IEEE Signal Processing Letters最新文献_第4页

Synth-Tracker: Recoverable and Traceable Defense Watermark Against Face Synthesis 合成跟踪器：针对人脸合成的可恢复和可跟踪防御水印

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-09 DOI: 10.1109/LSP.2025.3608085

Qingsong Zhang;Beijing Chen;Yuhui Zheng

{"title":"Synth-Tracker: Recoverable and Traceable Defense Watermark Against Face Synthesis","authors":"Qingsong Zhang;Beijing Chen;Yuhui Zheng","doi":"10.1109/LSP.2025.3608085","DOIUrl":"https://doi.org/10.1109/LSP.2025.3608085","url":null,"abstract":"The fast development of face synthesis technology has brought an increasing number of face synthesis services. However, when such services are misused in malicious activities, the face synthesis service providers (FSSPs) may face serious legal risks. Therefore, this letter proposes a recoverable and traceable defense watermarking method to protect FSSPs. The method designs a decoupled data hiding framework to separate two embedding tasks, where the source image and operator’s ID are inserted into the synthesized image respectively by invertible neural network and convolutional neural network. Furthermore, a facial masking strategy is employed to exclude background information of source image for enhancing the imperceptibility. The proposed method enables forensic traceability for the FSSPs to track back to the malicious users and recover the original source images, building a chain of evidence and inferring the forger’s intent after forgery. Experimental results show that compared to the existing methods, the proposed method has superior performance in source image recovery and ID extraction. In addition, the plug-and-play design of the proposed method allows for seamless integration into current face synthesis services.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3715-3719"},"PeriodicalIF":3.9,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210100","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

ReTeNet: A Residual Encoder and Transformer Encoders Network for Stress Monitoring From Wearable Device 用于可穿戴设备应力监测的剩余编码器和变压器编码器网络

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-09 DOI: 10.1109/LSP.2025.3607767

Md Santo Ali;Mohammod Abdul Motin;Sumaiya Kabir

{"title":"ReTeNet: A Residual Encoder and Transformer Encoders Network for Stress Monitoring From Wearable Device","authors":"Md Santo Ali;Mohammod Abdul Motin;Sumaiya Kabir","doi":"10.1109/LSP.2025.3607767","DOIUrl":"https://doi.org/10.1109/LSP.2025.3607767","url":null,"abstract":"Mental stress adversely impacts overall well-being, and chronic stress poses serious risks to both physical and mental health, necessitating the development of wearable-based stress monitoring tools. Blood volume pulse (BVP) sensors, widely integrated into commercially available wearable devices, offer a cost-effective and convenient solution for stress detection, but existing methods face challenges such as data imbalance, complex models unsuitable for real-time use, and limited generalizability. This study presents a lightweight residual-encoder and transformer-encoders network (ReTeNet) for stress monitoring using BVP signals. The proposed model is trained and evaluated on two datasets using a subject-independent, leave-one-subject-out (LOSO) cross-validation strategy: the private RUET SPML dataset with 26 healthy subjects and the publicly available WESAD dataset with 15 healthy subjects. It achieves 93.59% accuracy, 95.60% F1-score, and 0.9569 AUC on the RUET SPML dataset, while attaining 98.23% accuracy, 97.58% F1-score, and 0.9953 AUC on the WESAD dataset. The model effectively distinguishes mental stress with high accuracy while maintaining a lightweight architecture, making it well-suited for wearable devices. Furthermore, its capability to maintain balanced performance across imbalanced datasets highlights its potential for reliable real-time stress monitoring.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3635-3639"},"PeriodicalIF":3.9,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141583","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

Bayesian Transfer Filtering via UFIR Adaptive Regularization 基于UFIR自适应正则化的贝叶斯传输滤波

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-08 DOI: 10.1109/LSP.2025.3607235

Tianyu Zhang;Xiaojing Ping;Shunyi Zhao;Yuriy S. Shmaliy

引用次数: 0

Exploring the Depth From EAST: Efficient Aggregated State-Space Tanh-Tuned Model for Underwater Object Detection 从东方探索深度：用于水下目标检测的高效聚合状态空间tanh调谐模型

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-08 DOI: 10.1109/LSP.2025.3606841

Yili Xu;Xuanxuan Xiao

引用次数: 0

A New Interpretation of the Time-Interleaved ADC Mismatch Problem: A Tracking-Based Hybrid Calibration Approach 时间交错ADC失配问题的新解释：一种基于跟踪的混合校准方法

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-08 DOI: 10.1109/LSP.2025.3607310

Jiwon Sung;Jinseok Choi

引用次数: 0

LF-GS: 3D Gaussian Splatting for View Synthesis of Multi-View Light Field Images LF-GS：用于多视点光场图像视图合成的三维高斯溅射

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-05 DOI: 10.1109/LSP.2025.3606836

Yixu Huang;Rui Zhong;Ségolène Rogge;Adrian Munteanu

{"title":"LF-GS: 3D Gaussian Splatting for View Synthesis of Multi-View Light Field Images","authors":"Yixu Huang;Rui Zhong;Ségolène Rogge;Adrian Munteanu","doi":"10.1109/LSP.2025.3606836","DOIUrl":"https://doi.org/10.1109/LSP.2025.3606836","url":null,"abstract":"3D Gaussian Splatting (3D-GS) has emerged as a groundbreaking approach for view synthesis. However, when applied to light field image synthesis, the issue of a too narrow field of view (FOV) that leaves some areas uncovered, compounded by the problem of data sparsity, significantly compromises the quality of synthesized views using 3D-GS. To overcome these limitations, we present LF-GS, a specialized 3D-GS variant optimized for light field image synthesis. Our methodology incorporates two key innovations. First, by harnessing the unique advantage of light field sub-aperture images that provide dense geometric cues, our method enables the effective incorporation of enhanced depth and normal priors derived from light field images. This allows for more accurate depth than monocular depth estimation. Second, unlike other methods that struggle to control the generation of unreasonable Gaussians, we introduce adaptive regularization mechanisms. These mechanisms strategically regulate Gaussian opacity and spatial scale during optimization, thereby preventing model overfitting and preserving essential scene details. Comprehensive experiments on our newly constructed light field dataset demonstrate that LF-GS achieves significant quality improvements over 3D-GS.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3555-3559"},"PeriodicalIF":3.9,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090032","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

Learning Human-Object Interactions in Videos by State Space Models 通过状态空间模型学习视频中的人-物交互

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-05 DOI: 10.1109/LSP.2025.3606840

Qiyue Li;Xuyang Li;Yuanqing Li;Jiapeng Yan

引用次数: 0

Brain-Inspired Video Quality Assessment via Visual-EEG Feature Alignment 基于视觉-脑电特征对齐的脑启发视频质量评估

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-04 DOI: 10.1109/LSP.2025.3606204

Chenyang Zhang;Shuzhan Hu;Chenxing Li;Yiping Duan;Xiaoming Tao

{"title":"Brain-Inspired Video Quality Assessment via Visual-EEG Feature Alignment","authors":"Chenyang Zhang;Shuzhan Hu;Chenxing Li;Yiping Duan;Xiaoming Tao","doi":"10.1109/LSP.2025.3606204","DOIUrl":"https://doi.org/10.1109/LSP.2025.3606204","url":null,"abstract":"Video quality assessment (VQA) is crucial in applications such as video calls, real-time meetings, and surveillance, where video quality directly impacts user experience greatly. Traditional objective methods like SSIM and PSNR fail to capture the subjective perception of video quality, while subjective Quality of Experience (QoE) assessment metrics like Mean Opinion Score (MOS) are not scalable for large-scale automated VQA tasks. To overcome these limitations, deep learning approaches have emerged, but mostly focusing only on a single video modality, extracting low-level visual features such as color and texture. Recently, electroencephalography (EEG) has been shown to align with users’ subjective experiences, offering valuable insights into neural responses to visual content. Hence, in this letter, we propose a brain-inspired deep learning framework for VQA that aligns EEG and video features. We build a video distortion dataset annotated with both MOS and EEG signals to analyze the impact of video distortions on EEG responses and subjective ratings. We then employ an adaptive EEG feature learning network to extract EEG features linked to video distortions, and propose a video quality prediction network that aligns both video and EEG features using a three-stage training strategy. Our method outperforms existing techniques, showing strong alignment with human subjective ratings. Experimental results validate the effectiveness of EEG in enhancing VQA with a more human-centric approach.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3665-3669"},"PeriodicalIF":3.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210040","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

Token Aggregation and Selection Hashing for Efficient Underwater Image Retrieval 基于令牌聚合和选择哈希的高效水下图像检索

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-02 DOI: 10.1109/LSP.2025.3605283

Shishi Qiao;Benqian Lin;Guanren Bu;Shuai Yuan;Haiyong Zheng

{"title":"Token Aggregation and Selection Hashing for Efficient Underwater Image Retrieval","authors":"Shishi Qiao;Benqian Lin;Guanren Bu;Shuai Yuan;Haiyong Zheng","doi":"10.1109/LSP.2025.3605283","DOIUrl":"https://doi.org/10.1109/LSP.2025.3605283","url":null,"abstract":"The scarcity of large-scale annotated data poses significant challenges for underwater visual analysis. Deep hashing methods offer promising solutions for efficient large-scale image retrieval tasks due to their exceptional computational and storage efficiency. However, underwater images suffer from inherent degradation (e.g., low contrast, color distortion), complex background noise, and fine-grained semantic distinctions, severely hindering the discriminability of learned hash codes. To address these issues, we propose Token Aggregation and Selection Hashing (TASH), the first deep hashing framework specifically designed for underwater image retrieval. Built upon a teacher-student self-distillation Vision Transformer (ViT) architecture, TASH incorporates three key innovations: (1) An Underwater Image Augmentation (UIA) module that simulates realistic degradation patterns (e.g., color shifts) to augment the student branch’s input, explicitly enhancing model robustness to the diverse distortions encountered underwater; (2) A Multi-layer Token Aggregation (MTA) module that fuses features across layers, capturing hierarchical contextual information crucial for overcoming low contrast and resolving ambiguities in degraded underwater scenes; and (3) An Attention-based Token Selection (ATS) module that dynamically identifies and emphasizes the most discriminative tokens, eliminating the effect of background noise and enabling extracting subtle yet critical visual cues for distinguishing fine-grained underwater species. The resulting discriminative real-valued features are compressed into compact binary codes via a dedicated hash layer. Extensive experiments on two underwater datasets demonstrate that TASH significantly outperforms state-of-the-art methods, establishing new benchmarks for efficient and accurate underwater image retrieval.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3545-3549"},"PeriodicalIF":3.9,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090031","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

A Tracking Method for Dense Targets Within Resolvable Group Based on Collective Feature Correction 基于集体特征校正的可分辨群内密集目标跟踪方法

IF 3.9 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-09-02 DOI: 10.1109/LSP.2025.3605294

Guoqing Qi;Shuai Ke;Yinya Li;Andong Sheng

{"title":"A Tracking Method for Dense Targets Within Resolvable Group Based on Collective Feature Correction","authors":"Guoqing Qi;Shuai Ke;Yinya Li;Andong Sheng","doi":"10.1109/LSP.2025.3605294","DOIUrl":"https://doi.org/10.1109/LSP.2025.3605294","url":null,"abstract":"This article addresses the multi-target tracking problem for a dense but resolvable group, and designs a method that uses the velocity estimation of the group to correct the initialization of trajectories and optimize the trajectories identification for the sub-targets within the group. First, an extended target tracking algorithm based on the elliptical random hypersurface model (RHM) is adopted to obtain the overall motion state of the group. Second, the overall velocity estimation, i.e., the collective feature of the group, is used as a prior pseudo measurement information to assist in generating the newborn target state more accurately. Next, an adaptive Generalized Labeled Multi-Bernoulli (GLMB) algorithm is used to estimate the motion states of the dense targets within the group, and the sub-target motion states are modified by integrating the overall velocity estimation of the group. The simulation results verify that the velocity correction algorithm proposed in this paper can significantly improve the tracking performance of the dense group targets, and provide a theoretical guidance for the engineering applications in the group target tracking.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"3520-3524"},"PeriodicalIF":3.9,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145061938","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