发布求助
文献互助 智能选刊 最新文献

IEEE Signal Processing Letters最新文献

筛选
英文 中文
Gaussian Splatting Based on Mamba Interaction for Arbitrary Scale Image Super Resolution 基于曼巴交互作用的任意尺度图像超分辨率高斯溅射
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-26 DOI: 10.1109/LSP.2025.3615079
Yuning Liu;Yongtao Ma
{"title":"Gaussian Splatting Based on Mamba Interaction for Arbitrary Scale Image Super Resolution","authors":"Yuning Liu;Yongtao Ma","doi":"10.1109/LSP.2025.3615079","DOIUrl":"https://doi.org/10.1109/LSP.2025.3615079","url":null,"abstract":"Recently Gaussian Splatting has shown great potential in arbitrary scale super resolution over implicit neural representation with continuous feature expression ability and high rendering speed. But the Gaussian expression ability is constrained by fixed positions, the global Gaussian interaction based on self-attention improves the accuracy of Gaussian parameters but leads to large computational overhead. To address these problems, we propose GMSR, which introduces a set of Gaussian embeddings and initializes them based on window attention and encoded features, allowing them to interact locally and globally respectively. Specifically, based on the state space models, we learn the long-range dependencies of Gaussian embeddings within and across the windows, using the Hilbert scanning mechanism to maintain local continuity. To further emphasize key information, we calibrate the weights of embedded channels based on attention mechanism. Experimental results on three public datasets demonstrate that GMSR has achieved significant improvements in reconstruction effects and computational efficiency.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3824-3828"},"PeriodicalIF":3.9,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Improving the Convolutional Formulation for Efficient Computations of Short-Length DHT 改进卷积公式以实现短长度DHT的高效计算
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-25 DOI: 10.1109/LSP.2025.3614496
R. Rykmas;I. Prots’ko
{"title":"Improving the Convolutional Formulation for Efficient Computations of Short-Length DHT","authors":"R. Rykmas;I. Prots’ko","doi":"10.1109/LSP.2025.3614496","DOIUrl":"https://doi.org/10.1109/LSP.2025.3614496","url":null,"abstract":"The implementation of the fast Hartley transform (FHT) of arbitrary sizes on various computer platforms is in demand in many application areas. The synthesis of fast algorithms for the discrete Hartley transform (DHT) based on cyclic convolutions requires the formation and improvement of the block-cyclic structure of the basis to reduce computational complexity. A compact description of the block structure of the basis of the DHT in the form of a cyclic decomposition of substitution is considered. The synthesis of algorithms is illustrated through the example of the convolutional formation of the improved block-cyclic structure of a 14-point DHT. Two different improving block-cyclic structures of the 21-point DHT and their average time of execution are represented. The analysis of block structures for the DHT, in which each cyclic block is processed either independently or as part of a larger cyclic structure, leads to a more efficient implementation of the transform. The advantage in computation speed for short FHTs on modern computer platforms is confirmed by the obtained results in comparison with the FFTW library.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3819-3823"},"PeriodicalIF":3.9,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CLIP-DQA V2: Exploring CLIP for Dehazed Image Quality Assessment From a Fragment-Level Perspective CLIP- dqa V2：从片段级的角度探索CLIP去模糊图像质量评估
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-25 DOI: 10.1109/LSP.2025.3615082
Yirui Zeng;Jun Fu;Guanghui Yue;Hantao Liu;Wei Zhou
{"title":"CLIP-DQA V2: Exploring CLIP for Dehazed Image Quality Assessment From a Fragment-Level Perspective","authors":"Yirui Zeng;Jun Fu;Guanghui Yue;Hantao Liu;Wei Zhou","doi":"10.1109/LSP.2025.3615082","DOIUrl":"https://doi.org/10.1109/LSP.2025.3615082","url":null,"abstract":"Contrastive Language-Image Pretraining (CLIP) models have demonstrated strong performance in blind dehazed image quality assessment (DQA), yet their efficiency remains a concern. In this letter, we introduce CLIP-DQA V2, which explores CLIP for efficient blind DQA from a fragment-level perspective. To effectively map fragments sampled from dehazed images to quality scores, CLIP-DQA V2 integrates two key components: (1) multi-modal prompt learning, which jointly optimizes CLIP’s image and text encoders for better alignment between fragments and quality-related text descriptions, and (2) a semantic consistency loss that alleviates the semantic degradation caused by fragment sampling. Experiments on two widely used benchmark datasets show that CLIP-DQA V2 reduces computational cost by nearly 45% compared to previous methods, while delivering more accurate quality predictions.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3829-3833"},"PeriodicalIF":3.9,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DPARNet-RSE: Toward Angular Region-Customizable Speech Extraction 面向角度区域自定义语音提取
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-22 DOI: 10.1109/LSP.2025.3613271
Yi Yang;Caigen Zhou
{"title":"DPARNet-RSE: Toward Angular Region-Customizable Speech Extraction","authors":"Yi Yang;Caigen Zhou","doi":"10.1109/LSP.2025.3613271","DOIUrl":"https://doi.org/10.1109/LSP.2025.3613271","url":null,"abstract":"Most existing angular region-wise speech extraction methods face two critical limitations: inflexibility when handling different region boundaries, and performance degradation due to the varying numbers of speakers within the target regions. To address these issues, we adapt our recently proposed DPARNet, a lightweight dual-path attention and recurrent network for speech separation, into DPARNet-RSE, to perform angular region-customizable speech extraction. The key innovations include: (1) a boundary-conditioned attention module that encodes target boundaries into dynamic queries for robust region modeling; (2) a curriculum learning-based training approach that stabilizes convergence by progressively introducing data diversity; (3) a silence probability prediction module that directly triggers silent outputs when no target speaker is detected, effectively reducing speech and noise residuals in zero-target cases. The experimental results demonstrate its superior performance, robustness, generalization capability, and scalability in complex scenarios.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3779-3783"},"PeriodicalIF":3.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fuzzy Inference System-Enhanced Adaptive Sliding Innovation Filter for Non-Cooperative Target Tracking 非合作目标跟踪的模糊推理系统增强自适应滑动创新滤波器
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-22 DOI: 10.1109/LSP.2025.3613274
Yunyi Yang;Guoguang Wen;Yidi Wang;Yunhe Meng;Tingwen Huang
{"title":"Fuzzy Inference System-Enhanced Adaptive Sliding Innovation Filter for Non-Cooperative Target Tracking","authors":"Yunyi Yang;Guoguang Wen;Yidi Wang;Yunhe Meng;Tingwen Huang","doi":"10.1109/LSP.2025.3613274","DOIUrl":"https://doi.org/10.1109/LSP.2025.3613274","url":null,"abstract":"This letter proposes a novel adaptive sliding innovation filter (SIF) enhanced by a fuzzy inferencesystem (FIS), which aims to improve estimation robustness for non-cooperative target tracking. The main contributions include: first, an FIS-enhanced adaptive adjustment scheme for the sliding boundary layer (SBL) is proposed, which improves the tracking performance in dynamic and uncertain environments; second, the SBL width is designed as a vector, which better adapts to measurements with different characteristics and magnitudes; third, an innovation-related indicator is designed as the input of the FIS, which is capable of detecting faults without distributional assumptions, thereby allowing the proposed algorithm to handle system uncertainties effectively. Through the adaptive parameter adjustment of the proposed algorithm, the tracking performance is improved under uncertain conditions, such as maneuver-induced model mismatches and noise uncertainties. An experiment on non-cooperative orbital target tracking is provided to validate the theoretical advancements, demonstrating the proposed filter’s superior robustness and convergence speed compared to both conventional SIF and unscented Kalman filter (UKF) algorithms.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3784-3788"},"PeriodicalIF":3.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Nonlocal Tensor Wheel Decomposition for Hyperspectral Image Super-Resolution 高光谱图像超分辨率的非局部张量轮分解
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-22 DOI: 10.1109/LSP.2025.3612748
Hui-Lin Li;Ting-Zhu Huang;Liang-Jian Deng;Ting Xu
{"title":"Nonlocal Tensor Wheel Decomposition for Hyperspectral Image Super-Resolution","authors":"Hui-Lin Li;Ting-Zhu Huang;Liang-Jian Deng;Ting Xu","doi":"10.1109/LSP.2025.3612748","DOIUrl":"https://doi.org/10.1109/LSP.2025.3612748","url":null,"abstract":"Fusing paired multispectral image (MSI) with hyperspectral image (HSI) has emerged as a prevalent scheme for HSI super-resolution (HSR). We propose a nonlocal tensor wheel decomposition (NLTW) approach for HSR. By introducing TW decomposition for nonlocal group representation, the proposed NLTW model effectively explores the nonlocal self-similarity prior. Compared with existing nonlocal tensor decompositions for HSR, our model leverages higher-order representations and establishes connections among non-adjacent factors, exhibiting more expressive characterization capability. Moreover, we develop an efficient algorithm based on the alternating direction multipliers method (ADMM) and proximal alternating minimization (PAM), with Bayesian optimization strategy for automated hyperparameter tuning. Experiments on three datasets demonstrate the superiority of our model over state-of-the-art methods","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3799-3803"},"PeriodicalIF":3.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Essentially Bivariate Nonlinear Units for Complex-Valued Adaptive Filter 复值自适应滤波器的二元非线性单元
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-22 DOI: 10.1109/LSP.2025.3612687
Changan Liu;Zhibin Yan
{"title":"Essentially Bivariate Nonlinear Units for Complex-Valued Adaptive Filter","authors":"Changan Liu;Zhibin Yan","doi":"10.1109/LSP.2025.3612687","DOIUrl":"https://doi.org/10.1109/LSP.2025.3612687","url":null,"abstract":"This letter proposes a novel complex-valued nonlinear function (CVNF) approximation method for adaptive nonlinear filter, which is used to digitally cancel the weak nonlinearity, a commonly observed feature in most communication systems. The method approximates CVNF through a two-dimensional piecewise linear surface (2D-PLS), which is linear combination of nonlinear basis functions essentially of two variables. The finding is that such basis functions of two variables have stronger ability to express nonlinearity than the tensor product of two functions of one variable. Experiment using data collected from the transceiver in wireless communication show that the proposed method outperforms the other two methods dealing with nonlinear system identification on complex-valued signals in approximating accuracy as well as computational complexity.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3750-3753"},"PeriodicalIF":3.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CoughSlowFast: Cough Recognition With Audio and Video Signal Fusion 咳嗽慢速：咳嗽识别与音频和视频信号融合
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-22 DOI: 10.1109/LSP.2025.3612351
Mingke Feng;Guangtao Zhai;Xiao-Ping Zhang;Menghan Hu
{"title":"CoughSlowFast: Cough Recognition With Audio and Video Signal Fusion","authors":"Mingke Feng;Guangtao Zhai;Xiao-Ping Zhang;Menghan Hu","doi":"10.1109/LSP.2025.3612351","DOIUrl":"https://doi.org/10.1109/LSP.2025.3612351","url":null,"abstract":"The recognition of coughs plays a critical role in the diagnosis of respiratory diseases and the monitoring of public health. Traditional audio-based methods are highly susceptible to noise and lack spatial awareness, while visual methods struggle to recognize low-amplitude cough motions and are prone to confusion with other behaviors. To address these limitations, this letter proposes a multimodal cough recognition model, CoughSlowFast, which extends the SlowFast architecture by introducing a high-sampling-rate audio branch and designing a peak-aware masking mechanism to enhance the model responsiveness to key frames. A temporal fusion strategy is employed to effectively integrate low-frequency structural motion, high-frequency dynamic variations, and transient audio features. Evaluated on a self-constructed multimodal cough dataset containing 9,254 synchronized audio–video samples, CoughSlowFast achieves an accuracy of 95.91% and an F1-score of 0.9148 under complex environmental conditions, significantly outperforming mainstream models including CSN, SlowFast, VideoSwin, Neural Cough Counter, and AVE, thus demonstrating strong potential for real-world deployment.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3774-3778"},"PeriodicalIF":3.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mitigating Steganalysis Collapse Under Re-Compression via Pre-Transmission Guidance 通过预传输引导减轻再压缩下的隐写分析崩溃
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-22 DOI: 10.1109/LSP.2025.3612695
Xin Li;Hongxia Wang;Jinhe Li
{"title":"Mitigating Steganalysis Collapse Under Re-Compression via Pre-Transmission Guidance","authors":"Xin Li;Hongxia Wang;Jinhe Li","doi":"10.1109/LSP.2025.3612695","DOIUrl":"https://doi.org/10.1109/LSP.2025.3612695","url":null,"abstract":"Current steganalysis primarily focuses on analyzing clean pre-transmission images, which we term Transmission-Prior Steganalysis (TPS), neglecting the performance degradation caused by lossy transmission channels. This creates a critical mismatch in real-world scenarios where modern JPEG-resistant steganography preserves message integrity despite aggressive recompression, whereas transmission-induced distortions largely compromise detection performance. We formally identify this problem as Transmission-Disturbed Steganalysis (TDS) and propose PGD-Net (TPS Guides TDS Network), a teacher-student framework that bridges transmission-prior knowledge and distorted-image analysis through dual alignment mechanisms. The framework simultaneously ensures prediction consistency through output distribution alignment and preserves discriminative features via structured relation alignment. Experimental results demonstrate great improvements in detection performance for existing steganalyzers when applied to distorted images. By establishing the first benchmark for quality-loss scenarios, this work addresses a new practical deployment challenge, further advancing the field toward robust real-world applications.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3814-3818"},"PeriodicalIF":3.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Robust Fusion of Differential Beamformers for Speech Enhancement in Dynamic Interference Conditions 差分波束形成器在动态干扰条件下的鲁棒融合语音增强
IF 3.9 2区 工程技术
IEEE Signal Processing Letters Pub Date : 2025-09-19 DOI: 10.1109/LSP.2025.3612336
Kunlong Zhao;Xueqin Luo;Jilu Jin;Danqi Jin;Gongping Huang
{"title":"Robust Fusion of Differential Beamformers for Speech Enhancement in Dynamic Interference Conditions","authors":"Kunlong Zhao;Xueqin Luo;Jilu Jin;Danqi Jin;Gongping Huang","doi":"10.1109/LSP.2025.3612336","DOIUrl":"https://doi.org/10.1109/LSP.2025.3612336","url":null,"abstract":"Differential microphone arrays are widely used for far-field sound acquisition due to their high directivity and compact geometry. However, they lack the flexibility to adapt in dynamic acoustic environments with multiple or moving interferers. This paper proposes a novel method for fusing multiple differential beamformers to improve robustness under such conditions. A set of beamformers is designed with distortionless constraints in the target direction and nulls in various potential interference directions. An online fusion strategy is then applied, where a subset of beamformer outputs is selected and adaptively combined at each time frame based on the criterion of minimizing the instantaneous output variance. Simulation results demonstrate that the proposed method achieves superior interference suppression and speech quality, while maintaining low computational complexity suitable for real-time processing.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3794-3798"},"PeriodicalIF":3.9,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信