In multi-view multi-label (MVML) classification, each sample is represented by multiple heterogeneous views and annotated with multiple labels. Existing methods typically exploit pairwise semantic relationships to mine intra-view correlations and align inter-view features for generating structural representations. However, these methods ignore the direct expression of high-order semantic similarities and alignments from a group perspective, which necessitates multi-step aggregation for subsequent feature fusion, leading to the inefficient and incomplete integration of key semantic information. To overcome this limitation, we propose a novel hypergraph-based MVML method with Adaptive High-Order Semantic Fusion (HyperAHSF), which leverages hypergraphs to adaptively model group-level semantic similarities within each view and group-level semantic alignments across different views, enabling more effective feature fusion. Specifically, we first construct view-specific hyperedges by selecting multiple groups of node representations exhibiting high semantic similarity, which captures the group-level semantic similarities within each view, forming view-specific hypergraphs. Furthermore, we establish cross-view hyperedges to connect the multi-view node representations of each sample, which characterizes the group-level semantic alignments across different views, accordingly forming a unified multi-view hypergraph. Afterwards, we employ hypergraph neural networks to efficiently aggregate view-specific information and consensus information from their corresponding hypergraphs via group-level message passing. During the passing process, we impose a label-driven contrastive loss on the consensus information to encourage these representations to cluster toward their corresponding class prototypes, enhancing their discriminability. Finally, the consensus information together with the view-specific information is jointly integrated for multi-label classification. Extensive experiments demonstrate that HyperAHSF outperforms other state-of-the-art methods.

For the situation of the robot's foot soles rotating around their edges, the current posture balance control methods only used linear controllers and ignored the system's nonlinearity. For this problem, we propose a posture balance control method, which actively attenuate kinetic energy of the robot. Based on simplified dynamics model established for the foot rotating situation, our control law is deduced to adjust the amplitude of the ground contact force (GCF) and the angular acceleration of the robot foot rotation simultaneously. Then the posture balance controller against the impact force disturbance is designed. Stability of the foot rotation phase space is analyzed for our controller and other two existing controllers. Also, the situation of no balance controller is analyzed as a presentation of the system's passive characteristic. Then area of the stable region is compared between these three controllers. Simulations under frontal impact disturbances are also conducted. The results demonstrate that, our controller is able to resist stronger impact disturbance and make the robot recover its balance in a shorter time. This indicates that, compared with other posture control methods, the proposed control method makes better use of the robot joint motion to attenuate the robot's kinetic energy.