检索结果-内蒙古大学图书馆

2025 ieee symposium on Trustworthy, Explainable and Responsible computational intelligence, CITREx 2025 2025年

作者： Vellido, Alfredo

来源：评论

学校读者我要写书评

暂无评论

FASTEN: Video Event Localization Based on Audio-Visual Feature Alignment and Multi-Scale Temporal Enhancement

引用

ieee Signal processing Letters 2025年 32卷 2010-2014页

作者： Liu, Yin Wu, Qin Zeng, Mingyong Liu, Yahan Pan, Yuying Jiangnan University School of Artificial Intelligence and Computer Science Wuxi214122 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi214083 China Jiangnan University School of Internet of Things Engineering Wuxi214122 China

The audio-visual event localization task investigates how audio and visual modalities can mutually enhance video event localization. Current methods often rely on single-modality features or lack effective initial alignment between modalities. Although feature pyramids with multiple resolutions are commonly used, the effective and efficient mining of cross-modal and cross-level semantics remains a challenge. In this letter, we propose FASTEN, which stands for audio-visual Feature Alignment and multi-Scale Temporal ENhancement. Novel features derived from an initially aligned multimodal model are introduced and have been shown to be remarkably beneficial. We design an efficient encoder by sharing weights across all pyramid levels and propose a weighted cross-modal attention module to facilitate interaction between modalities. Additionally, global and local pyramids are fused to jointly capture multi-scale temporal dependencies. Evaluated on UnAV-100 and AVE, our method significantly outperforms competing solutions while reducing parameters and computational FLOPs greatly. © 1994-2012 ieee.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Raformer: Redundancy-Aware Transformer for Video Wire Inpainting

引用

ieee TRANSACTIONS ON image processing 2025年 34卷 1795-1809页

作者： Ji, Zhong Su, Yimu Zhang, Yan Hou, Jiacheng Pang, Yanwei Han, Jungong Tianjin Univ Sch Elect & Informat Engn Tianjin Key Lab Brain Inspired Intelligence Techno Tianjin 300072 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings compared to manual frame-by-frame removal. However, wire removal poses greater challenges due to the wires being longer and slimmer than objects typically targeted in general video inpainting tasks, and often intersecting with people and background objects irregularly, which adds complexity to the inpainting process. Recognizing the limitations posed by existing video wire datasets, which are characterized by their small size, poor quality, and limited variety of scenes, we introduce a new VWI dataset with a novel mask generation strategy, namely Wire Removal Video Dataset 2 (WRV2) and Pseudo Wire-Shaped (PWS) Masks. WRV2 dataset comprises over 4,000 videos with an average length of 80 frames, designed to facilitate the development and efficacy of inpainting models. Building upon this, our research proposes the Redundancy-Aware Transformer (Raformer) method that addresses the unique challenges of wire removal in video inpainting. Unlike conventional approaches that indiscriminately process all frame patches, Raformer employs a novel strategy to selectively bypass redundant parts, such as static background segments devoid of valuable information for inpainting. At the core of Raformer is the Redundancy-Aware Attention (RAA) module, which isolates and accentuates essential content through a coarse-grained, window-based attention mechanism. This is complemented by a Soft Feature Alignment (SFA) module, which refines these features and achieves end-to-end feature alignment. Extensive experiments on both the traditional video inpainting datasets and our proposed WRV2 dataset demonstrate that Raformer outperforms other state-of-the-art methods. Our codes and the WRV2 dataset will be made available at: https://***/Suyimu/WRV2.

关键词： Wire Transformers Films Visualization Training TV Production Manuals Context modeling computational modeling Video wire inpainting video inpainting video transformer redundant elimination

来源：评论

学校读者我要写书评

暂无评论

SFma-Unet: A Mamba-Based Spatial-Frequency Fusion Network for Medical image Segmentation

SFma-Unet: A Mamba-Based Spatial-Frequency Fusion Network fo...

引用

2025 ieee International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Liu, Zhanpeng Zhang, Yuqiang Wang, Bin Yang, Yang Cai, Lin Institute of Artificial Intelligence Xiamen University Xiamen China School of Artificial Intelligence Hubei University Wuhan China School of Life Sciences Hubei University Wuhan China

ISBN: (纸本)9798350368741

Recently, Mamba-based methods have gained popularity in medical image segmentation due to their ability to model long-range dependencies with linear computational complexity. However, current segmentation methods often face challenges such as low contrast, blurred boundaries, and unclear backgrounds in medical images. Considering that perceived objects and features exhibit greater discriminative power in the frequency domain, we propose a novel mamba-based spatial and frequency domain feature fusion network, SFMa-Unet, to address these challenges. Specifically, we designed the Spatial-Frequency Interaction (SFI) module, which leverages the powerful modeling capabilities of Mamba to fuse spatial and frequency domain features, enhancing feature representation. Additionally, we developed a Mamba-based multi-scale feature channel fusion (MFCF) bridge to capture local and global dependencies across different feature scales, further improving the model's representational capacity. We conduct comprehensive experiments on the ISIC17 and ISIC18 public datasets. Experimental results demonstrate the effectiveness and robustness of SFMa-Unet. Codes are available at https://***/RainCh-zyq/SFma-Unet. © 2025 ieee.

关键词： Medical image Segmentation spatial-frequency fusion Vision State Space Models

来源：评论

学校读者我要写书评

暂无评论

Scale-Aware Crowd Counting Network With Annotation Error Modeling

引用

ieee TRANSACTIONS ON image processing 2025年 34卷 2750-2764页

作者： Hsieh, Yi-Kuan Hsieh, Jun-Wei Li, Xin Zhang, Yu-Ming Tseng, Yu-Chee Chang, Ming-Ching Natl Yang Ming Chiao Tung Univ Coll Artificial Intelligence Hsinchu 30010 Taiwan SUNY Albany Comp Sci Dept Albany NY 12222 USA Natl Cent Univ Comp Sci Informat Engn Dept Taoyuan 32001 Taiwan

Traditional crowd-counting networks suffer from information loss when feature maps are reduced by pooling layers, leading to inaccuracies in counting crowds at a distance. Existing methods often assume correct annotations during training, disregarding the impact of noisy annotations, especially in crowded scenes. Furthermore, using a fixed Gaussian density model does not account for the varying pixel distribution of the camera distance. To overcome these challenges, we propose a Scale-Aware Crowd Counting Network (SACC-Net) that introduces a scale-aware loss function with error-compensation capabilities of noisy annotations. For the first time, we simultaneously model labeling errors (mean) and scale variations (variance) by spatially varying Gaussian distributions to produce fine-grained density maps for crowd counting. Furthermore, the proposed scale-aware Gaussian density model can be dynamically approximated with a low-rank approximation, leading to improved convergence efficiency with comparable accuracy. To create a smoother scale-aware feature space, this paper proposes a novel Synthetic Fusion Module (SFM) and an Intra-block Fusion Module (IFM) to generate fine-grained heat maps for better crowd counting. The lightweight version of our model, named SACC-LW, enhances the computational efficiency while retaining accuracy. The superiority and generalization properties of scale-aware loss function are extensively evaluated for different backbone architectures and performance metrics on six public datasets: UCF-QNRF, UCF CC 50, NWPU, ShanghaiTech A, ShanghaiTech B, and JHU. Experimental results also demonstrate that SACC-Net outperforms all state-of-the-art methods, validating its effectiveness in achieving superior crowd-counting accuracy. The source code is available at https://***/Naughty725.

关键词： Annotations Head Accuracy computational modeling Training Convolution Computer architecture Cameras Interpolation Feature extraction Annotation error modeling scale-aware crowd counting network (SACC-Net) density map generation low-rank approximation

来源：评论

学校读者我要写书评

暂无评论

Can LLMs Identify Event Causality More Accurately through Debate? A Systematic Assessment of LLMs' Factuality and Reasoning

Can LLMs Identify Event Causality More Accurately through De...

引用

2025 ieee symposium on Trustworthy, Explainable and Responsible computational intelligence, CITREx 2025

作者： Zhao, Yiheng Yan, Jun Montréal Canada

ISBN: (纸本)9798331520151

Event Causality Identification (ECI) aims to determine both the existence and direction of a causal relation between two events. Given the remarkable capabilities of large language models (LLMs) in various natural language processing (NLP) tasks, several studies have explored their performance in the ECI task. However, applying LLMs to the ECI task carries risks, as their generations often contain factual and reasoning errors. Due to the powerful capabilities of debate, some studies have leveraged it to mitigate these issues. However, debate can sometimes lead LLMs to generate even more errors, suggesting that debate may not effectively enhance the quality of LLMs' generations. Therefore, we propose a novel debate framework for LLMs in the ECI task to validate whether LLMs can identify event causality more accurately through debate. As LLMs' generations often mix correct information with factual and reasoning errors, binary judgments on their generations may not fully reveal their potential in real-world use cases. And factual errors reflect flaws in the factuality of LLMs' generations, while reasoning errors reveal weaknesses in their reasoning abilities. Therefore, we propose a Fine-Grained Factuality Score (FGFS) to better evaluate the factuality of LLMs' generations and a Fine-Grained Reasoning Score (FGRS) to assess their reasoning abilities more effectively. Additionally, we redefine factuality and correct reasoning for LLMs' generations at a fine-grained level to ensure more precise evaluation results for our metrics. Finally, considering the lack of automated evaluation for FGFS and FGRS and the time-consuming and costly nature of human evaluation, we propose automated methods for both proposed metrics and validate their superior performance by human expertise. © 2025 ieee.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Pre-Training a Graph Recurrent Network for Text Understanding

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE intelligence 2025年第5期47卷 4061-4074页

作者： Wang, Yile Yang, Linyi Teng, Zhiyang Zhou, Ming Zhang, Yue Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Westlake Univ Sch Engn Hangzhou 310024 Peoples R China ByteDance Singapore 048583 Singapore Langboat Ltd Beijing 100080 Peoples R China

Transformer-based pre-trained models have gained much advance in recent years, Transformer architecture also becomes one of the most important backbones in natural language processing. Recent works show that the attention mechanism inside Transformer may not be necessary, and Transformer alternatives such as convolutional neural networks, multi-layer perceptron, and state space model have also been investigated. Transformer-based models have two main limitations: First, they have quadratic time complexity due to the full attention mechanism, which leads to high computational costs. Second, they rely on representation of a special token such as [CLS] to encode entire text, which limits its sentence-level expressiveness. In this paper, we consider a graph recurrent network with linear time complexity for language model pre-training, which builds a graph structure for each sequence with local token-level communications, together with a sentence-level representation detached from other normal tokens. On both English and Chinese text understanding tasks, our model can achieve comparable performance to existing pre-trained models while also achieving higher inference efficiency. Furthermore, we discovered that the representations generated by our model are more diverse and uniform compared to that of Transformer, which alleviates the problems in existing pre-trained models such as representation degradation.

关键词： Transformers computational modeling Computer architecture Complexity theory Attention mechanisms Encoding Context modeling Bidirectional long short term memory Bidirectional control Training Graph recurrent network pre-trained language model text understanding transformer

来源：评论

学校读者我要写书评

暂无评论

Language-Enhanced Dual-Level Contrastive Learning Network for Open-Set Hyperspectral image Classification

引用

ieee TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Qin, Boao Feng, Shou Zhao, Chunhui Li, Wei Tao, Ran Zhou, Jun Harbin Engn Univ Minist Ind & Informat Technol Coll Informat & Commun Engn Harbin 150001 Peoples R China Harbin Engn Univ Minist Ind & Informat Technol Key Lab Adv Marine Commun & Informat Technol Harbin 150001 Peoples R China Minist Nat Resources Technol Innovat Ctr South China Sea Remote Sensing Guangzhou 510300 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Griffith Univ Sch Informat & Commun Technol Nathan Qld 4111 Australia

In recent years, language-supervised vision models have demonstrated impressive potential in learning open-world concepts. Some research has introduced this learning paradigm to the hyperspectral image (HSI) processing domain;however, there has been limited work integrating textual information into the hyperspectral open-set recognition task. To fill this gap, we leverage textual supervision information in open-set HSI classification (HSIC) and propose a language-enhanced dual-level contrastive learning network (LDCLNet). Specifically, we introduce a linguistic mode with prior knowledge as a supervised signal to enhance the metric distances between closed-set samples and provide supplementary semantic information for open-set samples. Second, a dual-level visual-language (V-L) contrastive learning (CL) approach, which can align visual and language embeddings separately at the instance level and manifold level, is proposed to establish a more accurate link between visual and language representations. Finally, a distance-refined open-set recognition method is proposed, which aims to effectively discover unknown class samples during testing by refining predictions of known and unknown classes. Extensive experiments and analysis on three public HSI datasets validate the effectiveness of LDCLNet.

关键词： Visualization Training Testing Feature extraction Hyperspectral imaging Contrastive learning Artificial intelligence Semantics image classification computational modeling Dual-level contrastive learning (CL) hyperspectral image (HSI) language-supervised vision model open-set classification

来源：评论

学校读者我要写书评

暂无评论

RSBEV-Mamba: 3-D BEV Sequence Modeling for Multiview Remote Sensing Scene Segmentation

引用

ieee TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Lin, Baihong Zou, Zhengxia Shi, Zhenwei Beihang Univ Sch Astronaut Dept Aerosp Intelligent Sci & Technol State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China

Multiview collaborative perception has been demonstrated to be highly effective in extracting 3-D information from remote sensing scenes by remote sensing bird's-eye-view (RSBEV). However, inherent depth uncertainty in purely visual methods limits view fusion accuracy, and high computational complexity makes it challenging to model long sequences efficiently. To address these issues, we reformulate the BEV segmentation problem as a 3-D sequence modeling task and propose RSBEV-Mamba, a novel framework comprising a 3-D BEV module, a 3-D VMamba module, and a dense BEV contrastive learning module. The 3-D BEV module projects multiview 2-D image features into 3-D world coordinates, thus establishing a foundation for accurate spatial representation. The 3-D VMamba module, based on state-space models (SSMs), optimizes the processing of densely projected features with linear computational complexity in global 3-D spatial modeling. It incorporates a 3-D selective scanning strategy (SS3D) block with 16 scanning strategies, transforming previously ignored projections at different heights into valid 3-D sequences and enriching the contextual depth and precision of BEV encoding. By employing a contrastive learning strategy with the CLIP model, we align BEV and ground truth (GT) features within the same dimensional framework, ensuring spatial integrity after side-view projection. Our approach achieves a 4% improvement mIoU, thus reaching a score of 0.7368 on LEVIR-MDS and surpassing previous state-of-the-art methods. This establishes the 3-D VMamba module as a general model for 3-D perception tasks and sets a new benchmark in remote sensing technology.

关键词： Three-dimensional displays Solid modeling Context modeling computational modeling Remote sensing Predictive models Feature extraction Contrastive learning Accuracy Transformers Bird's-eye-view (BEV) representation multiview collaborative segmentation remote sensing semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven computational intelligence for Leaf Disease Identification for Smart Agriculture 3

Deep Learning-Driven Computational Intelligence for Leaf Dis...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Phani Prasad, J. Jadala, Vijaya Chandra Department of CS&AI School of Computer Science and Artificial Intelligence SR University Warangal506371 India

ISBN: (纸本)9798331527549

In the context of smart farming, Artificial intelligence (AI) plays a crucial role in enhancing agricultural practices, from soil management to crop yield optimization. By leveraging deep learning and image processing techniques, AI can address various challenges across different agricultural sectors, particularly in detecting and mitigating plant diseases. This paper focuses on the use of these technologies for leaf disease detection to minimize crop loss. Deep learning and image processing are key components in identifying, classifying, and monitoring plant diseases. The study reviews various types of leaf diseases and examines the effectiveness of existing algorithms for detection. To improve performance, an algorithm based on ensemble learning methods is proposed. Experimental investigation is conducted on tomato leaf diseases, followed by a comparative analysis of the results. The proposed AI-driven system enables early disease detection, facilitating timely monitoring and intervention, ultimately reducing crop loss and improving overall crop health through proactive management and precautionary measures. © 2025 ieee.

关键词： Contrastive Learning

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：