{"title":"A RNN for Temporal Consistency in Low-Light Videos Enhanced by Single-Frame Methods","authors":"Claudio Rota;Marco Buzzelli;Simone Bianco;Raimondo Schettini","doi":"10.1109/LSP.2024.3475969","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475969","url":null,"abstract":"Low-light video enhancement (LLVE) has received little attention compared to low-light image enhancement (LLIE) mainly due to the lack of paired low-/normal-light video datasets. Consequently, a common approach to LLVE is to enhance each video frame individually using LLIE methods. However, this practice introduces temporal inconsistencies in the resulting video. In this work, we propose a recurrent neural network (RNN) that, given a low-light video and its per-frame enhanced version, produces a temporally consistent video preserving the underlying frame-based enhancement. We achieve this by training our network with a combination of a new forward-backward temporal consistency loss and a content-preserving loss. At inference time, we can use our trained network to correct videos processed by any LLIE method. Experimental results show that our method achieves the best trade-off between temporal consistency improvement and fidelity with the per-frame enhanced video, exhibiting a lower memory complexity and comparable time complexity with respect to other state-of-the-art methods for temporal consistency.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438500","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}
{"title":"Prototypical Metric Segment Anything Model for Data-Free Few-Shot Semantic Segmentation","authors":"Zhiyu Jiang;Ye Yuan;Yuan Yuan","doi":"10.1109/LSP.2024.3476208","DOIUrl":"https://doi.org/10.1109/LSP.2024.3476208","url":null,"abstract":"Few-shot semantic segmentation (FSS) is crucial for image interpretation, yet it is constrained by requirements for extensive base data and a narrow focus on foreground-background differentiation. This work introduces Data-free Few-shot Semantic Segmentation (DFSS), a task that requires limited labeled images and forgoes the need for extensive base data, allowing for comprehensive image segmentation. The proposed method utilizes the Segment Anything Model (SAM) for its generalization capabilities. The Prototypical Metric Segment Anything Model is introduced, featuring an initial segmentation phase followed by prototype matching, effectively addressing the learning challenges posed by limited data. To enhance discrimination in multi-class segmentation, the Supervised Prototypical Contrastive Loss (SPCL) is designed to refine prototype features, ensuring intra-class cohesion and inter-class separation. To further accommodate intra-class variability, the Adaptive Prototype Update (APU) strategy dynamically refines prototypes, adapting the model to class heterogeneity. The method's effectiveness is demonstrated through superior performance over existing techniques on the DFSS task, marking a significant advancement in UAV image segmentation.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438589","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}
{"title":"RS-2-BP: A Unified Deep Learning Framework for Deriving EIT-Based Breathing Patterns From Respiratory Sounds","authors":"Arka Roy;Udit Satija","doi":"10.1109/LSP.2024.3475358","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475358","url":null,"abstract":"Respiratory disorders have become the third largest cause of death worldwide, which can be assessed by one of the two key diagnostic modalities: breathing patterns (BPs) or the airflow signals, and respiratory sounds (RSs). In recent years, few studies have been conducted on finding correlation between these two modalities which indicate the structural flaws of lungs under disease condition. In this letter, we propose ‘RS-2-BP’: a unified deep learning framework for deriving the electrical impedance tomography-based airflow signals from respiratory sounds using a hybrid neural network architecture, namely ReSTL, that comprises cascaded standard and residual shrinkage convolution blocks, followed by feature refined transformer encoders and long-short term memory (LSTM) units. The proposed framework is extensively evaluated using the publicly available BRACETS dataset. Experimental results suggest that our ReSTL can accurately derive the BPs from RSs with an average mean absolute error of \u0000<inline-formula><tex-math>$0.024pm 0.011, ,0.436pm 0.120, ,0.020pm 0.011,,0.134pm 0.068$</tex-math></inline-formula>\u0000, and \u0000<inline-formula><tex-math>$0.031pm 0.019$</tex-math></inline-formula>\u0000, respectively for five different tasks. Furthermore, these derived BPs can be used for extracting different respiratory vitals, identifying disease conditions efficiently, and retrieving salient breathing cycle information from the RSs.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434635","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}
{"title":"MUSIC Based Multipath Delay Estimation Method in the Fractional Domain for OFDM-LFM","authors":"Jiaojiao Liu;Erdi Chen;Nan Sun;Biyun Ma","doi":"10.1109/LSP.2024.3475356","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475356","url":null,"abstract":"This letter proposes a high-resolution multipath time delay estimation (TDE) method for orthogonal frequency division multiplexing linear frequency modulation (OFDM-LFM) signals. Leveraging the expression of OFDM-LFM signals in the fractional domain, where the compressed subcarriers conform to a linear uniform arrangement, the algorithm combines with the multiple signal classification (MUSIC) algorithm for TDE. Simulation results show that regardless of the presence of Doppler effect, OFDM-LFM results in less relative root mean square error (RRMSE) compared to orthogonal frequency division multiplexing (OFDM). Furthermore, the superiority of OFDM-LFM signals is particularly evident at lower signal-to-noise ratios (SNRs). So the proposed algorithm offers promising implications for TDE in mobile scenarios.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443138","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}
{"title":"Kendall's Tau Based Spectrum Sensing for Cognitive Radio in the Presence of Laplace Noise","authors":"Yongjian Huang;Huadong Lai;Jisheng Dai;Weichao Xu","doi":"10.1109/LSP.2024.3475916","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475916","url":null,"abstract":"In the presence of non-Gaussian noise, traditional spectrum sensing techniques optimized for Gaussian noise may experience significant performance degradation. To address this challenge, this paper employs Kendall's tau (KT) as a detector to detect the primary signal in additive Laplace noise. Unlike techniques relying on fundamental information from raw observation data, this detector utilizes ranks to reduce the impact of impulsive component, thus being robust against large valued outliers. The analytic expressions concerning the expectation and variance of KT under Laplace noise are firstly established. Performance analyses are further conducted in terms of false alarm probability and detection probability. Monte Carlo simulations not only verified the correctness of the established theoretical results, but also demonstrated the superiority of KT over other commonly used methods in terms of detection probability under Laplace noise.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142447071","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}
{"title":"Optimizing Subband Adaptive Filters for Resilience Against Unanticipated Signal Truncation","authors":"Yuhong Wang;Xu Zhou;Zongsheng Zheng","doi":"10.1109/LSP.2024.3475349","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475349","url":null,"abstract":"This letter addresses a common issue in engineering applications: unanticipated signal truncation events caused by the mismatch between the operational range of measurement devices and the signals to be measured. Under such circumstances, the conventional normalized subband adaptive filtering (NSAF) algorithm significantly underperforms and may even fail to converge. To tackle this issue, we propose an improved NSAF algorithm. We introduce an expectation maximization framework to address the maximum likelihood estimation before the subband adaptive filter, specifically to handle double-sided signal truncation. This new approach leads to an NSAF for unanticipated truncation (UT-NSAF), which has been theoretically and numerically proven to be unbiased. Importantly, our research demonstrates that UT-NSAF significantly outperforms other algorithms in terms of estimation accuracy and convergence speed. Notably, the steady-state solution of UT-NSAF remains almost unaffected by varying truncation thresholds, showing robustness crucial for dealing with various unexpected signal truncation scenarios in engineering applications.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434536","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}
{"title":"Automated Audio Data Augmentation Network Using Bi-Level Optimization for Sound Event Localization and Detection","authors":"Wenjie Zhang;Peng Yu;Jun Yin;Xiaoheng Jiang;Mingliang Xu","doi":"10.1109/LSP.2024.3475350","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475350","url":null,"abstract":"In sound event localization and detection (SELD), traditional methods often treat localization and detection algorithms separately from data augmentation. During the model training process, the strategy for data augmentation is typically implemented in a non-learnable manner. Existing audio data augmentation strategies struggle to find optimal parameter solutions for data augmentation that can be effectively applied to SELD systems. To address this challenge, we introduce an innovative network-based strategy, termed the Automated Audio Data Augmentation (AADA) network. This strategy employs bi-level optimization to synergistically integrate audio data augmentation techniques with SELD tasks. In the AADA network, the lower-level SELD task serves as a constraint for the higher-level data augmentation process. The audio data augmentation parameters are adaptively optimized by utilizing the transfer of intermediate feature information from the SELD tasks, thus obtaining optimal parameters for these tasks. Evaluation of our approach on the Sony-TAU Realistic Spatial Soundscapes 2023 dataset achieves a SELD score of 0.4801, significantly surpassing the performance metrics of all traditional data augmentation strategies for SELD.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434568","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}
{"title":"A Momentum Accelerated Algorithm for ReLU-Based Nonlinear Matrix Decomposition","authors":"Qingsong Wang;Chunfeng Cui;Deren Han","doi":"10.1109/LSP.2024.3475910","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475910","url":null,"abstract":"Recently, there has been a growing interest in the exploration of Nonlinear Matrix Decomposition (NMD) due to its close ties with neural networks. NMD aims to find a low-rank matrix from a sparse nonnegative matrix with a per-element nonlinear function. A typical choice is the Rectified Linear Unit (ReLU) activation function. To address over-fitting in the existing ReLU-based NMD model (ReLU-NMD), we propose a Tikhonov regularized ReLU-NMD model, referred to as ReLU-NMD-T. Subsequently, we introduce a momentum accelerated algorithm for handling the ReLU-NMD-T model. A distinctive feature, setting our work apart from most existing studies, is the incorporation of both positive and negative momentum parameters in our algorithm. Our numerical experiments on real-world datasets show the effectiveness of the proposed model and algorithm.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142452700","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}
{"title":"Understanding Correlated Information Diffusion: From a Graphical Evolutionary Game Perspective","authors":"Hong Hu;Zhuoqun Li;H. Vicky Zhao","doi":"10.1109/LSP.2024.3475353","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475353","url":null,"abstract":"In online social networks, millions of connected intelligent individuals actively interact with each other, which not only facilitates opinion sharing but also offers the platform to spread detrimental gossips and rumors. Therefore, it is of crucial importance to better understand how the avalanche of information propagates over social networks and affects our social life and economy. However, most model-based works on information diffusion either consider the spreading of one single message or assume that different information spreads independently. In this letter, we investigate how correlated information spreads together and jointly influences users' decisions from a graphical evolutionary game perspective. We model the multi-source information diffusion process, analyze the impact of information's correlation and time delay on the evolutionary dynamics and the evolutionary stable states (ESS). Simulation results on synthetic networks and Facebook real-world networks are consistent with our analytical results. This investigation offers important insights to the understanding and management of multi-source information diffusion.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443067","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}
{"title":"Random Tensor Analysis: Outlier Detection and Sample-Size Determination","authors":"Shih Yu Chang;Hsiao-Chun Wu","doi":"10.1109/LSP.2024.3475909","DOIUrl":"https://doi.org/10.1109/LSP.2024.3475909","url":null,"abstract":"High-dimensional signal processing and data analysis have been appealing to researchers in recent decades. Outlier detection and sample-size determination are two essential pre-processing tasks for many signal processing applications. However, fast outlier detection for tensor data with arbitrary orders is still in high demand. Furthermore, sample-size determination for random tensor data has not been addressed in the literature. To fill this knowledge gap, we first derive new tensor Chernoff tail-bounds for random Hermitian tensors. According to our derived tail-bounds, we propose a novel approach for joint outlier detection and sample-size determination. The mathematical relationship among outlier-threshold (sample-size-threshold) probability, outlier-threshold spectrum, and critical sample-size along with the computational-complexity reduction brought by our proposed new analytic approach over the existing methods is also investigated through numerical evaluation over a variety of real tensor data.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142447022","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}