IEEE Signal Processing Letters最新文献_第4页

FM-RTDETR: Small Object Detection Algorithm Based on Enhanced Feature Fusion With Mamba 基于增强曼巴特征融合的FM-RTDETR小目标检测算法

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-21 DOI: 10.1109/LSP.2025.3553426

Yuchuan Yang;Jiahui Dai;Yong Wang;Yafei Chen

{"title":"FM-RTDETR: Small Object Detection Algorithm Based on Enhanced Feature Fusion With Mamba","authors":"Yuchuan Yang;Jiahui Dai;Yong Wang;Yafei Chen","doi":"10.1109/LSP.2025.3553426","DOIUrl":"https://doi.org/10.1109/LSP.2025.3553426","url":null,"abstract":"Traditional real-time object detection networks deployed in autonomous aerial vehicles (AAVs) struggle to extract features from small objects in complex backgrounds with occlusions and overlapping objects. To address this challenge, we propose FM-RTDETR, a real-time object detection algorithm optimized for small object detection. We redesign the encoder of RT-DETRv2 by integrating the Feature Aggregation and Diffusion Network (FADN), improving the algorithm's ability to capture contextual information. Subsequently, we introduce the Parallel Atrous Mamba Feature Fusion Module (PAMFFM), which combines shallow and deep semantic information to better capture small object features. Furthermore, we propose the Cross-stage Enhanced Feature Fusion Module (CEFFM), merging features for small objects to provide richer and more detailed information. Finally, we propose STIoU Loss, which incorporates a penalty term to adjust the scaling of the loss function, improving detection granularity for small objects. FM-RTDETR achieves AP<inline-formula><tex-math>$_{50}$</tex-math></inline-formula> scores of 54.0% and 56.3% on the VisDrone2019-DET and AI-TOD datasets. Compared with other state-of-the-art methods, our method shows great potential in small object detection from drones.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1570-1574"},"PeriodicalIF":3.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856341","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

Deep Learning-Based Approach for Identification and Compensation of Nonlinear Distortions in Parametric Array Loudspeakers 基于深度学习的参数阵列扬声器非线性畸变识别与补偿方法

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-21 DOI: 10.1109/LSP.2025.3553434

Mengtong Li;Tao Zhuang;Kai Chen;Jia-Xin Zhong;Jing Lu

{"title":"Deep Learning-Based Approach for Identification and Compensation of Nonlinear Distortions in Parametric Array Loudspeakers","authors":"Mengtong Li;Tao Zhuang;Kai Chen;Jia-Xin Zhong;Jing Lu","doi":"10.1109/LSP.2025.3553434","DOIUrl":"https://doi.org/10.1109/LSP.2025.3553434","url":null,"abstract":"Compared to traditional electrodynamic loudspeakers, the parametric array loudspeaker (PAL) offers exceptional directivity for audio applications but suffers from significant nonlinear distortions due to its inherent intricate demodulation process. The Volterra filter-based approaches have been widely used to reduce these distortions, but the effectiveness is limited by its inverse filter's capability. Specifically, its <inline-formula><tex-math>$p$</tex-math></inline-formula>th-order inverse filter can only compensate for nonlinearities up to the <inline-formula><tex-math>$p$</tex-math></inline-formula>th order, while the higher-order nonlinearities it introduces continue to generate lower-order harmonics. In contrast, this paper introduces the modern deep learning methods for the first time to address nonlinear identification and compensation for PAL systems. Specifically, the WaveNet neural network, recognized for its success in audio nonlinear system modeling, is utilized to identify and compensate for distortions in a double sideband amplitude modulation-based PAL system. Experimental measurements from 250 Hz to 8 kHz demonstrate that our proposed approach significantly reduces both total harmonic distortion and intermodulation distortion of audio sound generated by PALs, achieving average reductions to 3.11% and 0.93%, respectively. This performance is notably superior to results obtained using the current state-of-the-art Volterra filter-based methods. Our work opens new possibilities for improving the sound reproduction performance of PALs.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1455-1459"},"PeriodicalIF":3.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809017","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

Vector Quantization Based Query-Efficient Attack via Direct Preference Optimization 基于矢量量化的直接偏好优化查询高效攻击

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-21 DOI: 10.1109/LSP.2025.3553791

Ruijie Yang;Yuanfang Guo;Chao Zhou;Guohao Li;Yunhong Wang

引用次数: 0

Dual-Branch Network for No-Reference Super-Resolution Image Quality Assessment 无参考超分辨率图像质量评价的双分支网络

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-21 DOI: 10.1109/LSP.2025.3553432

Tong Tang;Fan Yang;Xinyu Lin;Weisheng Li

引用次数: 0

AdaMoT: Adaptive Motion-Aware Transformer for Efficient Visual Tracking AdaMoT：用于高效视觉跟踪的自适应运动感知变压器

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-21 DOI: 10.1109/LSP.2025.3553429

Yongjun Wang;Xiaohui Hao

{"title":"AdaMoT: Adaptive Motion-Aware Transformer for Efficient Visual Tracking","authors":"Yongjun Wang;Xiaohui Hao","doi":"10.1109/LSP.2025.3553429","DOIUrl":"https://doi.org/10.1109/LSP.2025.3553429","url":null,"abstract":"Visual object tracking utilizing adaptive computation presents challenges stemming from the complexities of modeling intricate motion patterns and achieving computational efficiency. While recent transformer-based trackers have shown promising results, they struggle to effectively capture varying motion dynamics and often waste computation on less informative regions, leading to degraded performance under fast motion and occlusion. In this letter, we present AdaMoT, an innovative motion-aware transformer framework featuring three lightweight modules that integrate adaptive attention and motion estimation: a Lightweight Adaptive Motion Estimation (LAME) module that guides transformer attention through motion pattern modeling, a Saliency-based Hard Attention Sampling (SHAS) module that reduces computation by 60% through focusing on motion-critical regions, and an Adaptive ViT Attention Head Adjustment (AVAHA) module that dynamically allocates attention heads based on motion complexity. Our framework uniquely integrates motion estimation with transformer attention through a shared feature space, achieving robust tracking with minimal overhead. Comprehensive testing indicate that AdaMoT attains superior performance on various demanding benchmarks (75.1% AO on GOT-10 k, 84.9% AUC on TrackingNet, 72.9% AUC on LaSOT) while maintaining real-time speed (32.1 FPS) with only 4% FLOPs increase.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1450-1454"},"PeriodicalIF":3.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808974","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 Proximal Newton Adaptive Importance Sampler 一种近牛顿自适应重要性采样器

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-21 DOI: 10.1109/LSP.2025.3553790

Víctor Elvira;Émilie Chouzenoux;O. Deniz Akyildiz

引用次数: 0

Modified Price Nonlinear Frequency Modulated Waveform for Improved Performance 改进的价格非线性调频波形，提高性能

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-21 DOI: 10.1109/LSP.2025.3553437

Geon U Kim;Jeong Phill Kim

引用次数: 0

SequenceOut: Boosting CNNs by Freezing Layers SequenceOut：通过冻结层来提升cnn

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-20 DOI: 10.1109/LSP.2025.3553430

Shitala Prasad;Rakesh Paul;Mayur Kamat

引用次数: 0

ViLNM: Visual-Language Noise Modeling for Text-to-Image Person Retrieval 文本到图像人物检索的视觉语言噪声建模

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-20 DOI: 10.1109/LSP.2025.3553424

Guolin Xu;Yong Feng;Yanying Chen;Guofan Duan;Mingliang Zhou

{"title":"ViLNM: Visual-Language Noise Modeling for Text-to-Image Person Retrieval","authors":"Guolin Xu;Yong Feng;Yanying Chen;Guofan Duan;Mingliang Zhou","doi":"10.1109/LSP.2025.3553424","DOIUrl":"https://doi.org/10.1109/LSP.2025.3553424","url":null,"abstract":"Text-to-image person retrieval (TPR) focuses on finding a specific person based on the textual description, and most methods implicitly assume the training image-text pairs are correctly aligned. In practice, the image-text pairs exist under-correlated or false-correlated due to the low quality of the images and annotation errors. Meanwhile, remarkable similarities between different person identities may lead to a mismatch between text and image. To tackle the two issues, we present a Visual-Language Noise Modeling (ViLNM) method that successfully captures robust cross-modal associations even with noise. Specifically, we design a Noise Token Aware (NTA) module that eliminates the words in the textual description that do not match the image, utilizing the matched words to establish a more reliable association. Besides, to enhance the recognition ability of the model for different person identities, we propose a Joint Inter and Intra-Modal Contrastive Loss (JII) and Local Aggregation (LA) module to increase the feature differences between different person identities. We conduct comprehensive experiments on three public benchmarks, and ViLNM performs best.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1386-1390"},"PeriodicalIF":3.2,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748913","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

Low Complexity MRC Detection of IRS-Aided Single User MIMO-OTFS 红外辅助单用户MIMO-OTFS的低复杂度MRC检测

IF 3.2 2区工程技术

IEEE Signal Processing Letters Pub Date : 2025-03-20 DOI: 10.1109/LSP.2025.3553428

Sapta Girish Neelam

引用次数: 0