Drones are widely used in fields such as aerial photography and security inspection, owing to their high mobility and wide field of view. Compared to a single drone, multi-drone systems can capture complementary information from different viewpoints, effectively addressing complex tracking scenarios such as occlusion, viewpoint changes, and target disappearance. However, existing multi-drone tracking methods often suffer from inadequate feature representation and inefficient inter-drone information fusion. To tackle these challenges, we propose FAEMTrack, a novel multi-drone tracking framework that integrates a feature-augmented embedding module (FAEM) with an advanced cross-drone fusion mechanism. FAEM enhances spatial-semantic feature encoding by replacing conventional convolutional layers with a multi-scale depthwise convolution block (MSDB) and spatial attention mechanism (SA), significantly improving the discriminative power of target features across different drone perspectives. Furthermore, to better utilize complementary information from different viewpoints, we introduce a cross-drone fusion strategy based on response confidence and entropy-weighted fusion, dynamically integrating information from multi-drone and promoting adaptive collaboration among them. Extensive experiments on the MDOT benchmark demonstrate that FAEMTrack outperforms existing state-of-the-art single-drone and multi-drone tracking methods in both tracking accuracy and robustness, showcasing its superior performance in complex scenarios. The source code and trained models will be available at https://github.com/wjh-scut/FAEMTrack.

Representation and generative learning mutually enhance each other across various domains. However, in point cloud processing, these models are typically trained independently, failing to leverage their synergy. To integrate 3D representation and generative learning deeply, we propose the Point-Mge framework. This framework uses a vector quantized variational autoencoder to reconstruct an occupancy neural field of 3D shapes, learning discrete semantic features of point patches. We introduce sliding masking ratios to smoothly transition from representation to generative learning. Additionally, our method exhibits good generalization in high-capacity models and achieves new state-of-the-art results in multiple down-stream tasks. In shape classification, Point-Mge attained 94.3% (+1.1%) on the ModelNet40 dataset and 92.9% (+5.5%) on the ScanObjectNN dataset. Experimental results also demonstrate that Point-Mge can generate high-quality 3D shapes in both unconditional and conditional settings. Code is available at https://github.com/robhlzeng/Point-Mge.

Summary Artificial bee colony (ABC) is a popular intelligent algorithm that is widely applied to many optimization problems. However, it is challenging for ABC to solve many‐objective optimization problems (MaOPs). To tackle this issue, this article proposes a many‐objective ABC based on multi‐population (called MMaOABC) for MaOPs. In MMaOABC, the population is divided into multiple sub‐populations, and each sub‐population optimizes one objective. Three search strategies are constructed based on multiple sub‐populations to improve convergence and diversity. In the employed bee stage, some excellent solutions in multiple sub‐populations are used to guide the convergence. In the onlooker bee stage, new selection probabilities based on diversity metrics are designed to enhance the diversity. Dimensional learning is introduced in the scout bee stage to avoid falling into local minimum. In addition, environmental selection and external archives are utilized for communications among sub‐populations. To validate the performance of MMaOABC, two benchmark sets (DTLZ and MaF) with 3, 5, 8, and 15 objectives are tested. Computational results show that MMaOABC is competitive when compared with seven other many‐objective evolutionary algorithms (MaOEAs). Finally, MMaOABC is applied to many‐objective cascade reservoir scheduling. Simulation results show that MMaOABC still obtains promising performance.

Many-objective evolutionary algorithms (MaOEAs) are widely used to solve many-objective optimization problems. As the number of objectives increases, it is difficult to achieve a balance between the population diversity and the convergence. Additionally, the selection pressure decreases rapidly. To tackle these issues, this paper proposes a two-stage many-objective evolutionary algorithm with dynamic generalized Pareto dominance (called TS-DGPD). First, a two-stage method is utilized for environmental selection. The first stage employs the cosine distance to accelerate the convergence. The second stage uses L p ${L}_{p}$ -norm maintain the population diversity. Moreover, a dynamic generalized Pareto dominance (DGPD) is used to increase the selection pressure of the population. To evaluate the performance of TS-DGPD, we compare it with several other MaOEAs on two benchmark sets with 3, 5, 8, 10, 15, and 20 objectives. Experimental results show that TS-DGPO performs satisfactorily on convergence and diversity.