检索结果-内蒙古大学图书馆

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Duan, Zhen Xiao, Shenghua Chen, Jie Zhao, Shu Zhang, Yanping Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui Hefei 230601 China School of Computer Science and Technology Anhui University Hefei 230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Hefei 230601 China

ISBN: (纸本)9783031927409

Few-shot Named Entity Recognition (Few-shot NER) aims to identify and classify unseen named entity types with a limited labeled samples. In recent years, large language models have achieved remarkable results in various NLP tasks due to their excellent zero/few-shot generalization capabilities. Recent research has extensively focused on using large language models to study the named entity recognition task. Negative sample entities have been demonstrated to be effective when performing this task using in-context learning paradigm. However, the problem of low efficiency and poor quality in manually constructing negative sample entities has been exposed. To address this issue, in this paper, we propose a Few-shot NER method based on generative negative sample enhancement (GNSE). Specifically, GNSE first utilizes a large language model to pre-identify potential entity spans in the support set text paragraphs in a zero-shot manner and generate the semantics of the spans based on the paragraph context. Then, the pre-identified candidate spans are compared with the ground-truth labels to determine positive or negative sample entity spans. Finally, based on Chain-of-Thought, the span semantics, positive and negative sample entities, and ground-truth labels are inserted into the example template for the in-context learning paradigm, and the test text from the query set is concatenated to construct a complete prompt. GNSE was evaluated on three widely used datasets: CoNLL’03, WNUT’17 and GUM. Experiments show that GNSE has achieved better performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Few-shot Named Entity Recognition In-context Learning Large Language Model Prompt Engineering

来源：评论

学校读者我要写书评

暂无评论

Metal Surface Defect Detection Algorithm Based on Improved YOLOv5

Metal Surface Defect Detection Algorithm Based on Improved Y...

引用

IEEE information technology and Mechatronics Engineering Conference (ITOEC)

作者： Xiaodong Su Fengchun Zhang Yurong Zhang Hongyan Xu Xu Chen College of Computer and-Information:Engineering Harbin-University of Commerce Harbin China Heilongiiang Provincial Key:Laboratory of Electronic Commerce and Information Processing Harbin China

Aiming at the problem of model misdetection and missed detection caused by the small defect and unclear features of industrial metal surfaces, this paper studies a large number of metal surface defects, and proposes a metal surface micro defect detection algorithm based on improved YOLOv5. First, this paper uses the FenceMask data enhancement method for regularization to solve the problem of few sample images. Then an enhanced multi-scale feature fusion pyramid network DS-FPN is proposed by introducing depthwise separable convolution, dilated convolution and spatial attention mechanism, so that the model can improve the ability to extract key information of images without adding additional parameters and calculations. An adaptive channel spatial attention mechanism SCBAM is also proposed, which adds non-local information to the original interaction with only local information, improving the feature expression ability of the model. Finally, through experimental verification, the detection accuracy of the model in this paper on the public data set GC10-DET has reached 74.9%, which is 4.7% higher than the original YOLOv5 model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GPMN: Human Pose Explicit Modeling Network based on Graph Model

GPMN: Human Pose Explicit Modeling Network based on Graph Mo...

引用

IEEE information technology and Mechatronics Engineering Conference (ITOEC)

作者： Yuru Zhang Jiayuan Zhao Xiaodong Su Hongyan Xu College of Computer and Information Engineering Harbin University of Commerce Harbin China Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin China

The human pose estimation task requires the use of visual cues and anatomical relationships between joints to locate key points. Due to the structural dependencies between human joints, it is difficult to model the dependencies between joints with a convolutional neural network-based approach. In this paper, we propose a graph pose modeling network (GPMN) based on a graph model, which constructs a structural graph model between joints and then uses a convolutional neural network to explicitly model the dependencies between joints. Specifically, this method extracts features through a backbone network and uses a graph model to obtain proximity joint dependencies. At the same time, a cross-cross-attention mechanism is used to obtain the distant joint dependencies for reinforcing challenging key points. To solve the problem that the challenging key points of the network are weakened during the training process, this paper uses a focal loss function to make the network focus more on the challenging key points, such as knees and ankles. Under the same experimental conditions, HRNet, the highest accuracy feature extraction network, and ResNet, the classical feature extraction network, are used as the backbone network. The accuracy of the algorithm with HRNet network as the backbone is improved by 2.6% compared with the original network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Deep Hashing Method for Multi-Scale Feature Fusion

Transformer-Based Deep Hashing Method for Multi-Scale Featur...

引用

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

作者： Chao He Hongxi Wei School of Computer Science Inner Mongolia University Hohhot China Provincial Key Laboratory of Mongolian Information Processing Technology Hohhot China National and Local Joint Engineering Research Center of Mongolian Information Processing Technology Hohhot China

The deep image hashing aims to map the input image into simply binary hash codes via deep neural networks. Motivated by the recent advancements of Vision Transformers (ViT), many deep hashing methods based on ViT have been proposed. Nevertheless, the ViT has enormous number of model parameters and high computational complexity. Moreover, the last layer of the ViT outputs only the classification tokens as image feature vectors, while the rest of the vectors are discarded. This results in the ineﬃciency of the model computation and the neglect of useful image information. Therefore, this paper proposes a Transformer-based deep hashing method for multi-scale feature fusion (TDH). Specifically, we use a hierarchical Transformer backbone to capture both global and local features of images. The hierarchical Transformer utilizes a local self-attention mechanism to process image blocks in parallel, which reduces computational complexity and promotes computational eﬃciency. Multi-scale feature fusion module captures all image feature vectors of the hierarchical Transformer output to obtain more enriched image feature information. We perform comprehensive experiments on three widely-studied datasets: CIFAR-10, NUS-WIDE and IMAGENET. The experimental results demonstrate that the proposed method in this paper indicates superior results compared to the existing state-of-the-art work. Source code is available https://***/shuaichaochao/TDH.

关键词： Deep learning Codes Speech coding Computational modeling Source coding Neural networks Signal processing

来源：评论

学校读者我要写书评

暂无评论

Exploring Rationale Learning for Continual Graph Learning 39

Exploring Rationale Learning for Continual Graph Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Song, Lei Li, Jiaxing Si, Qinghua Guan, Shihan Kong, Youyong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University Ministry of Education China

ISBN: (纸本)157735897X

Catastrophic forgetting poses a significant challenge for graph neural networks in continuously updating their knowledge base with data streams. To address this issue, much of the research has focused on node-level continual learning using parameter regularization or rehearsal-based strategies, while little attention given to graph-level tasks. Furthermore, current paradigms for continual graph learning may inadvertently capture spurious correlations for specific tasks through shortcuts, thereby exacerbating the forgetting of previous knowledge when new tasks are introduced. To tackle these challenges, we propose a novel paradigm, Rationale Learning GNN (RL-GNN), for graph-level continual graph learning. Specifically, we harness the invariant learning principle to incorporate environmental interventions into both the current and historical distributions, aiming to uncover rationales by minimizing empirical risk across all environments. The rationale serves as the sole factor guiding the learning process. Therefore, continual graph learning is redefined as capturing these invariant rationales within task sequences, alleviating catastrophic forgetting caused by spurious features. Extensive experiments on real-world datasets with varying task lengths demonstrate the effectiveness of our RL-GNN in continuous knowledge assimilation and reduction of catastrophic forgetting. Copyright © 2025, Association for the Advancement of Artificia Intelligence (***). All rights reserved.

关键词： Knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

HePa: Heterogeneous Graph Prompting For All-level Classification Tasks 39

HePa: Heterogeneous Graph Prompting For All-level Classifica...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Jinghong, Jia Song, Lei Li, Jiaxing Kong, Youyong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) Ministry of Education China

ISBN: (纸本)157735897X

Heterogeneous graphs, which are common in real-world downstream tasks, have recently sparked a wave of research interest. The performance of end-to-end heterogeneous graph neural networks (HGNNs) greatly relies on supervised training for specific tasks. To reduce the labeling cost, the”pretrain-finetune” paradigm has been widely adopted, but it leads to a knowledge gap between the pre-trained model and downstream tasks. In an effort to address this gap, the”pretrain-prompt” paradigm has emerged as a promising approach. This involves fine-tuning randomly initialized learnable vectors in downstream tasks. However, this approach may result in an insufficient representation of downstream task features. Existing techniques for heterogeneous graph prompting restructure the heterogeneous graph to align with the homogeneous graph prompting scheme. This can potentially introduce the same limitations as homogeneous graph prompt learning. In this paper, we propose HePa, short for Heterogeneous Graph Prompting for all-level classification tasks. It not only includes a unified prompt template-graph adapted for heterogeneous graphs but also introduces a novel pre-prompt token optimized during the pre-training phase to convey task information downstream. With these designs, HePa can complete all levels of classification tasks toward few-shot scenarios while activating in-context learning. Finally, we conducted a comprehensive experimental analysis of HePa on three benchmark datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Prompt-based Multi-task Learning for Multimodal Dialog State Tracking and Immersive Multimodal Conversation 11

Exploring Prompt-based Multi-task Learning for Multimodal Di...

引用

11th Dialog System technology Challenge, DSTC 2023

作者： Chen, Yirong Li, Ya Wang, Tao Xing, Xiaofen Xu, Xiangmin Liu, Quan Liu, Cong Hu, Guoping Guangdong Provincial Key Laboratory of Human Digital Twin School of EE South China University of Technology Guangzhou China iFLYTEK Research Hefei China Pazhou Lab. Guangzhou China School of Future Technology South China University of Technology Guangzhou China State Key Laboratory of Cognitive Intelligence Hefei China National Engineering Research Center of Speech and Language Information Processing Hefei China

With the rise of the metaverse, immersive multimodal conversation has attracted more and more researchers’ attention. Multimodal contexts will become more important for human-computer interaction in the metaverse, especially in shopping domain. Unlike traditional conversation tasks, immersive multimodal conversation has challenges such as multimodal ambiguous candidate identification and multimodal coreference resolution, which makes it more difficult to dialog state tracking and response generation, as described in SIMMC 2.1 challenge, a part of DSTC11. In particular, as the number of objects in the scene increases, the difficulty will increase dramatically. We proposed PMTLED (Prompt-based Multi-Task Learning Encoder-Decoder), in which different subtasks use different prompts to make the model tend to focus on the current subtask. We achieve the winner in ambiguous candidates indentification and runner-up in multimodal coreference resolution (MM-Coref), multimodal dialog state tracking (MM-DST) and assistant response generation. Our code and model are made publicly available at https://***/scutcyr/dstc11-simmc2.1-scut-bds-lab. © 2023 Association for Computational Linguistics.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition of sEMG Based on Res-LSTM 17th

Gesture Recognition of sEMG Based on Res-LSTM

引用

17th International Conference on Intelligent Robotics and Applications, ICIRA 2024

作者： Zhao, Yujia Zou, Chunlong Yun, Juntong Jiang, Du Huang, Li Liu, Ying Jiang, Guozhang Xie, Yuanmin Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442000 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430081 China College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

sEMG (surface electromyography) signal control of bionic prostheses has been widely studied over the past few years. In particular, sparse sEMG signals are rapidly developing in the field of gesture recognition for their convenience, noninvasiveness, and ease of access. However, compared with high-density EMG signals, sparse EMG signals lack rich feature information, which in turn affects gesture recognition accuracy. In order to reduce the loss of feature information of sparse EMG signals in the spatio-temporal dimension, this paper proposes a hybrid neural network Res-LSTM combining residual network and long short-term memory network. The ordinary convolutional blocks in the CNN network are replaced with residual blocks, and the final fully connected layer is removed and a constant mapping layer is added to adequate extraction of spatial feature information of the data. The Res layer’s output is utilized as the input for the long and short-term memory (LSTM) network, which further extracts the features of the data in the temporal dimension, and finally completes the categorization output through a fully connected layer. The average accuracy of 91.11% for gesture-motion classification was verified by training on a homebrew dataset;and tested on a public dataset, NinaPro DB1, with an average accuracy of 91.03%. The experimental findings indicate that the proposed Res-LSTM network framework contributes to solving the problem of lack of feature information of sparse sEMG signals and improves the pattern recognition accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Guided Implicit Depth Function With Scale-Aware Feature Fusion

引用

IEEE transactions on image processing : a publication of the IEEE Signal processing Society 2025年 34卷 3309-3322页

作者： Yifan Zuo Yuqi Hu Yaping Xu Zhi Wang Yuming Fang Jiebin Yan Wenhui Jiang Yuxin Peng Yan Huang Jiangxi University of Finance and Economics School of Information Management Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing (No. 2024SSY03141) Jiangxi Nanchang China Peking University Wangxuan Institute of Computer Technology Beijing China University of Technology Sydney Australian Artificial Intelligence Institute Sydney NSW Australia

Recently, the single image super-resolution based on implicit image function is a hot topic, which learns a universal model for arbitrary upsampling scales. By contrast, color-guided depth map super-resolution is less explored based on implicit function learning. The related research faces three questions. First, is it also necessary and applicable to fuse the depth feature and the color feature in the encoder with continuous upsampling scales? Second, is the scale information in the encoder as important as that in the decoder? Third, how to efficiently and effectively model the affinity of location distance and content similarity within cross domains in the decoder? This paper proposes a transformer-based network to answer the above questions, which includes a depth super-resolution branch and a guidance extraction branch. Specifically, in the encoder, the effective implicit cross transformer is designed to fuse the guidance from the color feature with continuous coordinate mapping. In addition, the unrelated guidance is filtered out by correlation evaluation in the high-dimension feature space. Unlike the scale only introduced in the decoder, this paper additionally embeds the scale into the position encoding and the feed-forward network in the encoder to learn the scale-aware feature representation. In the decoder, the high-resolution depth feature is reconstructed by using the internal prior and the external guidance. The internal prior is implemented by implicit self-attention in the depth super-resolution branch, and the external guidance is exploited via implicit cross-attention between both branches. Finally, the above decoded features are complementary to generate the high-resolution depth map. The sufficient experiments on the synthetic and real datasets for in-distribution and out-of-distribution upsampling scales validate the improved performance. The code and the models are public via https://***/NaNRan13/GIDF.

关键词： Guided Depth Map Super-resolution Implicit Image Function Local Implicit Transformer Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Alignment-Free RGB-T Salient Object Detection: A Large-scale Dataset and Progressive Correlation Network

arXiv

引用

arXiv 2024年

作者： Wang, Kunpeng Chen, Keke Li, Chenglong Tu, Zhengzheng Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University China Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University China

Alignment-free RGB-Thermal (RGB-T) salient object detection (SOD) aims to achieve robust performance in complex scenes by directly leveraging the complementary information from unaligned visible-thermal image pairs, without requiring manual alignment. However, the labor-intensive process of collecting and annotating image pairs limits the scale of existing benchmarks, hindering the advancement of alignment-free RGB-T SOD. In this paper, we construct a large-scale and high-diversity unaligned RGB-T SOD dataset named UVT20K, comprising 20,000 image pairs, 407 scenes, and 1256 object categories. All samples are collected from real-world scenarios with various challenges, such as low illumination, image clutter, complex salient objects, and so on. To support the exploration for further research, each sample in UVT20K is annotated with a comprehensive set of ground truths, including saliency masks, scribbles, boundaries, and challenge attributes. In addition, we propose a Progressive Correlation Network (PCNet), which models inter- and intra-modal correlations on the basis of explicit alignment to achieve accurate predictions in unaligned image pairs. Extensive experiments conducted on unaligned and aligned datasets demonstrate the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

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：