The performance of face recognition is highly dependent on detection accuracy and robustness. However, most face recognition methods assume that face regions are perfectly aligned and rely exclusively on visual features within bounding boxes. This assumption is often violated in complex environments, including low resolution, poor illumination, and partial occlusion. To overcome these limitations, this paper proposes a collaborative face detection and recognition framework enhanced by meta-auxiliary learning. The proposed method exploits shared representations by an improved feature extraction module, and introduces gender classification and age estimation as auxiliary tasks to construct a meta-composite loss. Furthermore, facial geometric structure are acquired by extracting facial landmark coordinates from detected face regions. This multi-task architecture imposes implicit constraints on shared features, while simultaneously boosting feature discriminability and system robustness. By fusing facial geometric structures with semantic meta-information, facial identity representations are effectively enriched, leading to substantial performance gains in complex scenarios. Extensive experiments on the SCFace and LRD benchmark datasets validate the effectiveness of the proposed method. On SCFace, our method achieves 77.21% Genuine Acceptance Rate (GAR) at a False Acceptance Rate (FAR) of 1%, surpassing ArcFace, Octuplet Loss, and HDFGD by 1–2 percentage points. On LRD200 and LRD100 under an extreme low-resolution condition of 15 pixels, the recognition accuracies of the proposed method reach 67.98% and 60.98%, respectively—on par with state-of-the-art methods and markedly superior to conventional baselines. These results confirm that meta-auxiliary learning effectively compensates for insufficient visual information by leveraging semantic cues. Non-parametric statistical tests (Wilcoxon signed-rank test) confirm that the improvements achieved by the proposed method are statistically significant (p < 0.05).

Dynamic multiobjective optimization problems (DMOPs) frequently arise in real-world applications, where environments evolve over time. A central challenge in solving DMOPs is the ability to accurately and efficiently track optimal solutions as the environment changes. Existing dynamic multiobjective evolutionary algorithms (DMOEAs) based on single-strategy mechanisms often perform well only under specific environmental conditions, while multistrategy cooperative frameworks tend to suffer from delayed decision-making in rapidly changing, highly uncertain scenarios To address these shortcomings, this article introduces a fuzzy inference-based adaptive multistrategy-DMOEAs (FIAMS-DMOEA). This approach is designed to enhance real-time responsiveness to sudden environmental changes and mitigate decision-making latency. In the proposed method, a randomly dynamic fuzzy system serves as the foundation for population-level adaptability, enabling the algorithm to cope with highly uncertain environmental dynamics. This is further augmented by a multistrategy adaptive response mechanism (MSAR) that improves overall adaptability. By leveraging fuzzy rules, the algorithm can perceive environmental uncertainty in real time and design differentiated migration strategies, thereby establishing a robust foundation for subsequent optimization. The adaptive response mechanism centers on a multistrategy weight update method based on individual dimensional effects, which evaluates individual contributions from a dimension-specific perspective. Extensive experimental results on a suite of 32 benchmark DMOPs demonstrate that FIAMS-DMOEA consistently outperforms five state-of-the-art DMOEAs in overall performance.

Much of the recent work on traffic forecasting relies on two implicit simplifications: representing the road network as an undirected graph and adopting temporally symmetric encoders within the historical observation window. These choices may obscure asymmetric predictive relations among sensors and the chronological ordering of intermediate temporal representations. CausalST addresses these limitations jointly. For spatial modeling, separate source and destination embeddings are assigned to each sensor to construct a learned directed adjacency under road-topology constraints. On the temporal side, dilated causal convolutions serve as a temporal inductive bias, ensuring that the representation at each historical position depends only on current and earlier observations. Delay-aware graph propagation aggregates current and lagged neighbor states over predefined discrete lags. A parallel spatial attention branch captures nonlocal dependencies beyond the physical topology, while a gated fusion unit adaptively integrates the temporal, graph-propagation, and spatial-attention representations. Experiments on PeMS03, PeMS04, and PeMS08 show that CausalST achieves the lowest MAPE among all compared methods while remaining competitive in MAE and RMSE. Ablation results reveal non-additive interactions between directed weighting and delayed aggregation, with the full configuration attaining the lowest MAE on both evaluated datasets.