检索结果-内蒙古大学图书馆

TECMH:Transformer-Based Cross-Modal Hashing For Fine-Grained Image-Text Retrieval

computers, Materials & Continua 2023年第5期75卷 3713-3728页

作者： Qiqi Li Longfei Ma Zheng Jiang Mingyong Li Bo Jin College of Computer and Information Science Chongqing Normal UniversityChongqing401331China Institute of Systems and Robotics(ISR) Department of Electrical and Computer Engineering(DEEC)University of CoimbraCoimbraPortugal

In recent years,cross-modal hash retrieval has become a popular research field because of its advantages of high efficiency and low ***-modal retrieval technology can be applied to search engines,crossmodalmedical processing,*** existing main method is to use amulti-label matching paradigm to finish the retrieval ***,such methods do not use fine-grained information in the multi-modal data,which may lead to suboptimal *** avoid cross-modal matching turning into label matching,this paper proposes an end-to-end fine-grained cross-modal hash retrieval method,which can focus more on the fine-grained semantic information of multi-modal ***,the method refines the image features and no longer uses multiple labels to represent text features but uses BERT for ***,this method uses the inference capabilities of the transformer encoder to generate global fine-grained ***,in order to better judge the effect of the fine-grained model,this paper uses the datasets in the image text matching field instead of the traditional label-matching *** article experiment on Microsoft COCO(MS-COCO)and Flickr30K datasets and compare it with the previous *** experimental results show that this method can obtain more advanced results in the cross-modal hash retrieval field.

关键词： Deep learning cross-modal retrieval hash learning transformer

来源：评论

学校读者我要写书评

暂无评论

Exploring Children’s Strategies in Response to Robot’s Advice During a Group Task with iCub and Nao 16th

Exploring Children’s Strategies in Response to Robot’s A...

引用

16th International Conference on Social robotics, ICSR + AI 2024

作者： Pusceddu, Giulia Sangineto, Mariapia Cocchella, Francesca Bogliolo, Michela Belgiovine, Giulia Lastrico, Linda Casadio, Maura Rea, Francesco Gena, Cristina Sciutti, Alessandra Robotics Brain and Cognitive Science Department Italian Institute of Technology Genoa Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy Department of Computer Science University of Turin Turin Italy Cognitive Architecture for Collaborative Technologies Unit Italian Institute of Technology Genoa Italy Scuola di Robotica Genoa Italy

ISBN: (纸本)9789819635184

This study investigates children’s trust in two humanoid robots, Nao and iCub, through a cooperative game designed to elicit spontaneous behaviors and group dynamics. We investigate whether participants change their choices after hearing advice from a robot, considering rounds where the advice is correct or incorrect, with the robot apologizing for its mistakes. Results reveal that, in most cases, participants prefer not to change their moves after the robot’s advice. Additionally, after the robots made mistakes, participants are less likely to actively follow their advice and more likely to reject it. No significant differences in strategies among the iCub and Nao samples are evidenced. Furthermore, we examine the influence of group dynamics, identifying "Proactive Players" who consistently initiated moves. A significant association between the strategies of this player and their teammates is found, suggesting potential influence. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Int-HRL: towards intention-based hierarchical reinforcement learning

引用

Neural Computing and Applications 2024年 1-12页

作者： Penzkofer, Anna Schaefer, Simon Strohm, Florian Bâce, Mihai Leutenegger, Stefan Bulling, Andreas Institute for Visualisation and Interactive Systems University of Stuttgart Pfaffenwaldring 5A Stuttgart70569 Germany Machine Learning for Robotics Technical University of Munich Boltzmannstrasse 3 Munich85748 Germany Department of Computer Science KU Leuven box 2600 Andreas Vesaliusstraat 13 Leuven3000 Belgium

While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma’s Revenge–one of the most challenging RL tasks in the Atari2600 game suite. We propose Int-HRL: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to an HRL agent that is significantly more sample efficient than previous methods. © The Author(s) 2024.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion 8

One Policy to Run Them All: an End-to-end Learning Approach ...

引用

8th Conference on Robot Learning, CoRL 2024

作者： Bohlinger, Nico Czechmanowski, Grzegorz Krupka, Maciej Kicki, Piotr Walas, Krzysztof Peters, Jan Tateo, Davide Department of Computer Science Technical University of Darmstadt Germany Institute of Robotics and Machine Intelligence Poznan University of Technology Poland Research Department: Systems AI for Robot Learning Germany IDEAS NCBR Warsaw Poland Hessian.AI Germany Centre for Cognitive Science Germany

Deep Reinforcement Learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is still missing a single learning framework that can control all these different embodiments easily and effectively and possibly transfer, zero or few-shot, to unseen robot embodiments. We introduce URMA, the Unified Robot Morphology Architecture, to close this gap. Our framework brings the end-to-end Multi-Task Reinforcement Learning approach to the realm of legged robots, enabling the learned policy to control any type of robot morphology. The key idea of our method is to allow the network to learn an abstract locomotion controller that can be seamlessly shared between embodiments thanks to our morphology-agnostic encoders and decoders. This flexible architecture can be seen as a potential first step in building a foundation model for legged robot locomotion. Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world. © 2024 Proceedings of Machine Learning Research.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Model Predictive Control for Optimal Dose Administration in Radiotherapy 15th

Nonlinear Model Predictive Control for Optimal Dose Administ...

引用

15th Advanced Doctoral Conference on Computing, Electrical and Industrial systems, DoCEIS 2024

作者： Araújo, João C. G. Guerreiro, Bruno J. Oliveira, Luis B. da Silva, Filipe Ferreira CTS-UNINOVA and LASI Department of Electrical and Computer Engineering NOVA School of Science and Technology Caparica2829-516 Portugal Institute for Systems and Robotics LARSyS Lisbon1049-001 Portugal CEFITEC Department of Physics NOVA School of Science and Technology Caparica2829-516 Portugal

ISBN: (纸本)9783031638503

This work discusses the nonlinear modeling of healthy and cancer cell population growth under the influence of radiotherapy, and proposes predictive control techniques to determine the optimal dose for tumor control, while sparing surrounding healthy tissue. Radiation effects are modelled by a linear-quadratic formalism, coupled with a novel population-specific delayed dose response. Numerical simulations of the open- and closed-loop system are conducted, and robustness against model uncertainty is studied. Results illustrate the controller’s performance when dealing with imperfect information and unexpected system behavior, and how it can be tuned to produce the desired treatment outcome. However, optimal operation is conditioned by a limited prediction horizon, as well as strict adherence to treatment schedules and dose restrictions. © IFIP International Federation for Information Processing 2024.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Model Depending on Optimized Support Vector Machine

引用

computers, Materials & Continua 2023年第7期76卷 499-515页

作者： Amel Ali Alhussan Fatma M.Talaat El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Mona Alnaggar Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Machine Learning&Information Retrieval Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Robotics and Intelligent Machines Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt

In computer vision,emotion recognition using facial expression images is considered an important research *** learning advances in recent years have aided in attaining improved results in this *** to recent studies,multiple facial expressions may be included in facial photographs representing a particular type of *** is feasible and useful to convert face photos into collections of visual words and carry out global expression *** main contribution of this paper is to propose a facial expression recognitionmodel(FERM)depending on an optimized Support Vector Machine(SVM).To test the performance of the proposed model(FERM),AffectNet is *** uses 1250 emotion-related keywords in six different languages to search three major search engines and get over 1,000,000 facial photos *** FERM is composed of three main phases:(i)the Data preparation phase,(ii)Applying grid search for optimization,and(iii)the categorization *** discriminant analysis(LDA)is used to categorize the data into eight labels(neutral,happy,sad,surprised,fear,disgust,angry,and contempt).Due to using LDA,the performance of categorization via SVM has been obviously *** search is used to find the optimal values for hyperparameters of SVM(C and gamma).The proposed optimized SVM algorithm has achieved an accuracy of 99%and a 98%F1 score.

关键词： Facial expression recognition machine learning linear dis-criminant analysis(LDA) support vector machine(SVM) grid search

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Fixed-Wing Tail-Sitter Tethered VTOL Drone with Custom Autopilot and Robust Control Techniques 16th

Design and Development of a Fixed-Wing Tail-Sitter Tether...

引用

16th APCA International Conference on Automatic Control and Soft Computing, CONTROLO 2024

作者： Safaee, Ahmad Aguiar, A. Pedro Santos, Filipe Neves Moreira, Antonio Paulo SYSTEC-ARISE Research Center for Systems and Technologies Faculty of Engineering University of Porto Porto4200-465 Portugal INESC-TEC-Institute for Systems and Computer Engineering Technology and Science CRIIS-Centre for Robotics in Industry and Intelligent Systems Porto4200-465 Portugal INESC-TEC-Institute for Systems and Computer Engineering and DEEC/FEUP - Department of Electrical and Computer Engineering Faculty of Engineering of the University of Porto Porto4200-465 Portugal

ISBN: (纸本)9783031817236

The need for aerial platforms capable of sustained operation is critical in fields such as surveillance, agricultural monitoring, disaster response, and temporary telecommunication systems. Traditional unmanned aerial vehicles (UAVs) are hampered by limited battery capacity and inefficient energy utilization. This paper introduces an autonomous vertical flight drone tethered to a ground-based platform, which overcomes these limitations. The drone is designed to optimize its position and energy usage by harnessing wind currents, functioning similarly to a kite when conditions permit. This is enabled by a custom-designed autopilot system comprising both hardware and software tailored for this application. We detail the model identification process for three vertical take-off and landing (VTOL) drone systems, employing authentic data that measures lateral positional errors from the tether. Robust mixed sensitivity controllers are developed and implemented. The effectiveness of these controllers is validated through simulations showing their capability to handle uncertainties. Furthermore, the practical application and robust performance of the system are confirmed by a real-world case study, highlighting its potential in real operational environments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： VTOL/STOL aircraft

来源：评论

学校读者我要写书评

暂无评论

A Scalable Real-time Semantic Segmentation Network for Autonomous Driving 1

A Scalable Real-time Semantic Segmentation Network for Auton...

引用

1st Workshop on Advanced Multimedia Computing for Smart Manufacturing and Engineering, AMC-SME 2023

作者： Liu, Jun Wu, Chao Yuan, Geng Niu, Wei Zhang, Wenbin Song, Houbing Herbert Robotics Institute of School of Computer Science Carnegie Mellon University Pittsburgh United States Department of Electrical & Computer Engineering Northeastern University Boston United States School of Computing University of Georgia Athens United States Department of Computer Science Michigan Technological University Houghton United States Department of Information Systems University of Maryland Baltimore County Baltimore United States

ISBN: (纸本)9798400702730

Computational resources are limited on real-time embedded devices, so the available computing cost of deployment on the target platform must be considered. We develop a feature extraction module based on the MobileNet backbone that can be adjusted in terms of computational complexity and capacity using the depth multiplier parameter, classifier depth, and kernel depth. These three parameters allow us to control the count of channels within the network, effectively managing the model's capacity and computational requirements. To achieve semantic segmentation, we incorporate additional components, such as an extension module. This extension module typically includes 1x1 pointwise convolutional layers for pixel-level classification and a transposed convolutional layer for upsampling the output to the original input image size. By combining the feature extraction module with this extension module, we can create a complete architecture capable of performing semantic segmentation tasks. The feature extraction module provides the initial feature extraction and the extension module adds the necessary components for accurate pixel-wise classification and upsampling. Compared to Hardware-aware Neural Architecture Search (NAS), pruning, runtime pruning, and knowledge distillation methods, our model has several advantages in terms of modular design, structural controllability, ease of implementation, and cost-effectiveness. Our computational efficiency, as measured by FLOPS, is highly competitive. Our method is distinguished by solving the problem of MobileNet's inability to adjust the size and number of convolution kernels. It achieves this through adaptable parameter tuning, including MobileNet's depth multiplier, the kernel size in the FCN head's Separable Convolution layer, and the depth of the first Point-wise Convolution layer. These adjustments are customized to match hardware's max multiply-accumulates (MACs), optimizing network capacity and maximizing resource utilizat

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Bilateral-Head Region-Based Convolutional Neural Networks: A Unified Approach for Incremental Few-Shot Object Detection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4376-4390页

作者： Li, Yiting Zhu, Haiyue Tian, Sichao Ma, Jun Xiang, Cheng Vadakkepat, Prahlad National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore Singapore Institute of Manufacturing Technology Agency for Science Technology and Research 138634 Singapore Peking Union Medical College Institute of Medicinal Plant Development Chinese Academy of Medical Sciences Beijing100193 China Robotics and Autonomous Systems Thrust Guangzhou511453 China The Hong Kong University of Science and Technology Division of Emerging Interdisciplinary Areas Hong Kong SAR Hong Kong Hkust Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen Futian518045 China

Practical object detection systems are highly desired to be open-ended for learning on frequently evolved datasets. Moreover, learning with little supervision further adds flexibility for real-world applications such as autonomous driving and robotics, where large-scale datasets could be prohibitive or expensive to obtain. However, continual adaption with small training examples often results in catastrophic forgetting and dramatic overfitting. To address such issues, a compositional learning system is proposed to enable effective incremental object detection from nonstationary and few-shot data streams. First of all, a novel bilateral-head framework is proposed to decouple the representation learning of base (pretrained) and novel (few-shot) classes into separate embedding spaces, which takes care of novel concept integration and base knowledge retention simultaneously. Moreover, to enhance learning stability, a robust parameter updating rule, i.e., recall and progress mechanism, is carried out to constrain the optimization trajectory of sequential model adaption. Beyond that, to enforce intertask class discrimination with little memory burden, we present a between-class regularization method that expands the decision space of few-shot classes for constructing unbiased feature representation. Final, we deeply investigate the incomplete annotation issue considering the realistic scenario of incremental few-shot object detection (iFSOD) and propose a semisupervised object labeling mechanism to accurately recover the missing annotations for previously encountered classes, which further enhances the robustness of the target detector to counteract catastrophic forgetting. Extensive experiments conducted on both Pascal visual object classes dataset (VOC) and microsoft common objects in context dataset (MS-COCO) datasets demonstrate the effectiveness of our method. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

M6(GPT)3: GENERATING MULTITRACK MODIFIABLE MULTI-MINUTE MIDI MUSIC FROM TEXT USING GENETIC ALGORITHMS, PROBABILISTIC METHODS AND GPT MODELS IN ANY PROGRESSION AND TIME SIGNATURE

arXiv

引用

arXiv 2024年

作者： Poćwiardowski, Jakub Modrzejewski, Mateusz Tatara, Marek S. Institute of Computer Science Warsaw University of Technology Warsaw Poland Department of Robotics and Decision Systems Gdansk University of Technology Gdansk Poland

This work introduces the M6(GPT)3 composer system, capable of generating complete, multi-minute musical compositions with complex structures in any time signature, in the MIDI domain from input descriptions in natural language. The system utilizes an autoregressive transformer language model to map natural language prompts to composition parameters in JSON format. The defined structure includes time signature, scales, chord progressions, and valence-arousal values, from which accompaniment, melody, bass, motif, and percussion tracks are created. We propose a genetic algorithm for the generation of melodic elements. The algorithm incorporates mutations with musical significance and a fitness function based on normal distribution and predefined musical feature values. The values adaptively evolve, influenced by emotional parameters and distinct playing styles. The system for generating percussion in any time signature utilises probabilistic methods, including Markov chains. Through both human and objective evaluations, we demonstrate that our music generation approach outperforms baselines on specific, musically meaningful metrics, offering a viable alternative to purely neural network-based systems. © 2024, CC BY-NC-SA.

关键词： Genetic algorithms

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：