Large-scale three dimensional vehicle aerodynamics prediction poses critical computational challenges in modern automotive design, where traditional CFD methods require prohibitive simulation times that conflict with rapid design iteration demands. While recent neural operator approaches show promise, existing methods struggle with computational complexity in dense meshes and fail to preserve essential topological information when processing large-scale point clouds. We propose FCMO, a physics-aware neural operator that integrates fluid mechanics principles with selective state space modeling for efficient large-scale vehicle aerodynamics. FCMO introduces four synergistic components: FlowCurv Anchor Sampling that intelligently selects mesh nodes based on normalized local curvature and windward sensitivity. Additionally, dual-scale physics-aware position encoding with adaptive k-NN construction transforms 3D irregular meshes into causality-preserving sequences through feature-guided serpentine scanning. The model integrates a flow-aware Mamba processor incorporating selective mechanisms that dynamically modulate state transitions based on wall distance and flow characteristics. Finally, a physics-constrained decoder enforces conservation laws through mixed weighted interpolation. Extensive experiments on Ahmed-Body and DrivAerNet benchmarks demonstrate that FCMO achieves consistent state-of-the-art performance with 5.2% improvement in surface pressure prediction, 9.3% enhancement in wall shear stress estimation, and 11.4% boost in drag coefficient accuracy, while maintaining superior computational efficiency with 9.4% fewer FLOPs and 9.9% reduced memory usage compared to existing methods.

Recently, convolutional neural networks for finger vein recognition have gained attention, but their application in IoT smart home security is underexplored. Existing methods typically require networks to identify all categories in a dataset, leading to high parameter demands, which is inefficient given the small, dynamic user groups (3-5 users) in smart homes. To address this, we propose a finger vein recognition system based on meta-learning. Our approach frames recognition as a meta-learning task, introducing a dynamic, exponentially-weighted multistep loss optimization to enhance the model-agnostic meta-learning process. This allows quick adaptation to new tasks with minimal data. Additionally, we design an adaptive recognition scheme that updates network parameters without altering the structure for various users. Experiments on public datasets confirm the effectiveness of our system in IoT smart home security, achieving excellent recognition performance.

ABSTRACT Multi‐object tracking (MOT) is a fundamental problem in computer vision that involves tracing the trajectories of foreground targets throughout a video sequence while establishing correspondences for identical objects across frames. With the advancement of deep learning techniques, methods based on deep learning have significantly improved accuracy and efficiency in MOT. This paper reviews several recent deep learning‐based MOT methods and categorises them into three main groups: detection‐based, single‐object tracking (SOT)‐based, and segmentation‐based methods, according to their core technologies. Additionally, this paper discusses the metrics and datasets used for evaluating MOT performance, the challenges faced in the field, and future directions for research.

In current mainstream radar-based personnel identification technologies, the identification process typically relies on detecting the Doppler effect or the intensity of radar reflection signals. However, this method encounters limitations when there are multiple people within the radar detection area, as it cannot precisely locate each person in the real space. Moreover, when these signals are directly input into neural networks for learning, the networks tend to capture macroscopic information, such as body reflections and velocity, while overlooking detailed information crucial for identification, such as body posture and gait. To overcome this challenge, this study proposes a real-time through-wall multiperson identification system based on MIMO radar, named RTMP-ID. This system employs a global-local dual-branch structure to learn fine-grained identity information. The local branch focuses on introducing a radar-based human posture estimation network, aiming to accurately extract sequences of human postures. Based on these sequences, an identity feature extraction model is constructed to derive individual identity information from the postures. Meanwhile, the global branch integrates the posture information obtained from the local branch in a feedback manner, further accurately extracting the target reflection regions for feature extraction. By fusing the features extracted by both branches, the system achieves accurate identification of individuals. Our research results emphasized the critical importance of introducing 3-D pose sequences to enhance the robustness and accuracy of multitarget person identification. We conducted experiments across three scenarios and achieved a maximum recognition rate of 97.4%, even in the presence of stationary individuals.

Finger vein recognition offers significant advantages in biometric authentication, while federated learning addresses data silo challenges in distributed environments. However, label noise issues severely impact recognition performance due to variations in data acquisition environments, fluctuations in user registration quality, and privacy constraints preventing centralized annotation review. Existing label noise research typically focuses on sample-level processing, overlooking quality variations between authentication systems and noise distribution characteristics across multiple source devices. This paper proposes FedRDA, a federated optimization framework that achieves precise identification and adaptive correction of noisy samples through a three-tier progressive mechanism. We first construct a hierarchical noise detection system that identifies label noise from both noisy client and noisy sample perspectives. Then, we design a dynamic pseudo-label learning module with an improved adaptive label ambiguation loss function that dynamically adjusts sample learning difficulty parameters and incorporates momentum update mechanisms, significantly enhancing model adaptability to label noise of varying difficulty, while integrating predictive uncertainty entropy with unsupervised consistency constraints for more accurate label correction. Finally, we propose an adaptive aggregation strategy based on distance awareness and gradient consistency metrics to address data isolation and label noise issues in distributed environments. Experiments on SDUMLA, MMCBNU_6000, FV-USM, and combined datasets demonstrate that FedRDA maintains high model accuracy even under high noise rate conditions, with approximately 14% accuracy improvement over existing methods. The proposed framework effectively mitigates the negative impact of label noise on model training, ensuring robust operation of finger vein recognition systems in practical distributed environments while protecting user privacy.

In recent years, the recognition accuracies of deep learning-based biometric recognition methods, which rely on large amounts of biometric data for training, have significantly increased. However, in practical applications, biometric data are often distributed in small and fragmented amounts among various local clients. Implementing distributed biometric recognition is therefore greatly important. Most existing distributed biometric methods are implemented by federated learning and have achieved great success. However, the conversion from traditional local learning to distributed learning with multiterminal cooperation poses a series of security hazards, such as Byzantine attacks, inference attacks, etc, that have not been addressed. To address the issues, in this paper, a decentralized federated learning links (FedLink) for distributed biometric recognition is proposed, which is resistant to malicious attacks such as Byzantine attacks. Additionally, we validate the performance and security of FedLink by using two biometric traits, fingerprint and finger vein, on the NUPT-FPV dataset. The experimental results demonstrate that the FedLinks has excellent recognition accuracy and performs comparably to the unattacked model when subjected to various degrees of Byzantine attacks.

Compared with single biometric recognition, multimodal biometric recognition based on fingerprint and finger vein has been widely considered because of its convenient sample collection, high security and accurate recognition. However, according to our investigation, there is no public dataset of fingerprint and finger vein collected at the same time. The existing work uses fingerprint datasets and finger vein datasets from different sources for research, besides the researchers data from building their own equipment, which lacks consideration of practical applications. This is not conducive to the promotion of multibiometric technology based on finger. To promote research on multimodal biometric recognition based on fingerprint and finger vein, we design a finger collection device and introduce a new dataset, NUPT-FPV. It is the first public dataset to collect fingerprint and finger vein simultaneously in real-world applications. NUPT-FPV obtained 840 finger information from 140 volunteers, each finger was collected 20 times (collected in two sessions), and 33600 fingerprint and finger vein images were obtained. In addition, we propose a novel multimodal fusion method based on a convolutional neural network as a benchmark. Extensive experiments were conducted to verify the necessity of our dataset. Through the released dataset and benchmark, we hope to further promote the development of multimodal biometrics based on fingerprint and finger vein.