样式: 排序: IF: - GO 导出 标记为已读
-
Chain-of-LoRA: Enhancing the Instruction Fine-Tuning Performance of Low-Rank Adaptation on Diverse Instruction Set IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-14 Xihe Qiu, Teqi Hao, Shaojie Shi, Xiaoyu Tan, Yu-Jie Xiong
-
Spectrum Attention Mechanism for a Complex Neural Network IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-14 Xinzhi Liu, Jun Yu, Toru Kurihara, Congzhong Wu, Shu Zhan
-
Specific Emitter Identification based on Multi-Scale Multi-Dimensional Approximate Entropy IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-14 Muhammad Usama Zahid, Muhammad Danish Nisar, Maqsood Hussain Shah, Syed Aamer Hussain
-
Adaptive Colour-Depth Aware Attention for RGB-D Object Tracking IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-13 Xue-Feng Zhu, Tianyang Xu, Xiao-Jun Wu
-
Fast Bootstrapping Nonparametric Maximum Likelihood for Latent Mixture Models IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-12 Shijie Wang, Minsuk Shin, Ray Bai
-
Universal Mismatched Steganalysis Equipped with Progressive Intermediate Domains IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-12 Shaowei Weng, Zhuwei Zhang, Lifang Yu, Peng Cao, Gang Cao
-
Unveiling the Truth: Exploring Human Gaze Patterns in Fake Images IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-11 Giuseppe Cartella, Vittorio Cuculo, Marcella Cornia, Rita Cucchiara
-
Cosine Scoring with Uncertainty for Neural Speaker Embedding IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-08 Qiongqiong Wang, Kong Aik Lee
-
SliNet: Slicing-Aided Learning for Small Object Detection IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-08 Chuanyan Hao, Hao Zhang, Wanru Song, Feng Liu, Enhua Wu
-
Parallax-aware Network for Light Field Salient Object Detection IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-08 Bo Yuan, Yao Jiang, Keren Fu, Qijun Zhao
-
Feature Block-Aware Correlation Filters for Real-Time UAV Tracking IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-08 Hong Zhang, Yan Li, Hanyang Liu, Ding Yuan, Yifan Yang
-
Lightweight Deep Neural Network Model With Padding-free Downsampling IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-06 Dengfeng Liu, Xiaohe Guo, Ning Wang, Qin Wu
-
Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-06 Zhen Qin, Xuwei Tan, Zhihui Zhu
-
An Efficient Hypergraph-Based Routing Algorithm in Time-Sensitive Networks IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-05 Yinzhi Lu, Guofeng Zhao, Chuan Xu, Shui Yu
-
Convolutional Neural Network Assisted Transformer for Automatic Modulation Recognition Under Large CFOs and SROs IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-05 Rui Zeng, Zhilin Lu, Xudong Zhang, Jintao Wang, Jian Wang
Automatic modulation recognition (AMR) has received widespread attention as a crucial aspect of non-cooperative communication. Despite this, large carrier frequency offsets (CFOs) and sample rate offsets (SROs) caused by inaccurate parameter estimation at the receiver are harmful to the recognition accuracy, which is still to be addressed. In this letter, we focus on intelligent modulation recognition
-
iPCa-Former: A Multi-Task Transformer Framework for Perceiving Incidental Prostate Cancer IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-04 Xianwei Pan, Simiao Wang, Yunan Liu, Lijie Wen, Mingyu Lu
-
Trainable Fractional Fourier Transform IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-04 Emirhan Koc, Tuna Alikasifoglu, Arda Can Aras, Aykut Koc
-
Analysis of Quantization Noise in Fixed-Point HDFT Algorithms IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-04 Monther Alrwashdeh, Balazs Czifra, Zsolt Koll ´ ar
-
TUT: Template-augmented U-net Transformer for Unsupervised Anomaly Detection IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-04 Ziyi Chen, Chenyao Bai, Yunlong Zhu, Xiwen Lu
-
A Class of Impulsive Eigenfunctions of Multidimensional Fourier Transform IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-04 Levent Onural
-
Space-Scale Hybrid Continuous-Discrete Sliding Frank-Wolfe Method IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-04 Clara Lage, Nelly Pustelnik, Jean Michel Arbona, Benjamin Audit
-
A channel-wise multi-scale network for single image super-resolution IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-03-04 Jiahuan Ji, Baojiang Zhong, Qihui Wu, Kai-Kuang Ma
-
FSTrack: One-shot multi-object tracking algorithm based on feature enhancement and similarity IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-28 Botong He, Liang Yuan, Kai Lv
-
Joint Motion Deblurring and Super-Resolution for Single Image Using Diffusion Model and GAN IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-27 Dongxiao Zhang, Ni Tang, Yanyun Qu
Blind super-resolution (SR) aims to restore real low-resolution (LR) images. However, most current methods focus on global uniform blur but neglect motion blur, and the few motion deblurring SR methods tend to produce too smooth images. In this letter, we introduce a novel diffusion-based SR method, which can effectively handle the motion blur effect in LR images and retain fine-grained texture information
-
A Benchmark for Vehicle Re-Identification in Mixed Visible and Infrared Domains IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-27 Qianqian Zhao, Simin Zhan, Rui Cheng, Jianqing Zhu, Huanqiang Zeng
We propose a new benchmark for vehicle re-identification in mixed visible and infrared domains. Unlike cross-modal vehicle re-identification, we focus on a more realistic scenario, namely, mixed-modal vehicle re-identification, in which both probe and gallery sets contain visible and infrared images. We provide auto-cropped visible and infrared images, simulating data from actual surveillance systems
-
Spectro-Temporally Compressed Source Features for Replay Attack Detection IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-27 Sarfaraz Jelil, Rohit Sinha, S. R. Mahadeva Prasanna
The role of pitch-synchronous source features in the detection of replay attacks on speaker verification systems has been explored earlier. This letter presents some advancements in the processing which enable the use of the entire source signal as well as better capture of the source dynamics. The resulting features are used to develop replay attack detection systems using both the Gaussian mixture
-
Reinforced Self-Supervised Training for Few-Shot Learning IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-27 Zhichao Yan, Yuexuan An, Hui Xue
Few-shot learning is an open problem to learning a new concept with little supervision from limited labeled data. As an alternative knowledge for few-shot learning, self-supervised learning can extract supervisory signals directly from unlabeled data. However, existing self-supervised few-shot methods which directly take the summation of two tasks, have two fundamental bottlenecks: 1) representation
-
Fine-Tuning for Bayer Demosaicking through Periodic-Consistent Self-Supervised Learning IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-27 Chang Liu, Songze He, Jiajun Xu, Jia Li
-
The Proximal Operator of the Piece-wise Exponential Function IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-27 Yulan Liu, Yuyang Zhou, Rongrong Lin
-
Generalization of Whittle's formula to compound-Gaussian processes IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-19 Jean-Pierre Delmas, Habti Abeida
-
Enhancing LPI Radar Signal Classification Through Patch-Based Noise Reduction IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-14 Junseob Kim, Sunghwan Cho, Sunil Hwang, Wonjin Lee, Yeongyoon Choi
This letter presents a novel patch-based noise reduction framework designed to enhance the performance of Low Probability of Intercept (LPI) radar waveform classification. The proposed approach capitalizes on the unique characteristic of the waveform’s Time-Frequency Images (TFIs) being concentrated in the central region of the image. By partitioning the noisy image into multiple patches, each patch
-
Active Defense Against Voice Conversion Through Generative Adversarial Network IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-12 Shihang Dong, Beijing Chen, Kaijie Ma, Guoying Zhao
Active defense is an important approach to counter speech deepfakes that threaten individuals’ privacy, property, and reputation. However, the existing works in this field suffer from issues such as time-consuming and ordinary defense effectiveness. This letter proposes a Generative Adversarial Network (GAN) framework for adversarial attacks as a defense against malicious voice conversion. The proposed
-
Joint Learning Spatial-Temporal Attention Correlation Filters for Aerial Tracking IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-12 Bo Zhao, Sugang Ma, Zhixian Zhao, Lei Zhang, Zhiqiang Hou
Discriminative correlation filter (DCF)-based UAV tracking algorithms have drawn much attention due to their outstanding robustness and high computational efficiency. However, these algorithms are easily disturbed by background noise and abrupt changes in target appearance, leading to tracking failure. To address the issues above, we propose a real-time UAV object tracking algorithm with adaptive spatial-temporal
-
UniEnc-CASSNAT: An Encoder-Only Non-Autoregressive ASR for Speech SSL Models IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-12 Ruchao Fan, Natarajan Balaji Shankar, Abeer Alwan
Non-autoregressive automatic speech recognition (NASR) models have gained attention due to their parallelism and fast inference. The encoder-based NASR, e.g. connectionist temporal classification (CTC), can be initialized from the speech foundation models (SFM) but does not account for any dependencies among intermediate tokens. The encoder-decoder-based NASR, like CTC alignment-based single-step non-autoregressive
-
Camouflaged Instance Segmentation From Global Capture to Local Refinement IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-12 Chen Li, Ge Jiao, Yun Wu, Weichen Zhao
Camouflaged instance segmentation (CIS) aims to segment instances that are seamlessly embedded in their surroundings. Existing CIS methods often focus on utilizing global information but neglect local information, resulting in incomplete feature representation and reduced accuracy. To address this, we propose a global-to-local network (GLNet) for CIS, leveraging both global and local information for
-
Distributed Fusion of Labeled Multi-Bernoulli Filters Based on Arithmetic Average IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-09 Jingxin Wei, Feng Luo, Jiawei Qi, Xianxian Luo
This letter considers the distributed fusion for Labeled Multi-Bernoulli (LMB) filters under the multi-sensor multi-target tracking scenario. In practice, a novel fusion method that combines the label-free strategy with the fusion method based on the Arithmetic Average (AA) is proposed. Firstly, the label-free version of the LMB posterior is obtained. Then, the corresponding Probability Hypothesis
-
Unified Referring Expression Generation for Bounding Boxes and Segmentations IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-08 Zongtao Liu, Tianyang Xu, Xiaoning Song, Xiao-Jun Wu
Referring expression generation (REG) is a challenging task at the intersection of computer vision and natural language processing, which aims at generating natural language descriptions that uniquely refer to a specific object within an image. Existing REG approaches solely utilize bounding boxes in a rather primitive manner to specify target objects, and employ the classical Convolutional Neural
-
Time-Reversal-Based Correction Algorithms for $\omega$-Free Trajectory Reconstruction Method IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-08 Xinyu Liu, Qingfeng Zhou, Chi-Tsun Cheng, Xindi Wang
The low-energy $\omega$ -free accelerometer pair (OFAP) system can achieve great performance in trajectory reconstruction. However, similar to conventional inertial systems, measurement errors in OFAP systems can get accumulated in the reconstruction process, which needs a trajectory correction algorithm to improve its long-term performance. Unfortunately, the linear correction algorithm used in conventional
-
Accelerated Distributed Allocation IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-08 Mohammadreza Doostmohammadian, Alireza Aghasi
Distributed allocation finds applications in many scenarios including CPU scheduling, distributed energy resource management, and networked coverage control. In this paper, we propose a fast convergent optimization algorithm with a tunable rate using the signum function. The convergence rate of the proposed algorithm can be managed by changing two parameters. We prove convergence over uniformly-connected
-
A Data-Driven Analysis of Robust Automatic Piano Transcription IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-08 Drew Edwards, Simon Dixon, Emmanouil Benetos, Akira Maezawa, Yuta Kusaka
Algorithms for automatic piano transcription have improved dramatically in recent years due to new datasets and modeling techniques. Recent developments have focused primarily on adapting new neural network architectures, such as the Transformer and Perceiver, in order to yield more accurate systems. In this letter, we study transcription systems from the perspective of their training data. By measuring
-
A Fast and Simple Algorithm for Computing MLE of the Amplitude Density Function Parameters IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-08 Mahdi Teimouri
Over the last decades, the family of $\alpha$ -stable distributions has proven to be useful for a variety of applications in telecommunication systems. Particularly, in the case of radar applications, finding a fast and accurate estimation method for the amplitude density function parameters appears to be of great significance. In this work, the maximum likelihood estimator (MLE) is proposed for parameters
-
Bi-Center Loss for Compound Facial Expression Recognition IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-08 Rongkang Dong, Kin-Man Lam
Compound facial expressions involve combinations of basic emotions, posing challenges to automatic facial expression recognition research. The focus of existing studies in facial expression recognition remains primarily on classifying basic or single expressions, which limits its application to compound facial expression recognition. Moreover, some compound facial expression recognition methods rely
-
S$^{3}$CA: A Sparse Strip Spectral Correlation Analyzer IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-08 Carol Jingyi Li, Richard Rademacher, David Boland, Craig T. Jin, Chad M. Spooner, Philip H.W. Leong
The spectral correlation density (SCD) is widely used to characterize cyclostationary signals and the strip spectral correlation analyzer (SSCA) is commonly used to estimate the SCD. Although the SSCA utilizes the fast Fourier transform (FFT) for computational efficiency, its real-time implementation still poses challenges as large input sizes are often involved. In this work, we present a sparse strip
-
A Novel Mixed-ADC Architecture for DOA Estimation IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-05 Xinnan Zhang, Yuanbo Cheng, Hing Cheung So, Jian Li
We propose a novel mixed analog-to-digital converter (ADC) architecture for direction-of-arrival (DOA) estimation using a uniform linear array, where the in-phase and quadrature-phase channels can be independently sampled by different ADCs. We derive the Cramér-Rao bound (CRB) and utilize its lower bound to optimize the placement of different ADCs via a swap-based method. Numerical examples are provided
-
Distributed Multi-Sensor Control for Multi-Target Tracking With a Sparsity-Promoting Objective Function IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-05 Zeren Li, Yunze Cai, Henry Leung
A distributed multi-sensor control method is presented for multi-target tracking. The problem is formulated as auctioned partially observed Markov decision processes (auctioned POMDPs), which is a tractable approach to approximate the solutions in a distributed manner. To ensure adequate coverage of the multi-sensor system, a sparsity-promoting objective function is also designed to reduce overlapping
-
High-Performance QC-LDPC Layered Decoder Based on Shortcut Updating IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-05 Zhongyong Wang, Zhaoyan Xie, Kexian Gong, Jin Yan, Lianghui Chen
Quasi-cyclic low density parity check (QC-LDPC) is widely used in various modern communication standards due to its excellent performance and convenient hardware implementation, but its commonly used pipelined layered decoder faces update conflicts that lead to performance degradation. This letter proposes a shortcut-based decoder to mitigate this problem. When the conflicts occur, we avoid the read/write
-
Empirical Bayesian Imaging With Large-Scale Push-Forward Generative Priors IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-02 S. Melidonis, M. Holden, Y. Altmann, M. Pereyra, K. C. Zygalakis
We propose a new methodology for leveraging deep generative priors for Bayesian inference in imaging inverse problems. Modern Bayesian imaging often relies on score-based diffusion generative priors, which deliver remarkable point estimates but significantly underestimate uncertainty. Push-forward models such as variational auto-encoders and generative adversarial networks provide a robust alternative
-
WTVI: A Wavelet-Based Transformer Network for Video Inpainting IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-02 Ke Zhang, Guanxiao Li, Yu Su, Jingyu Wang
Video inpainting aims to complete missing frames visually convincingly by balancing high-frequency detailed textures and low-frequency semantic structures. Conventional approaches utilize generative adversarial and reconstruction losses for optimizing output frames, each favoring different frequency aspects, to achieve this equilibrium. However, employing both loss types concurrently often results
-
Coarray LMS: Adaptive Underdetermined DOA Estimation With Increased Degrees of Freedom IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-02-02 Joel S., Shekhar Kumar Yadav, Nithin V. George
Underdetermined direction of arrival (U-DOA) estimation refers to the ability to estimate the DOA of more sources than the number of sensors in an array. Usually, to perform U-DOA estimation, the difference coarray of the physical array is utilized in techniques like coarray MUSIC. However, existing U-DOA estimation techniques are computationally expensive. To tackle this issue, in this work, we introduce
-
Knowledge Distillation via Multi-Teacher Feature Ensemble IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-30 Xin Ye, Rongxin Jiang, Xiang Tian, Rui Zhang, Yaowu Chen
This letter proposes a novel method for effectively utilizing multiple teachers in feature-based knowledge distillation. Our method involves a multi-teacher feature ensemble module for generating a robust feature ensemble and a student-teacher mapping module for bridging the student feature and ensemble feature. In addition, we utilize separate optimization, where the student's feature extractor is
-
Carrier Frequency Offset Estimation for OCDM With Null Subchirps IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-29 Sidong Guo, Yiyin Wang, Xiaoli Ma
In this letter, we investigate the carrier frequency offset (CFO) estimation problem in orthogonal chirp division multiplexing (OCDM) systems. We propose a transmission scheme by inserting consecutive null subchirps. A CFO estimator is developed to achieve a full acquisition range. We further demonstrate that the proposed transmission scheme not only helps to resolve CFO identifiability issues but
-
Constrained Regularization by Denoising With Automatic Parameter Selection IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-29 Pasquale Cascarano, Alessandro Benfenati, Ulugbek S. Kamilov, Xiaojian Xu
Regularization by Denoising (RED) is a well-known method for solving image restoration problems by using learned image denoisers as priors. Since the regularization parameter in the traditional RED does not have any physical interpretation, it does not provide an approach for automatic parameter selection. This letter addresses this issue by introducing the Constrained Regularization by Denoising (CRED)
-
Capturing High-Level Semantic Correlations via Graph for Multimodal Sentiment Analysis IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-29 Fan Qian, Jiqing Han, Yadong Guan, Wenjie Song, Yongjun He
Modeling intra-modal and cross-modal interactions poses significant challenges in multimodal sentiment analysis. Currently, graph-based methods like HGraph-CL achieve promising performance, which rely on two different levels of graph contrastive learning within and between modalities to explore sentiment correlations. However, HGraph-CL still faces the following drawbacks in graph construction: 1)
-
Phase-Coded Sequence Design for Local Shaping of Complete Second-Order Correlation IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-29 Yuanzhe Li, Weidong Hu, Hongqi Fan, Xiaoyong Du
The auto-correlation is not sufficient for the complete statistical characterization of a complex sequence, especially in applications involving nonlinear systems. Therefore, this letter addresses the sequence design problem considering the local shaping of complete second-order correlation, which controls the sidelobe level for both auto-correlation and conjugate correlation over specific lags. An
-
Deep Convolutional Network-Assisted Multiple Direction-of-Arrival Estimation IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-29 Jie Ma, Min Wang, Yiyi Chen, Haiming Wang
Multiple direction-of-arrival estimation is one of the core functions in array signal processing and has many engineering applications. It is proposed that it can be realized using a two-stage strategy which consists of multiclass classification for region segmentation and successive cancellation-based fine estimation in subregions. In the first stage, the deep convolutional network (DCN) is introduced
-
Frequency-Selective SIMO Channel Estimation Based on One-Bit Measurements IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-29 Tianyi Zhang, Yi Jiang
Using one-bit analog-to-digital converters (ADCs) can drastically reduce the cost and energy consumption of a wideband large array system. But it brings about challenges to the signal processing aspect of the system. This letter focuses on the estimation of a frequency-selective single-input multi-output (SIMO) channel from the received pilot signals quantized by one-bit ADCs. We first parameterize
-
Secure Wireless Communication via Movable-Antenna Array IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-29 Guojie Hu, Qingqing Wu, Kui Xu, Jiangbo Si, Naofal Al-Dhahir
Movable antenna (MA) array is a novel technology recently developed where positions of transmit/receive antennas can be flexibly adjusted in the specified region to reconfigure the wireless channel and achieve a higher capacity. In this letter, we, for the first time, investigate the MA array-assisted physical-layer security where the confidential information is transmitted from a MA array-enabled
-
Music Conditioned Generation for Human-Centric Video IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-26 Zimeng Zhao, Binghui Zuo, Yangang Wang
Music and human-centric video are two fundamental signals across languages. Correlation analysis between the two is currently used in choreography and film accompaniment. This letter explores this correlation in a new task: human-centric video generation from a start-end image pair and transitional music. Existing human-centric generation methods are not competent for this task because they require
-
ESAformer: Enhanced Self-Attention for Automatic Speech Recognition IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-25 Junhua Li, Zhikui Duan, Shiren Li, Xinmei Yu, Guangguang Yang
In this letter, an Enhanced Self-Attention (ESA) module has been put forward for feature extraction. The proposed ESA is integrated with the recursive gated convolution and self-attention mechanism. In particular, the former is used to capture multi-order feature interaction and the latter is for global feature extraction. In addition, the location of interest that is suitable for inserting the ESA
-
Balanced and Essential Modality-Specific and Modality-Shared Representations for Visible-Infrared Person Re-Identification IEEE Signal Process. Lett. (IF 3.9) Pub Date : 2024-01-25 Soonyong Gwon, Sejun Kim, Kisung Seo
Retrieving and matching individual images for Visible-Infrared Person Re-identification is a challenging task due to the huge modality gap between daytime color and nighttime infrared images from different modalities. Existing approaches rely on inefficient data augmentation and/or biased modality characteristics, limiting their potential for performance improvement. To solve these problems, we propose