检索结果-内蒙古大学图书馆

Reinforcement learning of non-additive joint steganographic embedding costs with attention mechanism

science China(Information sciences) 2023年第3期66卷 273-286页

作者： Weixuan TANG Bin LI Weixiang LI Yuangen WANG Jiwu HUANG Institute of Artificial Intelligence and Blockchain Guangzhou University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science and Cyber Engineering Guangzhou University

Image steganography is the art and science of secure communication by concealing information within digital images. In recent years, the techniques of steganographic cost learning have developed rapidly. Although the existing methods can learn satisfactory additive costs, the interplay of different pixels' embedding impacts has not been considered, so the potential of learning may not be fully exploited. To overcome this limitation, in this paper, a reinforcement learning paradigm called Jo Po L(joint policy learning) is proposed to extend the idea of additive cost learning to a non-additive situation. Jo Po L aims to capture the interactions within pixel blocks by defining embedding policies and evaluating contributions of embedding impacts on a block level rather than a pixel level. Then, a policy network is utilized to learn optimal joint embedding policies for pixel blocks through interactions with the environment. Afterwards,these policies can be converted into joint embedding costs for practical message embedding. The structure of the policy network is designed with an effective attention mechanism and incorporated with the domain knowledge derived from traditional non-additive steganographic methods. The environment is responsible for assigning rewards according to the impacts of the sampled joint embedding actions, which are evaluated by the gradient information of a neural network-based steganalyzer. Experimental results show that the proposed non-additive method Jo Po L significantly outperforms the existing additive methods against both feature-based and CNN-based steganalzyers over different payloads.

关键词： information hiding non-additive steganography steganalysis cost learning image processing

来源：评论

学校读者我要写书评

暂无评论

X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation 24

X-Prompt: Multi-modal Visual Prompt for Video Object Segment...

引用

32nd ACM International Conference on Multimedia, MM 2024

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

ISBN: (纸本)9798400706868

Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and RGB-Event, has garnered attention due to its capability to address challenging scenarios where traditional VOS methods struggle, such as extreme illumination, rapid motion, and background distraction. Existing approaches often involve designing specific additional branches and performing full-parameter fine-tuning for fusion in each task. However, this paradigm not only duplicates research efforts and hardware costs but also risks model collapse with the limited multi-modal annotated data. In this paper, we propose a universal framework named X-Prompt for all multi-modal video object segmentation tasks, designated as RGB+X. The X-Prompt framework first pre-trains a video object segmentation foundation model using RGB data, and then utilize the additional modality of the prompt to adapt it to downstream multi-modal tasks with limited data. Within the X-Prompt framework, we introduce the Multi-modal Visual Prompter (MVP), which allows prompting foundation model with the various modalities to segment objects precisely. We further propose the Multi-modal Adaptation Experts (MAEs) to adapt the foundation model with pluggable modality-specific knowledge without compromising the generalization capacity. To evaluate the effectiveness of the X-Prompt framework, we conduct extensive experiments on 3 tasks across 4 benchmarks. The proposed universal X-Prompt framework consistently outperforms the full fine-tuning paradigm and achieves state-of-the-art performance. Code: https://***/PinxueGuo/*** © 2024 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Multi-DNN Inference 30

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Mul...

引用

30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2024

作者： Kang, Woosung Lee, Jinkyu Lee, Youngmoon Oh, Sangeun Lee, Kilho Chwa, Hoon Sung DGIST Dept. of Electrical Engineering and Computer Science Korea Republic of Dept. of Computer Science and Engineering Korea Republic of Hanyang University Dept. of Robotics Korea Republic of Ajou University Department of Software and Computer Engineering Korea Republic of School of AI Convergence Soongsil University Korea Republic of

ISBN: (纸本)9798350358414

The increasing complexity and memory demands of Deep Neural Networks (DNNs) for real-Time systems pose new significant challenges, one of which is the GPU memory capacity bottleneck, where the limited physical memory inside GPUs impedes the deployment of sophisticated DNN models. This paper presents, to the best of our knowledge, the first study of addressing the GPU memory bottleneck issues, while simultaneously ensuring the timely inference of multiple DNN tasks. We propose RT-Swap, a real-Time memory management framework, that enables transparent and efficient swap scheduling of memory objects, employing the relatively larger CPU memory to extend the available GPU memory capacity, without compromising timing guarantees. We have implemented RT-Swap on top of representative machine-learning frameworks, demonstrating its effectiveness in making significantly more DNN task sets schedulable at least 72% over existing approaches even when the task sets demand up to 96.2% more memory than the GPU's physical capacity. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust STL Control Synthesis under Maximal Disturbance Sets 63

Robust STL Control Synthesis under Maximal Disturbance Sets

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Verhagen, Joris Lindemann, Lars Tumova, Jana Kth Royal Institute of Technology Division of Robotics Perception and Learning School of Electrical Engineering and Computer Science Stockholm Sweden University of Southern California Thomas Lord Department of Computer Science Los AngelesCA United States

ISBN: (纸本)9798350316339

This work addresses maximally robust control synthesis under unknown disturbances. We consider a nonlinear system, subject to a Signal Temporal Logic (STL) specification and jointly synthesize the maximal possible disturbance bounds and the corresponding controllers that ensure the STL specification is satisfied under these bounds. Many works have considered STL satisfaction under given bounded disturbances yet, to the authors' best knowledge, this is the first work that aims to maximize the permissible disturbance set and find corresponding maximally robust controllers. We, therefore, introduce disturbance robustness as a model-based robustness metric for STL planning and control synthesis. We extend the notion of disturbance-robust semantics for STL, which is a property of a specification, dynamical system, and controller, and provide an algorithm for maximally robust controllers satisfying an STL specification using Hamilton-Jacobi reachability. We show its soundness and provide a simulation example with an Autonomous Underwater Vehicle (AUV). © 2024 IEEE.

关键词： Control system synthesis

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Machine Learning Classifiers for Sudden Cardiac Arrest Detection

引用

Journal of The Institution of Engineers (India): Series B 2022年 1-7页

作者： Banerjee, Prakash Bhattacherjee, Saptak Dasgupta, Kousik Sen, Shibaprasad Department of Electrical and Electronics Engineering University of Engineering and Management Kolkata India School of Mechatronics and Robotics Indian Institute of Engineering Science and Technology Shibpur Howrah India Department of Computer Science and Engineering Kalyani Government Engineering College Kalyani India Department of Computer Science and Engineering University of Engineering and Management Kolkata India

Sudden cardiac arrest (SCA) is a type of cardiovascular disease which attacks a person so promptly that it gives minimum time for hospitalization and may also lead to the patient death. In order to save the patient from death, rapid detection of SCA just after the onset of symptoms with a high accuracy is very critical. Although numerous approaches of SCA detection based on electrocardiogram have been carried out, there is still need of standard method for SCA detection with high precession and fast detection. Hence, the present work proposes the use of four machine learning classifiers for detection of SCA based on temporal features extracted from ECG. Performance analysis of the classifiers used in this study on 19 SCA and 20 normal, i.e., healthy subjects, yields classification accuracies of 97.4%, 94.8%, 97.4% and 97.4% for SVM, decision tree, Naïve Bayes and KNN, respectively. Experimental results thus obtained demonstrate the potential of the proposed method as a promising alternative for SCA detection. © 2022, The Institution of Engineers (India).

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model 24

MambaMOS: LiDAR-based 3D Moving Object Segmentation with Mot...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zeng, Kang Shi, Hao Lin, Jiacheng Li, Siyu Cheng, Jintao Wang, Kaiwei Li, Zhiyong Yang, Kailun College of Computer Science and Electronic Engineering Hunan University Changsha China College of Optical Science and Engineering Zhejiang University Hangzhou China School of Robotics Hunan University Changsha China School of Electronics and Information Engineering South China Normal University Foshan China

ISBN: (纸本)9798400706868

LiDAR-based Moving Object Segmentation (MOS) aims to locate and segment moving objects in point clouds of the current scan using motion information from previous scans. Despite the promising results achieved by previous MOS methods, several key issues, such as the weak coupling of temporal and spatial information, still need further study. In this paper, we propose a novel LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model, termed MambaMOS. Firstly, we develop a novel embedding module, the Time Clue Bootstrapping Embedding (TCBE), to enhance the coupling of temporal and spatial information in point clouds and alleviate the issue of overlooked temporal clues. Secondly, we introduce the Motion-aware State Space Model (MSSM) to endow the model with the capacity to understand the temporal correlations of the same object across different time steps. Specifically, MSSM emphasizes the motion states of the same object at different time steps through two distinct temporal modeling and correlation steps. We utilize an improved state space model to represent these motion differences, significantly modeling the motion states. Finally, extensive experiments on the SemanticKITTI-MOS and KITTI-Road benchmarks demonstrate that the proposed MambaMOS achieves state-of-the-art performance. The source code is publicly available at https://***/Terminal-K/MambaMOS © 2024 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Intelligent Small Scale Autonomous Vehicle Development Based on Convolutional Neural Network (CNN) for Steering Angle Prediction 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Asy’ari, Muhammad Zacky Phang, Maxson Suganda, Nicholas Mariana, Yosica Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Architecture Department Faculty of Engineering Binus University Jakarta Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Human error is the most significant factor in traffic accidents. 61% of accidents in Indonesia are caused by driver negligence. Autonomous vehicles are unmanned vehicles that are believed to be able to reduce the number of accidents caused by human error. This study aims to create a prototype of a small-scale unmanned vehicle using computer vision that can move around the track. The prototype captures an image using a USB webcam and is processed by a Raspberry Pi 4 to predict the correct steering angle based on input from the camera. A convolutional neural network (CNN) algorithm is used to recognize the path. The material used to make the prototype is PLA (polylactic acid). The prototype steering system uses a servo motor, and the drive system uses a brushless DC motor controlled by the PCA9685 module. More than 1600 image data were used and taken based on a simplified track. The results of this study indicate that the prototype can move along the given track with a steering angle range of 20°–130° for right turns and 60°–170° for left turns. The throttle value capable of moving the prototype at a steady speed is 0.075. The Keras Tensorflow model, dataset, and autonomous car design can achieve the desired level of autonomy with an RMSE accuracy of 0.1145. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Visual-Language Collaborative Representation Network for Broad-Domain Few-Shot Image Classification 24

Visual-Language Collaborative Representation Network for Bro...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Guo, Qianyu Ren, Jieji Wang, Haofen Wu, Tianxing Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China College of Design and Innovation Tongji University Shanghai China School of Computer Science and Engineering Southeast University Nanjing China 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

ISBN: (纸本)9798400706868

Visual-language models based on CLIP have shown remarkable abilities in general few-shot image classification. However, their performance drops in specialized fields such as healthcare or agriculture, because CLIP's pre-training does not cover all category data. Existing methods excessively depend on the multi-modal information representation and alignment capabilities acquired from CLIP pre-training, which hinders accurate generalization to unfamiliar domains. To address this issue, this paper introduces a novel visual-language collaborative representation network (MCRNet), aiming at acquiring a generalized capability for collaborative fusion and representation of multi-modal information. Specifically, MCRNet learns to generate relational matrices from an information fusion perspective to acquire aligned multi-modal features. This relationship generation strategy is category-agnostic, so it can be generalized to new domains. A class-adaptive fine-tuning inference technique is also introduced to help MCRNet efficiently learn alignment knowledge for new categories using limited data. Additionally, the paper establishes a new broad-domain few-shot image classification benchmark containing seven evaluation datasets from five domains. Comparative experiments demonstrate that MCRNet outperforms current state-of-the-art models, achieving an average improvement of 13.06% and 13.73% in the 1-shot and 5-shot settings, highlighting the superior performance and applicability of MCRNet across various domains. © 2024 ACM.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

The Effect of Viewpoint Change Strategies on Multi-View Video and Audio Transmission QoE Over ICN/CCN 38

The Effect of Viewpoint Change Strategies on Multi-View Vide...

引用

38th IEEE Region 10 Conference, TENCON 2023

作者： Nunome, Toshiro Takada, Yoshiyuki Computer Science Program Graduate School of Engineering Nagoya Institute of Technology Department of Engineering Nagoya466-8555 Japan

ISBN: (纸本)9798350302196

In this paper, we exploit caches on intermediate nodes for QoE enhancement of multi-view video and audio transmission over ICN/CCN by controlling the content request start timing of consumers. We assume the selected single viewpoint transmission method;a consumer receives video and audio streams of a requested viewpoint. We perform a simple experiment with two consumers. When the consumers play video and audio with the time difference, we assess the effect of cached content by the former consumer's request on the output quality of the latter consumer. We deal with two types of viewpoint change strategies for the former consumer, which affect the efficiency of cache utilization. From the assessment results, we see that cache utilization has an important factor in enhancing QoE. © 2023 IEEE.

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：