检索结果-内蒙古大学图书馆

2023 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2023

作者： Kulwa, Frank Samuel, Oluwarotimi Williams Asogbon, Mojisola Grace Oyemakinde, Tolulope Tofunmi Obe, Olumide Olayinka Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems SIAT-CAS China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Guangdong Shenzhen518055 China University of Derby School of Computing and Engineering DerbyDE22 3AW United Kingdom Federal University of Technology Department of Computer Science Akure Nigeria

ISBN: (纸本)9781665493840

A major barrier to the commercialization of pattern recognition (PR)-based myoelectric prostheses is the lack of robustness to confounding factors such as electrode shift which has been lingering for years. To overcome this challenge, a novel Duo-Stage Convolutional Neural Network (DS-CNN) is proposed. The DS-CNN is comprised of two cascaded stages in which the first stage deciphers the occurrence of a particular kind of shift upon which a requisite CNN model is triggered in the second stage for accurate decoding of individual motion intent, which is necessary for initiating robust control of the prostheses. The proposed scheme works on raw EMG signals as input which reduces the preprocessing time that would be required in conventional machine learning-based PR schemes, to effectively mitigate both transverse and longitudinal shifts using the same network architecture. This approach was validated for four distinct electrode shift conditions (with shifts in the range of 7.50mm-10.05mm) in a dataset obtained from 18 able-bodied subjects that performed 8 classes of targeted hand gestures. The experimental results show that the proposed dual-stage driven deep neural network model can adequately resolve the effects of electrode shift with classification accuracy near the No-shift scenario ( © 2023 IEEE.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Can Encrypted Images Still Train Neural Networks? Investigating Image Information and Random Vortex Transformation

arXiv

引用

arXiv 2024年

作者： Cao, Xiao-Kai Mo, Wen-Jin Wang, Chang-Dong Lai, Jian-Huang Huang, Qiong School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China College of Mathematics and Informatics South China Agricultural University Guangzhou China

Vision is one of the essential sources through which humans acquire information. To simulate this biological characteristic, researchers have proposed models such as Convolutional Neural Networks and Vision Transformers to mimic the human visual system’s processing of visual tasks like image classification. These models have achieved significant success in experiments. However, there has been limited theoretical analysis of the variation in information content during image processing. This is not an insignificant task, as it plays a crucial guiding role in image feature extraction, image quality assessment, and the design of image encryption algorithms. In this paper, we establish a novel framework for measuring image information content to evaluate the variation in information content during image transformations. Within this framework, we design a nonlinear function to calculate the neighboring information content of pixels at different distances, and then use this information to measure the overall information content of the image. Hence, we define a function to represent the variation in information content during image transformations. Additionally, we utilize this framework to prove the conclusion that swapping the positions of any two pixels reduces the image’s information content. Furthermore, based on the aforementioned framework, we propose a novel image encryption algorithm called Random Vortex Transformation. This algorithm encrypts the image using random functions while preserving the neighboring information of the pixels. The encrypted images are difficult for the human eye to distinguish, yet they allow for direct training of the encrypted images using machine learning methods. Experimental verification demonstrates that training on the encrypted dataset using ResNet and Vision Transformers only results in a decrease in accuracy ranging from 0.3% to 6.5% compared to the original data, while ensuring the security of the data. Furthermore, there is a po

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Compact Transformer for Adaptive Style Transfer

A Compact Transformer for Adaptive Style Transfer

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yi Li Xin Xie Haiyan Fu Xiangyang Luo Yanqing Guo School of Artificial Intelligence Dalian University of Technology Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

Due to the limitation of spatial receptive field, it is challenging for CNN-based style transfer methods to capture rich and long-range semantic concepts in artworks. Though the transformer provides a fresh solution by considering long-range dependencies, it suffers from the heavy burdens of parameter scale and computation cost especially in vision tasks. In this paper, we design a compact transformer architecture AdaFormer to address the problem. The model scale shrinks about 20% compared to state-of-the-art transformer for style transfer. Furthermore, we explore the adaptive style transfer by letting the content to select the detailed style element automatically and adaptively, which encourages the output to be both appealing and reasonable. We evaluate AdaFormer comprehensively in the experiments and the results have shown the effectiveness and superiority of our approach compared to existing artistic methods. Diverse plausible stylized images are obtained with better content preservation, more convincing style sfumato and lower computation complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval

arXiv

引用

arXiv 2024年

作者： Zeng, Gangyan Zhang, Yuan Wei, Jin Yang, Dongbao Zhang, Peng Gao, Yiwen Qin, Xugong Zhou, Yu School of Cyber Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Media Convergence and Communication Communication University of China China Institute of Information Engineering Chinese Academy of Sciences China Laboratory for Advanced Computing and Intelligence Engineering China TMCC College of Computer Science Nankai University China

Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition processes, resulting in inefficient and inflexible retrieval. Different from them, in this work we propose to explore the intrinsic potential of Contrastive Language-Image Pre-training (CLIP) for OCR-free scene text retrieval. Through empirical analysis, we observe that the main challenges of CLIP as a text retriever are: 1) limited text perceptual scale, and 2) entangled visual-semantic concepts. To this end, a novel model termed FDP (Focus, Distinguish, and Prompt) is developed. FDP first focuses on scene text via shifting the attention to the text area and probing the hidden text knowledge, and then divides the query text into content word and function word for processing, in which a semantic-aware prompting scheme and a distracted queries assistance module are utilized. Extensive experiments show that FDP significantly enhances the inference speed while achieving better or competitive retrieval accuracy compared to existing methods. Notably, on the IIIT-STR benchmark, FDP surpasses the state-of-the-art model by 4.37% with a 4 times faster speed. Furthermore, additional experiments under phrase-level and attribute-aware scene text retrieval settings validate FDP’s particular advantages in handling diverse forms of query text. The source code will be publicly available at https://***/Gyann-z/FDP. © 2024, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Continual Learning with Bayesian Model Based on a Fixed Pre-Trained Feature Extractor

SSRN

引用

SSRN 2022年

作者： Yang, Yang Cui, Zhiying Xu, Junjie Zhong, Changhong Zheng, Wei-Shi Wang, Ruixuan School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing MOE

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly in intelligent diagnosis systems where initially only training data of a limited number of diseases are available. In this case, updating the intelligent system with data of new diseases would inevitably downgrade its performance on previously learned diseases. Inspired by the process of learning new knowledge in human brains, we propose a Bayesian generative model for continual learning built on a fixed pre-trained feature extractor. In this model, knowledge of each old class can be compactly represented by a collection of statistical distributions, e.g. with Gaussian mixture models, and naturally kept from forgetting in continual learning over time. Unlike existing class-incremental learning methods, the proposed approach is not sensitive to the continual learning process and can be additionally well applied to the data-incremental learning scenario. Experiments on multiple medical and natural image classification tasks showed that the proposed approach outperforms state-of-the-art approaches which even keep some images of old classes during continual learning of new classes. © 2022, The Authors. All rights reserved.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Libo Qin Fuxuan Wei Qiguang Chen Jingxuan Zhou Shijue Huang Jiasheng Si Wenpeng Lu Wanxiang Che School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU.

关键词： Large language models Signal processing Benchmark testing Multitasking Filling Acoustics Speech processing Information exchange Standards

来源：评论

学校读者我要写书评

暂无评论

VISUALLY MAINTAINED IMAGE DISTURBANCE AGAINST DEEPFAKE FACE SWAPPING

VISUALLY MAINTAINED IMAGE DISTURBANCE AGAINST DEEPFAKE FACE ...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Dong, Junhao Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781665438643

As a deep learning-based application, DeepFake can generate malicious images or videos through replacing the face of a source image with the target face, which poses a significant threat to social media. In this paper, we propose a scheme to prevent such tampering by exploring adversarial examples against DeepFake. Specifically, adversarial examples are produced by adding tailored distortion to source images. The added distortion is imperceptible to human vision but can mislead the generation of face-swapped images effectively. We present three novel adversarial attacks against DeepFake autoencoders from perspectives of adversarial transferability and latent representation. Our first method synthesizes universal perturbation, which is image-agnostic. By contrast, the latter two methods directly perform the preciser perturbation specific to a source image. Extensive experiments demonstrate the effectiveness of our adversarial examples against DeepFake in terms of both reference and non-reference image quality assessment. © 2021 IEEE

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Motion Feature Integration for Action Recognition

Multi-scale Motion Feature Integration for Action Recognitio...

引用

International Conference on Computer and Communications (ICCC)

作者： Jinming Lai Huicheng Zheng Jisheng Dang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology China

Analyzing video data with intricate temporal structures and extracting comprehensive motion information remains a significant challenge. In this work, we introduce the multi-scale motion feature integration (MMFI) network, which leverages two key modules for motion analysis: the progressive local context aggregation (PLCA) module and the multi-scale motion excitation (MSME) module. The PLCA module captures frame-level motion details by incrementally processing frame-wise differences near the input frame in the early stages of the network. The MSME module provides motion-attentive channel weights in deeper layers with higher dimensions, incorporating short- and long-range segment-level motion information. These modules synergistically capture motion details across various scales. Our approach is evaluated on the large-scale video dataset Something-Something V1, yielding state-of-the-art performance with minimal computational overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GAEM: Graph-driven Attention-based Entropy Model for LiDAR Point Cloud Compression

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Cui, Mingyue Zhong, Yuyang Feng, Mingjian Long, Junhua Ling, Yehua Xu, Jiahao Huang, Kai Sun Yat-sen University School of Computer Science and Engineering Guangzhou400100 China Sun Yat-sen University key Laboratory of Machine Intelligence and Advanced Computing Guangzhou400100 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Guangxi Transportation Science and Technology Group Co. Ltd Nanning530029 China

High-quality LiDAR point cloud (LPC) coding is essential for efficiently transmitting and storing the vast amounts of data required for accurate 3D environmental representation. The Octree-based entropy coding framework has emerged as the predominant method, however, previous study usually overly relies on large-scale attention-based context prediction to encode Octree nodes, overlooking the inherent correlational properties of this structure. In this paper, we propose a novel Graph-driven Attention-based Entropy Model (GAEM), which adopts partitioned graph attention mechanisms to uncover contextual dependencies among neighboring nodes. Different from the Cartesian coordinate-based coding mode with higher redundancy, GAEM uses the multi-level spherical Octree to organize point clouds, improving the quality of LPC reconstruction. GAEM combines graph convolution for node feature embedding and grouped-graph attention for exploiting dependency among contexts, which preserves performance in low-computation using localized nodes. Besides, to further increase the receptive field, we design a high-resolution cross-attention module introducing sibling nodes. Experimental results show that our method achieves state-of-the-art performance on the LiDAR benchmark SemanticKITTI and MPEG-specified dataset Ford, compared to all baselines. Compared to the benchmark GPCC, our method achieves gains of up to 53.9% and 53.6% on SemanticKITTI and Ford while compared to the sibling-introduced methods, we achieve up to 42.3% and 44.7% savings in encoding/decoding time. In particular, our GAEM allows for extension to downstream tasks (i.e., vehicle detection and semantic segmentation), further demonstrating the practicality of the method. (Figure presented) © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Hypergraph-Enhanced Multi-Granularity Stochastic Weight Completion in Sparse Road Networks

引用

ACM Transactions on Knowledge Discovery from Data 2025年第3期19卷

作者： Han, Xiaolin Zhang, Yikun Ma, Chenhao Shang, Xuequn Cheng, Reynold Grubenmann, Tobias Li, Xiaodong Northwestern Polytechnical Universit China and Laboratory for Advanced Computing and Intelligence Engineering Wuxi Xi'an China Northwestern Polytechnical University Xi'an China The Chinese University of Hong Kong - Shenzhen Shenzhen China The University of Hong Kong Hong Kong Edinburgh Napier University Edinburgh United Kingdom Xiamen University China and Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen China

Road network applications, such as navigation, incident detection, and Point-of-Interest (POI) recommendation, make extensive use of network edge weights (e.g., traveling times). Some of these weights can be missing, especially in a road network where traffic data may not be available for every road. In this article, we study the stochastic weight completion (SWC) problem, which computes the weight distributions of missing road edges. This is difficult, due to the intricate temporal and spatial correlations among neighboring edges. Besides, the road network can be sparse, i.e., there is a lack of traveling information in a large portion of the network. To tackle these challenges, we propose a multi-granularity framework for Region-Wise Graph Completion (RegGC). To learn coarse spatial correlations among distantly located roads, we construct a region-wise hypergraph neural architecture based on semantic region dependencies. For finer spatial correlations, we incorporate contextual road network properties (e.g., speed limits, lane counts, and road types). Moreover, it incorporates recent and periodic dimensions of road traffic. We evaluate RegGC against 10 existing methods on 3 real road network datasets. They show that RegGC is more effective and efficient than state-of-the-art solutions. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Semantic Segmentation

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：