检索结果-内蒙古大学图书馆

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

作者： Uesugi, Kenta Saito, Naoki Maeda, Keisuke Ogawa, Takahiro Haseyama, Miki Hokkaido University Japan

ISBN: (纸本)9798350368741

Composed image Retrieval (CIR) provides an effective way to manage and access large-scale visual data. Construction of the CIR model utilizes triplets that consist of a reference image, modification text describing desired changes, and a target image that reflects these changes. For effectively training CIR models, extensive manual annotation to construct high-quality training datasets, which can be time-consuming and labor-intensive, is required. To deal with this problem, this paper proposes a novel triplet synthesis method by leveraging counterfactual image generation. By controlling visual feature modifications via counterfactual image generation, our approach automatically generates diverse training triplets without any manual intervention. This approach facilitates the creation of larger and more expressive datasets, leading to the improvement of CIR model's performance. © 2025 ieee.

关键词： Composed image retrieval counterfactual image generation triplet synthesis

来源：评论

学校读者我要写书评

暂无评论

EvaSR: Rethinking Efficient visual Attention Design for image Super-Resolution

EvaSR: Rethinking Efficient Visual Attention Design for Imag...

引用

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

作者： Wu, Zhijian Zhang, Chenhan Huang, Dingjiang School of Data Science and Engineering East China Normal University Shanghai China Trenton Collegiate Institute ON Canada

ISBN: (纸本)9798350368741

Due to the advantages of long-range modeling via the self-attention mechanism, Transformer has taken various vision tasks by storm, including image super-resolution (SR). In this study, we reveal that the convolutional neural network (CNN) with proper visual attention is a more simple and effective paradigm than Transformer in image SR tasks. We reexamine the successful SR models and discover several key characteristics that contribute to accurate image reconstruction. Built on this recipe, we propose a pure CNN-based SR network using efficient visual attention, dubbed EvaSR. Benefiting from the carefully designed visual attention, our EvaSR can favorably capture both local structure and long-range dependencies, and achieve adaptivity in spatial and channel dimensions while retaining the simplicity and efficiency of CNNs. The experimental results demonstrate that our EvaSR achieves state-of-the-art performance among the existing efficient SR methods. Especially, the tiny version of EvaSR needs 21.4% and 15.2% parameters of IMDN and SMSR with better performance. © 2025 ieee.

关键词： Efficient Network Gated Linear Unit image Super-resolution Transformer

来源：评论

学校读者我要写书评

暂无评论

Computer graphics and image processing techniques based on visual communication design 4

Computer graphics and image processing techniques based on v...

引用

4th International conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Chen, Zhaoguo College of Arts Shandong Agricultural Engineering University Shandong Province Jinan250103 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

To fully harness the capabilities of computer graphics and image processing technologies and elevate the quality of visual communication design, this paper presents a comprehensive suite of innovative methodologies. Firstly, the fundamental principles of primary colors are utilized to formulate a series of vector functions, facilitating the precise calculation of error distances and the establishment of an intricate visual communication zoning model. Subsequently, through the exhaustive extraction of pertinent feature information from graphics and images, we achieve the scientific encoding of coefficient-constrained features and determine the corresponding hyperplanes to acquire the relevant parameters for visual communication. Eventually, the implementation of advanced design image expression algorithms markedly enhances the effectiveness of visual communication image representation. The empirical findings reveal that these visual communication design methods exhibit remarkable reliability and feasibility, effectively boosting image recognition accuracy across four distinct image categories with varying levels of complexity, thereby yielding exceptional visual communication outcomes. © 2025 SPIE.

关键词： Design visual communications visualization Computer graphics image processing image storage Color image segmentation image enhancement

来源：评论

学校读者我要写书评

暂无评论

Hybrid Feature Approach for Enhancing Zero-Shot image Classification 4th

Hybrid Feature Approach for Enhancing Zero-Shot Image Classi...

引用

4th International conference on Artificial Intelligence and Knowledge processing

作者： Khanam, Shaista Sonar, Poonam N. Mumbai Univ Mumbai Maharashtra India

ISBN: (纸本)9783031734762;9783031734779

Zero-shot learning (ZSL) directs the challenge of classifying unseen test images without explicit training on those samples. ZSL can identify and classify unlabeled images available in abundance by learning from visual and semantic embedding vectors (feature vectors). Information-enriched visual features extracted from images play a crucial role in ZSL. This paper proposes a hybrid feature approach that integrates low-level (LL), and high-level (HL) features extracted from images. Gray Level Co-occurrence Matrix (GLCM) and Gabor features are employed to obtain LL texture features, while HL features are derived from the ResNet-50 model, renowned for capturing complex hierarchical representations. These hybrid visual features are then mapped with semantic features using linear mapping, where the semantic features are embedding vectors of labels generated by the fastText model. Experiments on the AWA2 and SUN datasets are conducted in a bid to evaluate the proposed approach's effectiveness. The hybrid feature approach has demonstrated enhanced quality in zero-shot image classification, effectively classifying images that the model has not seen during training.

关键词： Hybrid feature Zero-shot image classification GLCM

来源：评论

学校读者我要写书评

暂无评论

Infrared and Visible image Fusion with Hierarchical Human Perception

Infrared and Visible Image Fusion with Hierarchical Human Pe...

引用

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

作者： Yang, Guang Li, Jie Liu, Xin Zhong, Zhusi Gao, Xinbo School of Electronic Engineering Xidian University Xi'an China Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9798350368741

image fusion combines images from multiple domains into one image, containing complementary information from source domains. Existing methods take pixel intensity, texture and high-level vision task information as the standards to determine preservation of information, lacking enhancement for human perception. We introduce an image fusion method, Hierarchical Perception Fusion (HPFusion), which leverages Large Vision-Language Model to incorporate hierarchical human semantic priors, preserving complementary information that satisfies human visual system. We propose multiple questions that humans focus on when viewing an image pair, and answers are generated via the Large Vision-Language Model according to images. The texts of answers are encoded into the fusion network, and the optimization also aims to guide the human semantic distribution of the fused image more similarly to source images, exploring complementary information within the human perception domain. Extensive experiments demonstrate our HPFusoin can achieve high-quality fusion results both for information preservation and human visual enhancement. Our code is available at https://***/SSyangguang/HPFusion. © 2025 ieee.

关键词： Human Perception image Fusion Large Vision-Language Model

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning-Based Beam Prediction Scheme for Vision-Aided mmWave Wireless communications

引用

ieee Internet of Things Journal 2025年第11期12卷 17869-17879页

作者： Wang, Heng Yang, Dihan Xie, Xin The Key Laboratory of Industrial Internet of Things and Networked Control Chongqing University of Posts and Telecommunications Chongqing400065 China

Millimeter wave (mmWave) wireless communications are significant technologies that support Internet of Things (IoT) systems to achieve fast and stable data transmission, and the guarantee of its communication quality usually depends on accurate beam prediction. Due to the advantage of not relying on channel state information, beam prediction schemes using visual data and artificial intelligence become popular. Most of the current vision-aided beam prediction schemes directly predict the index of the optimal beam in the codebook. However, these methods are only applicable to certain codebooks and have limited generalization and scalability. To address the issues, we propose a vision-aided beam prediction scheme based on deep reinforcement learning (DRL). The scheme takes the original image as input and extracts the position and velocity of the user through the object detection algorithm. Subsequently, combined with the current state of the base station, it outputs a continuous angle value and finally matches it with the beam index in the codebook. Furthermore, we integrate the attention mechanism into the actor network of the deep deterministic policy gradient (DDPG) and propose a scheme of DDPG with attention mechanism (DDPG-A), which can perform differential processing on features, thereby enhancing algorithmic performance. The simulation test utilizing real datasets demonstrates that the proposed scheme has good generalization and scalability while considerably reducing the beam training overheads. © 2014 ieee.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deformable Attention-Based Edge-Aware Network for Single image Super-Resolution

Deformable Attention-Based Edge-Aware Network for Single Ima...

引用

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

作者： Zhang, Ju Zhong, Baojiang Ma, Kai-Kuang School of Computer Science and Technology Soochow University Suzhou China College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9798350368741

Accurately reconstructing object edges is a key challenge in single image super-resolution (SISR), as it greatly influences our visual perception of image quality. To address this fundamental issue, we propose a novel SISR approach named the deformable attention-based edge-aware (DAE) network. The DAE network features a deformable attention block that dynamically adjusts attention weights to align with edge structures, thereby improving edge awareness and reconstruction quality. Moreover, our network incorporates a multi-patterns window block that captures fine-grained edge details and enhances information flow across network layers. This combination results in visually superior SISR outputs. Extensive experiments and comparisons with the state-of-the-art methods demonstrate that our DAE network excels in both quantitative metrics and visual quality. © 2025 ieee.

关键词： deformable attention edge-aware single image super-resolution window attention

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multimodal image Fusion: A Novel Approach with Nystrom Attention Mechanisms in Transformer Models

Optimizing Multimodal Image Fusion: A Novel Approach with Ny...

引用

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

作者： Zeng, Yuqin Wen, Ze Fan, Shuqian Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China Chongqing School University of Chinese Academy of Sciences Chongqing China Chongqing China

ISBN: (纸本)9798350368741

This work proposed a new model based on transformers for multimodal image fusion, with explicit attention paid to fusing infrared and visible images toward enhanced detail and information content. This method, which incorporates Nystrom attention and skip connections, optimizes the fusion process so that important features of both modalities are preserved. Traditional models find it hard to keep details in the content and introduce artifacts. On the contrary, this model can efficiently cope with these challenges, as it makes use of an attention mechanism that is computationally highly effective. This will efficiently fuse large-scale image data and may be useful in those fields where very detailed and comprehensive visual information is demanded. The detailed evaluations prove that our model has superior performance over the current state-of-the-art methods in texture detail preservation, thermal differentiation, and overall image quality, which possesses great potential for advanced imaging applications. © 2025 ieee.

关键词： attention mechanism image fusion multimodal imaging transformer

来源：评论

学校读者我要写书评

暂无评论

TriFormer: Triple Branch Heterogeneous Transformers for UHD image Restoration

TriFormer: Triple Branch Heterogeneous Transformers for UHD ...

引用

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

作者： Ma, Xinchen Lu, Yue School of Communication and Electronic Engineering East China Normal University Shanghai China

ISBN: (纸本)9798350368741

Ultra-high-definition (UHD) image restoration is becoming a critical research area due to the increasing demand for high-quality visual content in various applications, including autonomous driving, remote sensing, digital entertainment, etc. However, UHD image restoration tasks present notable challenges, including the significant computational burden posed by the large image size scale, the difficulty in preserving fine details and textures, and the increased susceptibility to noise and artifacts during the restoration process. In this paper, we propose a novel triple-branched optimized heterogeneous transformer for UHD image restoration, named TriFormer. Specifically, our method embeds a high-resolution CNN branch for high-frequency features, a low-resolution pixel-wise attention branch for low-frequency features, and a channel-wise attention branch for feature fusion. We perform experiments across two UHD image restoration tasks: enhancing low-light images and deblurring. Results demonstrate that our model outperforms state-of-the-art approaches both quantitatively and qualitatively. The code will be made available at https://***/Chloemxxxxc/TRIFORMER. © 2025 ieee.

关键词： image restoration transformer Ultra-high-definition(UHD)

来源：评论

学校读者我要写书评

暂无评论

Filtering Methods, Assessment Criteria, and Prospects for image Denoising

Filtering Methods, Assessment Criteria, and Prospects for Im...

引用

2025 ieee International Students' conference on Electrical, Electronics and Computer Science, SCEECS 2025

作者： Wandile, Piyush S Singh Kirar, Bhupendra Kirar, Seema Indian Institute of Information Technology Computer Science and Engineering Bhopal India Indian Institute of Information Technology Electronics and Communications Engineering Bhopal India Bansal Institute of Science and Technology Electronics and Communications Engineering Bhopal India

ISBN: (纸本)9798331529833

image denoising is a crucial step in image acquisition and processing that helps improve the image quality by removing the unwanted noise. In this paper Gaussian and median filters are used as denoiser and performance is evaluated using some of the key metrics like Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Feature Similarity Index Measure (FSIM), Structural Similarity Index Measure (SSIM), Mean Absolute Error (MAE), and Correlation Coefficient. A denoiser with low MSE, high PSNR, values of 1 for SSIM, FSIM, and Correlation Coefficient. Reported results are better in comparison to existing for better image quality. © 2025 ieee.

关键词： Wiener filtering

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：