analyses show that ADAPT can focus on each agent with adaptive prediction, allowing for accurate predictions efficiently. https://***/adapt

关键词：

来源：评论

学校读者我要写书评

暂无评论

P3S-Diffusion:A Selective Subject-driven Generation Framework via Point Supervision

arXiv

引用

arXiv 2024年

作者： Hu, Junjie Gao, Shuyong Hong, Lingyi Wang, Qishan Zhao, Yuzhou Wang, Yan Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

Recent research in subject-driven generation increasingly emphasizes the importance of selective subject features. Nevertheless, accurately selecting the content in a given reference image still poses challenges, especially when selecting the similar subjects in an image (e.g., two different dogs). Some methods attempt to use text prompts or pixel masks to isolate specific elements. However, text prompts often fall short in precisely describing specific content, and pixel masks are often expensive. To address this, we introduce P3S-Diffusion, a novel architecture designed for context-selected subject-driven generation via point supervision. P3S-Diffusion leverages minimal cost label (e.g., points) to generate subject-driven images. During fine-tuning, it can generate an expanded base mask from these points, obviating the need for additional segmentation models. The mask is employed for inpainting and aligning with subject representation. The P3S-Diffusion preserves fine features of the subjects through Multi-layers Condition Injection. Enhanced by the Attention Consistency Loss for improved training, extensive experiments demonstrate its excellent feature preservation and image generation capabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Network security, trust & privacy in a wiredwireless Environments–An Overview

Network security, trust & privacy in a wiredwireless Environ...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Shruti Bhatla Devendra Gautam Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Mersin Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Nicosia Mersin Turkey Research Center for AI and IoT Faculty of Engineering University of Kyrenia Kyrenia Mersin Turkey Department of Computer Science and Engineering Graphic Era Hill University Dehradun ABES Engineering College Ghaziabad

In this report, we explore the key challenges and threats facing network security in wired and wireless environments, as well as the technologies and best practices for addressing these challenges. We provide an overview of the key concepts and terminology related to network security, trust, and privacy, and discuss the role of encryption in maintaining trust and privacy in these environments. We also examine common attack vectors and countermeasures and offer some recommendations for best practices in the realm of network security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-Autonomous Interaction Framework for Contact-Based Operations with Commercial UAVs IN GNSS-Denied Environments

Semi-Autonomous Interaction Framework for Contact-Based Oper...

引用

International Conference on Unmanned aircraft Systems (ICUAS)

作者： A. González-Morgado Q. Zhang G. Damigos E. Cuniato T. Hui E. Sahin G. Nikolakopoulos R. Siegwart M. Fumagalli A. Ollero G. Heredia GRVC Robotics Labs University of Seville Spain 3D Media Group Tampere University Finland Department of Computer Electrical and Space Ericsson Research and the Robotics and AI Group Autonomous Systems Lab (ASL) at ETH Zurich Switzerland Department of Electrical and Photonics Engineering Technical University of Denmark Denmark Department of Computer Electrical and Space Robotics and AI Group

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

Unmanned aerial vehicles (UAVs) are being increasingly established for autonomous contacted-based inspection of industrial assets, reducing the risk of errors by human operators. However, challenges remain in the navigation under unreliable Global Navigation Satellite System (GNSS) signals, or in the detection and interaction with the inspection surface, which limits the autonomy level of current UAV industrial technologies. This paper presents a semi-autonomous framework which combines automated target detection and interaction in GNSS-denied environments, with supervision commands by a human operator, to increase both safety and reliability. Our framework is composed of: (i) a camera-based onboard odometry solution for positioning the UAV in GNSSdenied conditions, (ii) a target-detection and filtering algorithm which estimates the orientation and position of the interaction target and (iii) a visual servoing strategy for approaching and contacting the target. The proposed framework is developed completely in ROS, and can be used with any commercial UAV. The framework is validated through outdoor flights, where a UAV detects and contacts a target on a vertical pipe.

关键词： Vibrations Global navigation satellite system Three-dimensional displays Switches Inspection Autonomous aerial vehicles Visual servoing Safety Odometry Reliability

来源：评论

学校读者我要写书评

暂无评论

General Compression Framework for Efficient Transformer Object Tracking

arXiv

引用

arXiv 2024年

作者： Hong, Lingyi Li, Jinglun Zhou, Xinyu Yan, Shilin Guo, Pinxue Jiang, Kaixun Chen, Zhaoyu Gao, Shuyong Zhang, Wei Lu, Hong Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China

Transformer-based trackers have established a dominant role in the field of visual object tracking. While these trackers exhibit promising performance, their deployment on resource-constrained devices remains challenging due to inefficiencies. To improve the inference efficiency and reduce the computation cost, prior approaches have aimed to either design lightweight trackers or distill knowledge from larger teacher models into more compact student trackers. However, these solutions often sacrifice accuracy for speed. Thus, we propose a general model compression framework for efficient transformer object tracking, named CompressTracker, to reduce the size of a pre-trained tracking model into a lightweight tracker with minimal performance degradation. Our approach features a novel stage division strategy that segments the transformer layers of the teacher model into distinct stages, enabling the student model to emulate each corresponding teacher stage more effectively. Additionally, we also design a unique replacement training technique that involves randomly substituting specific stages in the student model with those from the teacher model, as opposed to training the student model in isolation. Replacement training enhances the student model’s ability to replicate the teacher model’s behavior. To further forcing student model to emulate teacher model, we incorporate prediction guidance and stage-wise feature mimicking to provide additional supervision during the teacher model’s compression process. Our framework CompressTracker is structurally agnostic, making it compatible with any transformer architecture. We conduct a series of experiment to verify the effectiveness and generalizability of CompressTracker. Our CompressTracker-4 with 4 transformer layers, which is compressed from OSTrack, retains about 96% performance on LaSOT (66.1% AUC) while achieves 2.17× speed up. © 2024, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Fog enabling technologies in healthcare: A review

Fog enabling technologies in healthcare: A review

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Yadav, Aditya Pradhan, Onesimus Chandra Khanam, Ruqaiya Amrita Computer Science and Engineering Sharda School of Engineering and Technology Sharda University U.P Greater Noida India Department of EECE Center for AI in Medicine Imaging and Forensic Sharda University U.P Greater Noida India Center for Cyber Security and Cryptology Computer Science and Engineering Sharda School of Engineering and Technology Sharda University U.P Greater Noida India

ISBN: (纸本)9781032669663

This paper provides an overview of fog computing healthcare technologies that are playing a huge role in the current healthcare Industry. In this paper, we suggest the Data mining is the most effective option for disease prediction. The suggested framework intends to support health care based on disease symptoms, and health-related data. Gathering and analyzing activity-specific data that may be utilized to gauge the health benefits of exercise and its intensity as well as provide suggestions. Health Informatics makes extensive use of wireless sensor networks (WSNs). Patients at risk for chronic illnesses are increasingly being monitored via wireless and wearable sensors. This ensures that patients follow their treatment schedules and protects them from unexpected assaults. Along with its abilities, the fog computing framework also brings over from the cloud computing platform a number of security flaws that must be solved for the benefit of the user. Fog computing is crucial because it aids in the system’s elimination of latency problems, which are crucial in the healthcare sector. © 2024 The Author(s).

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

iDrone: IoT-Enabled Unmanned Aerial Vehicles for Detecting Wildfires Using Convolutional Neural Networks

引用

SN computer Science 2022年第3期3卷 1-13页

作者： Sethuraman, Sibi Chakkaravarthy Tadkapally, Gaurav Reddy Mohanty, Saraju P. Subramanian, Anitha School of Computer Science and Engineering and Center of Excellence in Artificial Intelligence and Robotics (AIR) VIT-AP University Amaravati India Department of Computer Science and Engineering University of North Texas Denton 76207 TX United States School of Electronics Engineering and Center of Excellence in Artificial Intelligence and Robotics (AIR) VIT-AP University Amaravati India

The rise of global temperatures, over the past few decades, has disrupted the usual balance of nature. As a result of increasing temperatures, wildfires have destroyed millions of acres of land, thousands of structures, and homes. The pollution and toxic gases produced by the wildfires are carried out to thousands of miles, thus threatening the lives all around the world. Most wildfires occur due to anthropogenic factors, which cannot be predicted solely based on climate conditions. Henceforth, to detect wildfires before escalating, we propose iDrone, which is a wildfire detection system equipped with an end-to-end CNN image classification model: XtinguishNet, trained on a wildfire imagery dataset to detect the possible flames or smokes in an image. In addition, our approach also acquires the weather data and the intensity of the fire. Contrasting with existing wildfire detection systems, our proposed solution is a fusion of the Internet of Things (IoT) and Deep Learning, aiming to provide a one-stop solution for all the needs required to minimize the damage caused by wildfires. When validated and tested using various benchmark datasets, video surveillance, iDrone acquired a high accuracy of 98.36% with the least computational power. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： CNN computer vision Deep learning Forest fires iDrone Wildfires

来源：评论

学校读者我要写书评

暂无评论

From Efficient Multimodal Models to World Models: A Survey

arXiv

引用

arXiv 2024年

作者： Mai, Xinji Tao, Zeng Lin, Junxiong Wang, Haoran Chang, Yang Kang, Yanlan Wang, Yan Zhang, Wenqiang Shanghai Engineering Research Center of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Academy for Engineering and Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Multimodal Large Models (MLMs) are becoming a significant research focus, combining powerful large language models with multimodal learning to perform complex tasks across different data modalities. This review explores the latest developments and challenges in MLMs, emphasizing their potential in achieving artificial general intelligence and as a pathway to world models. We provide an overview of key techniques such as Multimodal Chain of Thought (M-COT), Multimodal Instruction Tuning (M-IT), and Multimodal In-Context Learning (M-ICL). Additionally, we discuss both the fundamental and specific technologies of multimodal models, highlighting their applications, input/output modalities, and design characteristics. Despite significant advancements, the development of a unified multimodal model remains elusive. We discuss the integration of 3D generation and embodied intelligence to enhance world simulation capabilities and propose incorporating external rule systems for improved reasoning and decision-making. Finally, we outline future research directions to address these challenges and advance the field. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Irregular Change Detection in Sparse Bi-Temporal Point Clouds Using Learned Place Recognition Descriptors and Point-to-Voxel Comparison

Irregular Change Detection in Sparse Bi-Temporal Point Cloud...

引用

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

作者： Nikolaos Stathoulopoulos Anton Koval George Nikolakopoulos Department of Computer Electrical and Space Engineering Robotics and AI Group Luleå University of Technology Luleå Sweden

Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments. This article proposes an innovative approach for change detection in 3D point clouds using deep learned place recognition descriptors and irregular object extraction based on voxel-to-point comparison. The proposed method first aligns the bi-temporal point clouds using a map-merging algorithm in order to establish a common coordinate frame. Then, it utilizes deep learning techniques to extract robust and discriminative features from the 3D point cloud scans, which are used to detect changes between consecutive point cloud frames and therefore find the changed areas. Finally, the altered areas are sampled and compared between the two time instances to extract any obstructions that caused the area to change. The proposed method was successfully evaluated in real-world field experiments, where it was able to detect different types of changes in 3D point clouds, such as object or muck-pile addition and displacement, showcasing the effectiveness of the approach. The results of this study demonstrate important implications for various applications, including safety and security monitoring in construction sites, mapping and exploration and suggests potential future research directions in this field.

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：