Visible-Infrared Person Re-identification (VI-ReID) is critical for round-the-clock surveillance systems yet is hindered by significant modality discrepancies. Existing methods often fail to fully exploit frequency domain information, focusing predominantly on spatial domain feature learning or limited frequency decompositions. To address this, we propose the Multi-Frequency Embedding Network (MFENet), a feature-level method that operates in the frequency domain through multi-frequency decomposition to learn discriminative and modality-invariant features. Specifically, the HiLo-Frequency Modulation (HiLo-FM) module efficiently extracts low-frequency features via frequency-domain filtering and high-frequency details through lightweight multiscale convolutions, followed by attention-based fusion. The Frequency-Aware Diversity Enhancer (FADE) module further enriches feature discriminability by weighting multi-frequency components and learning diverse features through multi-branch architectures. To further enhance the performance of our method, we introduce two innovative loss functions. The Cross-Modality Soft Retrieval (CMSR) loss prioritizes cross-modality consistency over intra-modality similarity, while the Cross-Modality Ranking Regularization (CMRR) loss enhances feature diversity through differentiable rank correlation optimization. Extensive experiments demonstrate the state-of-the-art performance of our method, achieving 61.06% Rank-1 and 67.75% mAP in the challenging IR to VIS mode on the largest VI-ReID benchmark LLCM, surpassing existing methods by significant margins without resorting to reranking or additional labeled data. Code is available at https://github.com/GuHY777/MFENet-VIReID.

Extracting robust discriminative features is a critical challenge in person re-identification (ReID). While Transformer-based methods have successfully addressed some limitations of convolutional neural networks (CNNs), such as their local processing nature and information loss resulting from convolution and downsampling operations, they still face the scalability issue due to the quadratic increase in memory and computational requirements with the length of the input sequence. To overcome this, we propose a pure Mamba-based person ReID framework named ReIDMamba. Specifically, we have designed a Mamba-based strong baseline that effectively leverages fine-grained, discriminative global features by introducing multiple class tokens. To further enhance robust features learning within Mamba, we have carefully designed two novel techniques. First, the multi-granularity feature extractor (MGFE) module, designed with a multi-branch architecture and class token fusion, effectively forms multi-granularity features, enhancing both discrimination ability and fine-grained coverage. Second, the ranking-aware triplet regularization (RATR) is introduced to reduce redundancy in features from multiple branches, enhancing the diversity of multi-granularity features by incorporating both intra-class and inter-class diversity constraints, thus ensuring the robustness of person features. To our knowledge, this is the pioneering work that integrates a purely Mamba-driven approach into ReID research. Our proposed ReIDMamba model boasts only one-third the parameters of TransReID, along with lower GPU memory usage and faster inference throughput. Experimental results demonstrate ReIDMamba's superior and promising performance, achieving state-of-the-art performance on five person ReID benchmarks. Code is available athttps://github.com/GuHY777/ReIDMamba.

Myocardial infarction remains a global health challenge. Accurate myocardial segmentation in late gadolinium enhancement cardiac magnetic resonance imaging (LGE-CMRI) is critical for diagnosis and treatment planning. Although deep learning architectures have demonstrated excellent segmentation performance in conventional CMRI, their accuracy significantly declines in LGE-CMRI due to low tissue contrast and complex background interference. To address these challenges, we propose a Progressive Multi-scale Vision Transformer (PMVT) for myocardial segmentation in LGE-CMRI, which enhances spatial representation capabilities and improves adaptability in complex scenarios through multi-scale feature fusion and interaction. Specifically, PMVT includes a Multi-scale Progressive Attention Decoder (MPSD) for modeling both long and short-term dependencies, and a Multi-layer Hybrid Context Purification (MHCP) that combines different combinations of four prediction heads for prediction and loss calculation, effectively suppressing background interference. Experiments demonstrate that the proposed PMVT outperforms state-of-the-art (SOTA) models, achieving a Dice score of 89.61% for myocardial segmentation (a 1.56% improvement over the current SOTA). This result highlights its considerable potential for clinical applications in automated LGE-CMRI analysis.

Although the discriminative correlation filter‐ (DCF)‐based tracker improves tracking performance, some object representation issues can still be further optimized. On the one hand, the DCF tracker’s deep convolutional features contain many noisy channels, and assigning the same weights to multiple channels cannot distinguish the importance of different channels. On the other hand, a simple weighted fusion approach cannot fully utilize the benefits of different feature types. We propose a visual object tracking algorithm based on adaptive channel weighting and feature game fusion to solve these problems. In this study, an adaptive channel weighting strategy is designed to assign suitable weights to each channel based on the average energy ratio of the target and background regions in the feature channels and prune the channels with low weights to improve feature robustness and reduce computational complexity. Simultaneously, the game theory concept is introduced in the multifeature fusion. The handcrafted features are combined with shallow and deep convolutional features according to feature complementarity. Then, the two combined features are seen as two sides of the game, continuously gamed during the tracking process to generate a feature model with a higher representation capacity. Extensive experiments are conducted on four mainstream visual tracking benchmark datasets, including OTB2015, VOT2018, LaSOT, and UAV123. The experimental results show that the proposed algorithm performs outstandingly compared to the state‐of‐the‐art trackers.

Abstract Correlation filters with convolutional neural network (CNN) features have been successfully applied to visual tracking owing to their impressive combined capability for object representation. Unfortunately, further performance improvement is limited due to unwanted boundary effects of the circular structure. In this work, through an in‐depth study of the features’ characteristics, the authors propose a novel tracking strategy to achieve simultaneous filter matching and regularization with CNN features when tracking is on the fly. With a feature decomposed transform matrix, a spatial semantic regularization is generated to reduce the boundary effect effectively during filter optimization. Before each output, the regularized filter is then back performed to match with the extracted features of a search region to find the optimum candidate. Specifically, the most important advantage of the proposed spatial semantic map is to initialize only in the first frame as all the other tracking strategies. Besides, the authors design a novel updating strategy to tackle the cases where the object is occluded or disappeared in the scene. At this time, the maximum of the map is small, even negative. A substantial experiment has been carried out on the popular benchmark tracking datasets; the reliable results have demonstrated that the authors’ method is able to outperform most of the state‐of‐the‐art tracking works in both accuracy and robustness.

Discriminative correlation filters (DCFs) have shown promising tracking performance in recent years thanks to the powerful representation ability of deep features. However, a large number of target-irrelevant channels in deep features limits the tracking performance and increases the computational cost. To eliminate the negative impact of noisy channels and improve the utilization efficiency of deep features in DCF-based trackers, we present an adaptive feature channel selection method for robust visual tracking. Our method adaptively chooses the most discriminative channels to learn a more robust target appearance model, which is achieved by evaluating the energy relationship between background and foreground in each feature channel. Moreover, according to the feedback of channel selection, an adaptive model update strategy is proposed to alleviate the model degradation problem caused by incorrect model updating. Extensive experimental results obtained on five popular tracking benchmarks demonstrate the effectiveness of the proposed algorithm and its superiority over the state-of-the-art trackers.