Electronics (Basel)

Dynamic scene reconstruction has achieved significant milestones with the advent of 3D Gaussian Splatting (3DGS). However, extending this technology from geometric reconstruction to semantic understanding in dynamic environments remains a challenge. Existing methods often rely on external 2D trackers, which lead to temporal inconsistencies and semantic drift, or suffer from the high computational costs of high-dimensional feature fields. In this paper, we propose a novel framework, Gaussian Semantic Segmentation based on Color and Shape Deformation Fields (GSSBC), to address these issues. Building upon our GBC dynamic scene representation, we bind learnable semantic features to deformable Gaussian primitives. We introduce a spatiotemporal contrastive learning strategy guided by the Segment Anything Model (SAM) to enforce semantic consistency without explicit tracking. Furthermore, we employ a density-based clustering algorithm with label propagation to extract discrete object entities efficiently. Experimental results on the HyperNeRF and Neu3D datasets demonstrate that our method achieves superior segmentation accuracy and spatiotemporal stability compared to state-of-the-art approaches, enabling effective semantic understanding in complex dynamic scenes.

Full fine-tuning of large-scale vision-language models for video action recognition incurs prohibitive computational cost and often degrades pre-trained spatial representations. To address this, we propose VETA-CLIP, a Video Efficient Temporal Adaptation framework that enhances temporal modeling while preserving cross-modal alignment. By incorporating lightweight adapters into a frozen backbone, VETA-CLIP introduces only 3.55M trainable parameters (a 98% reduction compared to full fine-tuning). Our approach features two key innovations: (1) an Efficient Spatio-Temporal Attention (ESTA) mechanism with a parameter-free boundary replication temporal shift (BRTS) module, which explicitly decouples spatial and temporal attention heads to capture inter-frame dynamics while minimizing disruption to the pre-trained spatial representations; and (2) a novel Variation Loss that maximizes both local inter-frame differences and global temporal variance, encouraging the model to focus on action-related changes rather than static backgrounds. Extensive experiments on HMDB-51, UCF-101, and Something-Something v2 demonstrate that VETA-CLIP achieves competitive performance across zero-shot, base-to-novel, and few-shot protocols, while and remains competitive on the Kinetics-400 dataset. Notably, our eight-frame variant requires only 4.7 GB of peak GPU memory and 2.47 ms of inference per video, demonstrating exceptional computational efficiency alongside consistent accuracy gains.

As social robots are increasingly deployed in domains such as healthcare, education, and entertainment, there is growing demand for affective agents that can interpret users’ affective states and respond in contextually appropriate ways. Existing work has established strong foundations for emotion generation and appraisal, but the step that connects generated emotion to behavioral execution still relies heavily on model-specific rules or implicit links. We frame this issue as a Mechanism Gap and propose an Emotional BDI framework that introduces Frijda’s action tendency as an intermediate representation layer between the Affective Core and the Belief–Desire–Intention (BDI) Executor. Rather than mapping emotion directly to concrete behavior, the framework first transforms affective state into a directional action tendency and then lets BDI reasoning realize that tendency according to role and context. This creates an explicit emotion-to-behavior mediation structure through which the same emotion can be expressed differently across situations and roles. In an exploratory user evaluation with 26 participants, the proposed model received more favorable ratings than an Emotion-Driven Agent in satisfaction (p=0.010) and appropriateness (p=0.002). Compared with a Cooperative Agent, the proposed model showed a significant advantage only in satisfaction (p=0.030). These findings suggest that the proposed framework offers a useful architectural direction for affective decision making beyond direct mapping or unconditional compliance.

Ensuring physical layer security for low-altitude economic networking (LAENet) is critical due to the broadcast nature of wireless channels. In dense urban environments, multi-antenna LAENet systems are often impaired by the keyhole effect, which induces rank deficiency and poses significant security challenges. This paper investigates the secrecy performance of a multiple-input multiple-output multiple-antenna eavesdropper (MIMOME) system in LAENet with keyhole channels. Depending on the availability of channel state information (CSI) at the transmitter, three wiretap scenarios are considered: (i) broadcasting, (ii) passive eavesdropping, and (iii) spoofing. For each scenario, the optimal precoder is designed to maximize the secrecy transmission rate. Based on these designs, we derive closed-form expressions for the secrecy outage probability (SOP) and average secrecy rate (ASR). To provide insights into the effect of keyholes on secrecy diversity order and array gain under this severe rank-deficiency structure, we also obtain asymptotic expressions for SOP and ASR in the high signal-to-noise ratio (SNR) regime using the Mellin transform. Numerical results validate the analytical expressions and illustrate the influence of key parameters on secrecy performance. These findings provide meaningful guidance for the secure design of future LAENet deployments.

Autonomous robots are increasingly integrated into social contexts, making affective human–robot interaction (HRI) critical for their effectiveness and acceptance. However, existing research remains dispersed across domains and techniques, lacking a unified framework to characterize core robotic capabilities. To address this gap, we adopt a capability-oriented perspective and conduct a comprehensive literature review, through which we propose a structured taxonomy of capabilities for robots in affective HRI. The taxonomy comprises five core dimensions: perception (recognizing human internal states), strategy (planning responses based on human states and context), expression (conveying robot lifelikeness and social presence), sustainability (maintaining effective and reliable operation over time), and ethics (ensuring behavior within ethical constraints). By organizing diverse research efforts into a structured framework, this taxonomy provides a systematic foundation for designing socially competent robots and guiding future research.