Existing multi-view 3D human pose estimation methods heavily rely on precise extrinsic calibration, which significantly restricts their practical deployment in uncontrolled environments. To address this limitation, we propose an Extrinsic Parameter-free Multi-view 3D Human Skeleton Estimation (EFMK) framework with three technical contributions. First, a Local-Global Pose Embedding scheme is proposed to simultaneously capture the fine-grained joint dependencies while establishing cross-view correspondences. Second, a Spatial-View Joint Transformer architecture is developed with three dedicated components: (1) Feature Transformation Modulation generates adaptive modulation vectors for distinct tokens to model heterogeneous relationship patterns; (2) Prior Knowledge Enhancement systematically integrates human kinematic constraints and multi-view geometric priors into attention computation through structural topology encoding; (3) Spatial-View Joint Attention implements decoupled spatial-view attention computation followed by joint distribution modeling to capture hierarchical spatial-view dependencies. Third, a Bone-wise Reprojection-based Multi-view Aggregation mechanism is introduced to consolidate multiple 3D outputs into a single, higher-quality 3D pose for practical applications. Extensive experiments on three benchmarks demonstrate that our method achieves state-of-the-art performance while maintaining a compact model size. Code and results are available at https://github.com/Z-Z-J/EFMK.

Unmanned aerial vehicles (UAVs) have emerged as a promising solution to support ground networks. In UAV-enabled wireless powered communication networks (WPCNs), the UAV provides data collection (DC) and energy transmission (ET) services for ground energy harvesting (EH) IoT devices. In view of the limited working efficiency of a single UAV, we propose a multi-UAV-enabled WPCN system. In order to further improve the efficiency of the system, we jointly optimize the data transmission performance of the network and the average harvested energy of IoT devices by designing the trajectories of the UAVs. The high mobility of UAVs causes the rapid change of channels, which leads to limitations of the centralized management scheme. Therefore, the problem is modeled as a multi-agent deep reinforcement learning (MADRL) problem. The scenario of multiple UAVs working collaboratively is formulated as a decentralized partially observable Markov decision process (Dec-POMDP). We develop a multi-agent deep deterministic policy gradient (MADDPG)-based approach to design UAVs' trajectories by adjusting the flying velocity and direction. Simulation results prove that the proposed algorithm far exceeds the benchmark schemes.