检索结果-内蒙古大学图书馆

Prior Knowledge-Driven Hybrid Prompter Learning for RGB-Event Tracking

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Mianzhao Shi, Fan Cheng, Xu Chen, Shengyong Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System School of Computer Science and Engineering Tianjin300384 China Technical University of Denmark Department of Technology Management and Economics Kongens Lyngby Denmark

Event data can asynchronously capture variations in light intensity, thereby implicitly providing valuable complementary cues for RGB-Event tracking. Existing methods typically employ a direct interaction mechanism to fuse RGB and event data. However, due to differences in imaging mechanisms, the representational disparity between these two data types is not fixed, which can lead to tracking failures in certain challenging scenarios. To address this issue, we propose a novel prior knowledge-driven hybrid prompter learning framework for RGB-Event tracking. Specifically, we develop a frame-event hybrid prompter that leverages prior tracking knowledge from the foundation model as intermediate modal support to mitigate the heterogeneity between RGB and event data. By leveraging its rich prior tracking knowledge, the intermediate modal reduces the gap between the dense RGB and sparse event data interactions, effectively guiding complementary learning between modalities. Meanwhile, to mitigate the internal learning disparities between the lightweight hybrid prompter and the deep transformer model, we introduce a pseudo-prompt learning strategy that lies between full fine-tuning and partial fine-tuning. This strategy adopts a divide-and-conquer approach to assign different learning rates to modules with distinct functions, effectively reducing the dominant influence of RGB information in complex scenarios. Extensive experiments conducted on two public RGB-Event tracking datasets show that the proposed HPL outperforms state-of-the-art tracking methods, achieving exceptional performance. © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PointFaceFormer: Local and Global Attention Based Transformer for 3D Point Cloud Face Recognition

PointFaceFormer: Local and Global Attention Based Transforme...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Ziqi Gao Qiufu Li Gui Wang Linlin Shen Computer Vision Institute Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science University of Nottingham Ningbo China

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Existing 3D point cloud-based facial recognition struggles to fully leverage both global and local information inherent in the 3D point cloud data. In this paper, we introduce the PointFaceFormer, the first Transformer model designed for 3D point cloud face recognition. It incorporates an attention mechanism based on dot product and cosine functions to construct a similarity Transformer architecture, which effectively extracts both local and global features from the point cloud data. Experimental results demonstrate that PointFaceFormer achieves a recognition accuracy of 89.08% and a verification accuracy of 76.93% on the large-scale facial point cloud dataset Lock3DFace, which is a new state-of-the-art in 3D face recognition. Furthermore, PointFaceFormer exhibits excellent generalization performance on cross-quality datasets. Additionally, we validate the effectiveness of the attention mechanism through ablation experiments, which justify the effectiveness of the proposed modules.

关键词： Point cloud compression Solid modeling Three-dimensional displays Attention mechanisms Accuracy Face recognition Transformers

来源：评论

学校读者我要写书评

暂无评论

HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation

HR-APR: APR-agnostic Framework with Uncertainty Estimation a...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Changkun Liu Shuai Chen Yukun Zhao Huajian Huang Victor Prisacariu Tristan Braud Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Engineering Science Active Vision Laboratory University of Oxford United Kingdom Division of Integrated Systems Design The Hong Kong University of Science and Technology Hong Kong

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact of these unreliable predictions. However, existing uncertainty modelling techniques are often coupled with a specific APR architecture, resulting in suboptimal performance compared to state-of-the-art (SOTA) APR methods. This work introduces a novel APR-agnostic framework, HR-APR, that formulates uncertainty estimation as cosine similarity estimation between the query and database features. It does not rely on or affect APR network architecture, which is flexible and computationally efficient. In addition, we take advantage of the uncertainty for pose refinement to enhance the performance of APR. The extensive experiments demonstrate the effectiveness of our framework, reducing 27.4% and 15.2% of computational overhead on the 7Scenes and Cambridge Landmarks datasets while maintaining the SOTA accuracy in single-image APRs.

关键词： Training Uncertainty Accuracy Databases Pipelines Estimation Network architecture

来源：评论

学校读者我要写书评

暂无评论

Adaptive Federated Learning for EEG Emotion Recognition

Adaptive Federated Learning for EEG Emotion Recognition

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Calvin Chan Qingqing Zheng Chengjian Xu Qiong Wang Pheng Ann Heng Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Department of Computer Science and Engineering The Chinese University of Hong Kong

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Emotion classification based on electroencephalogram (EEG) signals has drawn huge attention in affective brain computer interface (BCI). Recently, plenty of deep learning approaches have been proposed to improve the performance of EEG emotion recognition, especially the application of domain adaptation methods to tackle the challenge of large individual differences of EEG signals from subject to subject. However, these conventional transfer learning methods would result in information leakage during the sharing of domain data to enhance the accuracy of the target tasks. Therefore, in this paper, we proposed a distributed deep learning method, named adaptive federated learning (AdaFL) for EEG emotion recognition. In AdaFL, a server collaboratively learns a global model by adaptively aggregating the local models according to their importance in several communication rounds. In particular, an importance function is developed to evaluate each client, which would determine to select a subset of optimal clients for subsequent global model aggregation. The function is a simple transformation of the training loss and the sample size of the local models. Then, the resulting importance scores of selected clients are further converted into aggregation coefficients to measure the weights of the local models for global model aggregation. The distinct advantage of AdaFL is that the cross-subject information could be well utilized and the information leakage risk could be significantly reduced. To validate the efficacy of the proposed AdaFL, we conduct extensive experiments on two real EEG emotion datasets, i.e., SEED and DEAP. The experimental results show that the proposed AdaFL has achieved 94.95 ± 0.40% and 91.06 ± 0.29% average classification accuracy on the SEED and DEAP datasets, respectively, which reflects the superiority of our method over the state-of-the-art approaches.

关键词： Training Deep learning Adaptation models Emotion recognition Accuracy Federated learning Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Matching individual Ladoga ringed seals across short-term image sequences (vol 102, pg 957, 2022)

引用

MAMMALIAN BIOLOGY 2022年第3期102卷 1045-1045页

作者： Nepovinnykh, E. Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering School of Engineering Science Lappeenranta-Lahti University of Technology LUT P.O.Box 20 53851 Lappeenranta Finland Department of Artificial Intelligence Institute of Computer Science and Technology Peter the Great St. Petersburg Polytechnic University Polytechnicheskaya 29 Saint Petersburg Russian Federation 195251 Department of Computer Science and Computational Experiment Southern Federal University Rostov-on-Don Russian Federation 344006 Interregional Charitable Public Organization “Biologists for Nature Conservation” (BFNC) 24 line 3-7 Saint Petersburg Russian Federation 199106

Automated wildlife reidentification has attracted increasing attention in recent years as it provides a non-invasive tool to identify and to track individual wild animals over time. In this paper, the first steps are taken towards the automatic photo-identification of the Ladoga ringed seals (Pusa hispida ladogensis). A method is proposed that takes a sequence of images, each containing multiple individuals as the input, and produces cropped images of seals grouped based on one certain individual per group. The method starts by detecting each seal from the images and proceeds to matching the individual seals between the images. It is shown that high grouping accuracy can be obtained with a general-purpose image retrieval method on an image sequence taken from the same location within a relatively short period of time. Each resulting group contains multiple images of one individual with slightly different variations, for example, in pose and illumination. Utilizing these images simultaneously provides more information for the individual re-identification compared to the traditional approach, i.e., which utilizes just one image at a time. It is further demonstrated that a convolutional neural network based method can be used to extract the unique pelage patterns of the seals despite the low contrast. Finally, a method is proposed and experiments with the novel Ladoga ringed seals data are carried out to provide a proof-of-concept for the individual re-identification.

关键词： Animal re-identification Convolutional neural networks Instance segmentation Ladoga ringed seal Photo-identification

来源：评论

学校读者我要写书评

暂无评论

Towards the Improvement of the Cognitive Process of the Synthesized speech of Mathematical Expression in MathML: An Eye-Tracking 2

Towards the Improvement of the Cognitive Process of the Synt...

引用

2nd International Conference on Interactive Media, Smart Systems and Emerging Technologies, IMET 2022

作者： Souza, Adriana Freitas, Diamantino Bahia Federal Institute of Education Science and Technology Bahia Brazil Doctoral Program in Digital Media Faculty of Engineering of the University of Porto Porto Portugal Faculty of Engineering of the University of Porto Speech Processing Laboratory Electrical and Computer Engineering Department Porto Portugal

ISBN: (数字)9781665470162

ISBN: (纸本)9781665470162

Being one essential part of the solutions we are developing to provide accessibility for blind persons, synthesized speech of mathematical content, although having evolved in naturalness in recent years, still keeps a characteristic of generating very long outputs, which makes it difficult for a person who uses a screen reader to memorize. Eye-gaze tracking has been useful for studying cognitive processes and student's effort in performing tasks therefore it seems attractive as a means to understand how people analyze, process, and break down extensive math expressions into smaller ones. This understanding can help to build a similar model of auditory rendering of MathML capable of avoiding cognitive overload. Therefore, we carried out an experiment to do a gaze-based analysis of reading and memorizing mathematical expressions. Our sample consisted of fourteen participants, and seven mathematical expressions were used in the experiment. The results showed that the computed complexity of the expressions and the average duration of eye-gaze fixations have a strong and significant relationship. Therefore, we conclude that the complexity variable must always be considered in the speech synthesis process of mathematical expressions. However, when considering why participants requested the repetition of an expression with not larger complexity during the memorization process, a tentative interpretation based on the number of MathML tree nodes and the computed complexity of the expressions was not enough to explain it, indicating that other factors need to be investigated. Although some answers to the research questions were not yet conclusive, we consider this research relevant because it points to directions for the work in order to minimize the cognitive processing and mental load of the synthesized speech rendering of mathematical expressions. © 2022 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

A Riemannian Residual Learning Mechanism for SPD Network

A Riemannian Residual Learning Mechanism for SPD Network

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhenyu Cai Rui Wang Tianyang Xu Xiaojun Wu Josef Kittler School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Wuxi China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K.

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The generalization of Euclidean network paradigm to the Riemannian manifolds has attracted much attention for offering useful geometric representations in processing manifold-valued data in recent years. However, the information degradation during data compression mapping hinders Riemannian networks from going deeper, and there are very few solutions specifically designed for this problem. Given the remarkable success of deep Residual learning in Euclidean networks, a novel Riemannian residual learning mechanism (RRLM) is proposed in the context of Symmetric Positive Definite (SPD) manifolds, enabling the characterization of deep spatiotemporal features while preserving the manifold properties. Based on RRLM, a stack of SPD manifold-constrained residual-like blocks is designed on the tail of the original SPDNet(backbone) for the sake of conducting deep Riemannian residual learning. For simplicity, we refer to the network architecture introduced above as Riemannian residual SPD network (ResSPDNet). The experimental results achieved on three types of visual classification tasks, i.e., facial emotion recognition, drone recognition, and action recognition, demonstrate that our method can achieve improved accuracy with a deepened network structure.

关键词： Manifolds Learning systems Degradation Emotion recognition Visualization Accuracy Face recognition

来源：评论

学校读者我要写书评

暂无评论

FusionPortableV2: A Unified Multi-Sensor Dataset for Generalized SLAM Across Diverse Platforms and Scalable Environments

arXiv

引用

arXiv 2024年

作者： Wei, Hexiang Jiao, Jianhao Hu, Xiangcheng Yu, Jingwen Xie, Xupeng Wu, Jin Zhu, Yilong Liu, Yuxuan Wang, Lujia Liu, Ming Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Robot Perception and Learning Lab Department of Computer Science University College London United Kingdom Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology China Guangzhou China

Simultaneous Localization and Mapping (SLAM) technology has been widely applied in various robotic scenarios, from rescue operations to autonomous driving. However, the generalization of SLAM algorithms remains a significant challenge, as current datasets often lack scalability in terms of platforms and environments. To address this limitation, we present FusionPortableV2, a multi-sensor SLAM dataset featuring sensor diversity, varied motion patterns, and a wide range of environmental scenarios. Our dataset comprises 27 sequences, spanning over 2.5 hours and collected from four distinct platforms: a handheld suite, a legged robot, a unmanned ground vehicle (UGV), and a vehicle. These sequences cover diverse settings, including buildings, campuses, and urban areas, with a total length of 38.7km. Additionally, the dataset includes ground-truth (GT) trajectories and RGB point cloud maps covering approximately 0.3km2. To validate the utility of our dataset in advancing SLAM research, we assess several state-of-the-art (SOTA) SLAM algorithms. Furthermore, we demonstrate the dataset's broad application beyond traditional SLAM tasks by investigating its potential for monocular depth estimation. The completae dataset, including sensor data, GT, and calibration details, is accessible at https://***/dataset/fusionportable v2. Copyright © 2024, The Authors. All rights reserved.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

A Multifaceted Feature Extraction Approach for Noise-Robust Punjabi Spoken Digit Recognition System Under Low-Resource Conditions

A Multifaceted Feature Extraction Approach for Noise-Robust ...

引用

International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions)

作者： Puneet Bawa Virender Kadyan Gunjan Chhabra Centre of Excellence for Speech and Multimodal Laboratory Chitkara University Institute of Engineering & Technology Chitkara University Punjab India Speech and Language Research Centre School of Computer Science University of Petroleum & Energy Studies Energy Acres Bidholi Dehradun Uttarakhand India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

ISBN: (数字)9798350350357

ISBN: (纸本)9798350350364

The development of optimal solutions in un-favourable acoustic conditions has become a crucial step in guaranteeing the durability and dependability of automated speech recognition (ASR) systems across many real-world applications. The study aims to enhance the efficiency of low-resource ASR systems in scenarios when conventional systems exhibit sub-optimal performance. The proposed methodology aims to enhance the performance of Punjabi spoken digit recognition in noisy situations with limited resources. This is achieved via the use of multidimensional feature extraction and model adapation methods. Initially, a baseline system has been developed under clean enviornmental conditions. Subsequently, a singular enhancement of a spoken digit-based system is carried out, including phonetically diverse and continuous Punjabi phrases. Moreover, research on noise augmentation demonstrate that the approaches used for feature extraction have a subtle but significant effect. The vulnerability of Mel-Frequency Cepstral Coefficients (MFCC) to noise has been found to be remarkable, however, Gammatone Frequency Cepstral Coefficients (GFCC) and the combined feature extraction approach of MFCC and GFCC (MF-GFCC) exhibit excellent resistance. The multifaceted approach undergoes a battery of rigorous tests at various noise levels, aiming to simulate the conditions often seen in real-world situations. The efficacy of the suggested enhancements has been validated by evaluating and appraising the performance evaluation metrics, the Word Error Rate (WER). The findings reveals the lower WER of 13.25% under high noise conditions and 13.30% under low noise conditions indicating not only provide valuable insights for improving speech recognition in challenging real-world situations, but also providing ramifications for various languages that have comparable limits as English.

关键词： Resistance Error analysis Noise speech recognition speech enhancement Feature extraction Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Toward AI-Powered Edge Intelligence for Object Detection in Self-Driving Cars: Enhancing IoV Efficiency and Safety

引用

IEEE Internet of Things Journal 2025年第11期12卷 16990-16997页

作者： Ahmed, Imran Ahmad, Misbah Siddiqi, Muftooh Ur Rehman Chehri, Abdellah Jeon, Gwangill Anglia Ruskin University School of Computing and Information Science CambridgeCB1 1PT United Kingdom University of the West of England Centre for Machine Vision Bristol Robotics Laboratory BristolBS16 1QY United Kingdom Hartpury University Department of Animal and Agriculture GloucesterGL19 3BE United Kingdom Aston University College of Engineering and Physical Sciences BirminghamB4 7ET United Kingdom Royal Military College of Canada Department of Mathematics and Computer Science KingstonONK7K 7B4 Canada Incheon National University Department of Embedded Systems Engineering Incheon22012 Korea Republic of

In the rapidly advancing field of intelligent transportation systems, integrating artificial intelligence (AI) with edge computing presents a promising way to enhance the safety and efficiency of the Internet of Vehicles (IoV). This study explores and presents a deep learning-based object detection model within an edge computing framework which aims to facilitate real time object detection in self driving cars. Using an urban traffic scenarios-based dataset, our research shows the ability of the model to accurately detect and classify various objects important for autonomous driving. The YOLOv8 model is used in this work due to its optimal balance between accuracy and computational efficiency. This model has also demonstrated its worth by achieving good performance results, including an average precision of 0.79, a recall of 0.62, and an F1-score of 0.69. The results are demonstrated by a detailed confusion matrix, highlighting the model’s effectiveness in complex driving environments and underscoring its reliability for in-vehicle deployment. By implementing AI directly on edge devices within vehicles, our approach might be helpful in significantly reducing latency, boosting decision-making speed, and enhancing data privacy by minimising dependence on cloud processing. The findings not only support the model’s capabilities but also illustrate the practical benefits of edge intelligence in autonomous vehicles. These benefits, such as faster decision making and improved data privacy, contribute effectively to the IoV infrastructure. This study marks a substantial step toward recognizing the possibility of AI-enhanced edge computing in driving the next generation of autonomous vehicle technology. © 2014 IEEE.

关键词： Artificial intelligence (AI) autonomous vehicles deep leaning edge computing Internet of Vehicles (IoV)

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：