检索结果-内蒙古大学图书馆

Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagation

ACM Transactions on Multimedia computing, Communications and Applications 2025年第4期21卷

作者： Wang, Jiahui Xu, Qin Jiang, Bo Luo, Bin The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China The Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

The transductive Few-shot Learning (FSL) mostly employs either prototype learning or label propagation methods to generalize to new classes by using the information of all query samples. However, existing methods have several main limitations. First, the prototype methods mainly focus on support samples which fail to fully exploit the relationships of query samples. Second, existing label propagation methods are generally not effective for the class-imbalanced problem. Third, existing works usually optimize the learnable parameters during inference which significantly reduces the efficiency of existing methods. To address these limitations, this article proposes an efficient and robust method for transductive FSL problem, termed Prototype-based Soft-label Propagation (PSLP), which combines the prototype learning and label propagation together for FSL problem. In our proposed method, first, the soft-label presentation for each query sample is estimated by leveraging prototypes. Then, the soft-label propagation is conducted on the learned query-support graph and the prototype representation is rectified. Both steps are conducted progressively for boosting the performance. Moreover, to learn effective prototypes for soft-label estimation and the desirable query-support graph for soft-label propagation, we design a new joint message passing scheme to learn the sample presentation and relational graph jointly. The PSLP method is parameter-free and can be implemented very efficiently. The experiments conducted on four popular benchmarks show that our method achieves competitive results on both balanced and imbalanced settings compared to the state-of-the-art methods. The code is released at https://***/mobulan/PSLP. © 2025 Copyright held by the owner/author(s).

关键词： Few-shot learning Transductive learning Message passing label propagation

来源：评论

学校读者我要写书评

暂无评论

Enhancing bone-conducted speech with spectrum similarity metric in adversarial learning

引用

Speech Communication 2025年 170卷

作者： Pan, Yan Zhou, Jian Wang, Huabin Zheng, Wenming Tao, Liang Kwan, Hon Keung Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China Key Laboratory of Child Development and Learning Science Ministry of Education and School of Biological Science and Medical Engineering Southeast University Nanjing210096 China Department of Electrical and Computer Engineering University of Windsor Windsor Canada

Although bone-conducted (BC) speech offers the advantage of being insusceptible to background noise, its transmission path through bone tissue entails not only serious attenuation of high-frequency components but also speech distortion and the loss of unvoiced speech, resulting in a substantial degradation in both speech quality and intelligibility. Existing BC speech enhancement methods focus mainly on approaching high-frequency component restoration but overlook the restoration of missing unvoiced speech and the mitigation of speech distortion, resulting in a noticeable gap in speech quality and intelligibility compared to air-conducted (AC) speech. In this paper, a spectrum-similarity metric based adversarial learning method is proposed for bone-conducted speech enhancement. The acoustic features corresponding to source-excitation and filter-response are disentangled using the WORLD vocoder and mapped to its AC speech counterparts with logarithmic Gaussian normalization and a vocal tract converter, respectively. To reconstruct unvoiced speech from BC speech and decrease the nonlinear speech distortion in BC speech, the vocal tract converter predicts low-dimensional Mel-cepstral coefficients of AC speech using a generator which is supervised by a classification discriminator and a spectrum similarity discriminator. While the classification discriminator is used to distinguish between authentic AC speech and enhanced BC speech, the spectrum similarity discriminator is designed to evaluate the spectrum similarity between enhanced BC speech and its AC counterpart. To evaluate spectrum similarity, the correlation of time–frequency units in spectrum of long duration is captured within the self-attention layer embedded in the spectrum similarity discriminator. Experimental results on various speech datasets show that the proposed method is capable of restoring unvoiced speech segment and diminishing speech distortion, resulting in predicting accurate fine-grained AC spe

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

Improving Event-Level Financial Sentiment Analysis with Retrieval-Augmented Multipath Chain-of-Thought Prompting 12th

Improving Event-Level Financial Sentiment Analysis with Ret...

引用

12th CCF Conference on BigData, BigData 2024

作者： Zhang, Yiming Ao, Xiang Yu, Guoxin He, Qing Henan Institute of Advanced Technology Zhengzhou University Zhengzhou450002 China Beijing100190 China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing100190 China

ISBN: (纸本)9789819610235

Event-level Financial Sentiment Analysis (EFSA) aims to extract all the quintuples containing five sentiment elements from a given financial news text, which has gained prominence as an emerging domain recently. The present study utilizes a 4-hop Chain-of-Thought (CoT) prompting based on LLMs to predict sentiment elements in a fixed order, which neglects the interdependencies among the sentiment elements within a quintuple. Inspired by recent multi-view prompting (MvP) and CoT ideas, we propose a novel framework termed Retrieval-Augmented Multipath Chain-of-Thought (RMP-CoT) that aggregates quintuples generated by LLMs through different reasoning paths, leveraging a retrieval-augmented mechanism. Specifically, RMP-CoT integrates different element orders into CoT prompting to guide LLMs in generating multiple sentiment quintuples through the utilization of retrieval-augmented mechanism, and then selects the most plausible quintuples by voting. To investigate the effectiveness of our framework, we conduct extensive experiments on four benchmark tasks of EFSA. RMP-CoT pushes the state-of-the-art by over 6% F1 on the EFSA task and also performs quite effectively on the other sub-tasks of EFSA. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Chain-of-Thought Event-level Sentiment Analysis Financial Sentiment Analysis

来源：评论

学校读者我要写书评

暂无评论

EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation

arXiv

引用

arXiv 2025年

作者： Zhang, Zihao Chen, Haoran Zhao, Haoyu Lu, Guansong Fu, Yanwei Xu, Hang Wu, Zuxuan Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Noah’s Ark Lab Huawei Canada

Handling complex or nonlinear motion patterns has long posed challenges for video frame interpolation. Although recent advances in diffusion-based methods offer improvements over traditional optical flow-based approaches, they still struggle to generate sharp, temporally consistent frames in scenarios with large motion. To address this limitation, we introduce EDEN, an Enhanced Diffusion for high-quality large-motion vidEo frame iNterpolation. Our approach first utilizes a transformer-based tokenizer to produce refined latent representations of the intermediate frames for diffusion models. We then enhance the diffusion transformer with temporal attention across the process and incorporate a start-end frame difference embedding to guide the generation of dynamic motion. Extensive experiments demonstrate that EDEN achieves state-of-the-art results across popular benchmarks, including nearly a 10% LPIPS reduction on DAVIS and SNU-FILM, and an 8% improvement on DAIN-HD. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Assisted Revocable Cross-Domain Authentication for Vehicular Ad-Hoc Networks

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Li, Ru Cui, Jie Zhang, Jing Wei, Lu Zhong, Hong He, Debiao Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230039 China Anhui University Anhui Engineering Laboratory of IoT Security Technologies Hefei230039 China Wuhan University School of Cyber Science and Engineering 430072 China

With the rapid development of vehicular ad-hoc networks (VANETs) and the increasing diversification of user demands, interactions between different management domains have become more frequent. Identity authentication is an effective way to establish cross-domain trust and secure communication. However, the existing cross-domain authentication schemes of VANETs are limited to the same management or authentication technology for each domain and rely on centralized cross-domain identity management. Even distributed management solutions encounter latency sensitivity, security and privacy challenges. To address these challenges, we propose a blockchain-assisted revocable cross-domain authentication scheme for VANETs. The proposed scheme can establish trust between domain entities by deploying different authentication methods and using distributed management to avoid single-point failures. In addition, the scheme can revoke the identity of malicious vehicles by updating the group public key, thereby ensuring the security and privacy of cross-domain Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication. This design avoids the additional impacts of blockchain technology constraints on the high mobility and real-time requirements of VANETs. Security analysis and performance evaluation show that our scheme can resist more attacks and has better security than other related schemes while also achieving a better balance between communication and computational cost. © 2025 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

High-order diversity feature learning for pedestrian attribute recognition

引用

Neural Networks 2025年 188卷 107463页

作者： Wu, Junyi Huang, Yan Gao, Min Niu, Yuzhen Chen, Yuzhong Wu, Qiang Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fujian Fuzhou China Australian Artificial Intelligence Institute University of Technology Sydney NSW Australia Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fujian Fuzhou China School of Electrical and Data Engineering University of Technology Sydney NSW Australia

Pedestrian attribute recognition (PAR) involves accurately identifying multiple attributes present in pedestrian images. There are two main approaches for PAR: part-based method and attention-based method. The former relies on existing segmentation or region detection methods to localize body parts and learn corresponding attribute-specific feature from the corresponding regions, where the performance heavily depends on the accuracy of body region localization. The latter adopts the embedded attention modules or transformer attention to exploit detailed feature. However, it can focus on certain body regions but often provide coarse attention, failing to capture fine-grained details, the learned feature may also be interfered with by irrelevant information. Meanwhile, these methods overlook the global contextual information. This work argues for replacing coarse attention with detailed attention and integrating it with global contextual feature from ViT to jointly represent attribute-specific regions. To tackle this issue, we propose a High-order Diversity Feature Learning (HDFL) method for PAR based on ViT. We utilize a polynomial predictor to design an Attribute-specific Detailed Feature Exploration (ADFE) module, which can construct the high-order statistics and gain more fine-grained feature. Our ADFE module is a parameter-friendly method that provides flexibility in deciding its utilization during the inference phase. A Soft-redundancy Perception Loss (SPLoss) is proposed to adaptively measure the redundancy between feature of different orders, which can promote diverse characterization of features. Experiments on several PAR datasets show that our method achieves a new state-of-the-art (SOTA) performance. On the most challenging PA100K dataset, our method outperforms previous SOTA by 1.69% and achieves the highest mA of 84.92%. © 2025 The Authors

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

NetPrompt: Neural Network Prompting Enhances Event Extraction in Large Language Models

引用

IEEE Transactions on Big Data 2025年

作者： Mu, Lin Cheng, Yide Shen, Jun Zhang, Yiwen Zhong, Hong School of Computer Science and Technology Anhui University Anhui Hefei230601 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education the Anhui Engineering Laboratory of IoT Security Technologies the School of Computer Science and Technology the Institute of Physical Science and Information Technology Anhui University Hefei230039 China

Event Extraction involves extracting event-related information such as event types and event arguments from context, which has long been tackled through well-designed neural networks or fine-tuned pre-trained language models. These approaches require substantial annotated data for tuning parameters and are resource-intensive. Recently, Prompting strategies with frozen parameters, such as Chain-of-Thought and Self-Consistency, have delivered success in NLP using LLMs by generating intermediate thought steps. However, they suffer from the challenge of error propagation and lack of interaction between different thoughts. In this paper, we propose Neural Network-based Prompting (NetPrompt), a novel network-structured prompting strategy for event extraction. The core idea behind NetPrompt is to imitate the excellent information integration capabilities of neural network structures. Specifically, we first decompose the event extraction problem into diverse intermediate subtasks, and each subtask is represented as a node in different layers of the network, the output of the nodes in the preceding layer is fed into the subsequent layer. Secondly, we propose pruning strategies to adapt the reasoning overhead to different problems. Finally, we have conducted extensive experiments on two widely used event extraction benchmarks to evaluate NetPrompt. The results demonstrated that NetPrompt significantly improved the event extraction performance compared to previous methods. ©2015 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning

arXiv

引用

arXiv 2025年

作者： You, Zuyao Wang, Junke Kong, Lingyu He, Bo Wu, Zuxuan Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China University of Maryland College Park United States

(Image Present) We present Pix2Cap-COCO, the first panoptic pixel-level caption dataset designed to advance fine-grained visual understanding. To achieve this, we carefully design an automated annotation pipeline that prompts GPT-4V to generate pixel-aligned, instance-specific captions for individual objects within images, enabling models to learn more granular relationships between objects and their contexts. This approach results in 167,254 detailed captions, with an average of 22.94 words per caption. Building on Pix2Cap-COCO, we introduce a novel task, panoptic segmentation-captioning, which challenges models to recognize instances in an image and provide detailed descriptions for each simultaneously. To benchmark this task, we design a robust baseline based on X-Decoder. The experimental results demonstrate that Pix2Cap-COCO is a particularly challenging dataset, as it requires models to excel in both fine-grained visual understanding and detailed language generation. Furthermore, we leverage Pix2Cap-COCO for Supervised Fine-Tuning (SFT) on large multimodal models (LMMs) to enhance their performance. For example, training with Pix2Cap-COCO significantly improves the performance of GPT4RoI, yielding gains in CIDEr (+1.4%), ROUGE (+0.4%), and SPICE (+0.5%) on Visual Genome dataset, and strengthens its region understanding ability on the ViP-Bench, with an overall improvement of +5.1%, including notable increases in recognition accuracy (+11.2%) and language generation quality (+22.2%). Code is available at https://***/geshang777/pix2cap. © 2025, CC BY-NC-SA.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Autonomous Path Planning via Sand Cat Swarm Optimization With Multi-Strategy Mechanism for Unmanned Aerial Vehicles in Dynamic Environment

引用

IEEE Internet of Things Journal 2025年

作者： Deng, Wu Feng, Jiayi Zhao, Huimin Civil Aviation University of China College of Electronic Information and Automation Tianjin300300 China Civil Aviation University of China Tianjin Key Lab Intelligent Signal and Image Processing Tianjin300300 China State Key Laboratory of Rail Transit Vehicle System of Southwest Jiaotong University Chengdu610031 China

Unmanned Aerial Vehicles (UAVs) face critical challenges in path planning in dynamic environment. Sand Cat Swarm Optimization (SCSO) algorithm has demonstrated promise in addressing complex optimization challenges. However, SCSO is limited by slow convergence, susceptibility to local optima, and insufficient adaptability. To overcome these shortcomings, an enhanced SCSO with the spiral search, Livy flight, tent chaotic mapping, and adaptive sparrow alert mechanism, namely TSLS-SCSO is developed to propose an autonomous path planning method for UAVs in dynamic environment. In TSLS-SCSO, a new population initialization strategy with tent chaotic mapping is designed to achieve a large dynamic range and coverage capability. Then a new spiral search strategy is designed to broaden the search range in the search phase. And a new Livy flight strategy is employed to enrich the diversity of population in the attacking prey phase. A new sparrow alert mechanism with integrating the sand cat group with the sparrow alert is designed to obtain faster convergence speed and accuracy. The experiment results on CEC 2017 and CEC 2022 show that the TSLS-SCSO obtains higher accuracy and more stable solutions and exhibits better competitiveness. Furthermore, the proposed UAV path planning method successfully found effective paths with an obstacle avoidance effectiveness of 95.5%. The obtained results validate the effectiveness and competitiveness of TSLS-SCSO in UAV path planning in the dynamic environment. © 2014 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Covering Algorithm

引用

Tsinghua Science and Technology 2014年第1期19卷 76-81页

作者： Jie Chen Shu Zhao Yanping Zhang Department of Computer Science and Technology and Key Lab of Intelligent Computing and Signal Processing Anhui University

The concept of deep learning has been applied to many domains, but the definition of a suitable problem depth has not been sufficiently explored. In this study, we propose a new Hierarchical Covering Algorithm （HCA） method to determine the levels of a hierarchical structure based on the Covering Algorithm （CA）. The CA constructs neural networks based on samples＇ own characteristics, and can effectively handle multi-category classification and large-scale data. Further, we abstract characters based on the CA to automatically embody the feature of a deep structure. We apply CA to construct hidden nodes at the lower level, and define a fuzzy equivalence relation R on upper spaces to form a hierarchical architecture based on fuzzy quotient space theory. The covering tree naturally becomes from R. HCA experiments performed on MNIST dataset show that the covering tree embodies the deep architecture of the problem, and the effects of a deep structure are shown to be better than having a single level.

关键词： deep architecture hierarchy fuzzy equivalence relation covering tree MNIST dataset

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：