Augmented reality (AR) demonstrates great promise in science education. However, students’ conceptions of learning when they learn science using AR are currently unclear. This study aimed to analyze learners’ views and scientific epistemic beliefs on learning science. Eighty-two elementary school students in grades 4–6 participated in a two-week course on the introduction to sound. The intervention adopted inquiry-based learning utilizing three AR software programs that integrated multisensory channels. The data were collected through Cheng’s Conceptions of Learning Science by AR (CLSAR) questionnaire and Learners’ Scientific Epistemic Beliefs (SEB) questionnaire. The results show that students in this study generally had positive conceptions of learning science and a high level of scientific epistemic beliefs. Moreover, gender differences existed in the relationship between CLASR and SEB. This study contributed to the currently unresolved discussion of the impact of demographic differences on students’ learning, indicating that AR can be used to enhance senior students’ learning of science in elementary schools.
Skeleton representation learning offers substantial advantages for action recognition by encoding intricate motion details and spatial–temporal dependencies among joints. However, fully supervised approaches necessitate large amounts of annotated data, which are often labor-intensive and costly to acquire. In this work, we propose the Spatial–Temporal Heatmap Masked Autoencoder (STH-MAE), a novel self-supervised framework tailored for skeleton-based action recognition. Unlike coordinate-based methods, STH-MAE adopts heatmap volumes as its primary representation, mitigating noise inherent in pose estimation while capitalizing on advances in Vision Transformers. The framework constructs a spatial–temporal heatmap (STH) by aggregating 2D joint heatmaps across both spatial and temporal axes. This STH is partitioned into non-overlapping patches to facilitate local feature learning, with a masking strategy applied to randomly conceal portions of the input. During pre-training, a Vision Transformer-based autoencoder equipped with a lightweight prediction head reconstructs the masked regions, fostering the extraction of robust and transferable skeletal representations. Comprehensive experiments on the NTU RGB+D 60 and NTU RGB+D 120 benchmarks demonstrate the superiority of STH-MAE, achieving state-of-the-art performance under multiple evaluation protocols.
In the realm of Industry 5.0, the incorporation of Artificial Intelligence (AI) in overseeing workers, machinery, and industrial systems is essential for fostering a human-centric, sustainable, and resilient industry. Despite technological advancements, the construction industry remains largely labor intensive, with site management and interventions predominantly reliant on manual judgments, leading to inefficiencies and various challenges. This research emphasizes identifying unsafe behaviors and risks within construction environments by employing AI. Given the continuous emergence of unsafe behaviors that requires certain caution, it is imperative to adapt to these novel categories while retaining the knowledge of existing ones. Although deep convolutional neural networks have shown excellent performance in behavior recognition, they traditionally function as predefined multi-way classifiers, which exhibit limited flexibility in accommodating emerging unsafe behavior classes. Addressing this issue, this study proposes a versatile and efficient recognition model capable of expanding the range of unsafe behaviors while maintaining the recognition of both new and existing categories. Adhering to the continual learning paradigm, this method integrates two types of complementary prompts into the pre-trained model: task-invariant prompts that encode knowledge shared across tasks, and task-specific prompts that adapt the model to individual tasks. These prompts are injected into specific layers of the frozen backbone to guide learning without requiring a rehearsal buffer, enabling effective recognition of both new and previously learned unsafe behaviors. Additionally, this paper introduces a benchmark dataset, Split-UBR, specifically constructed for continual unsafe behavior recognition on construction sites. To rigorously evaluate the proposed model, we conducted comparative experiments using average accuracy and forgetting as metrics, and benchmarked against state-of-the-art continual learning baselines. Results on the Split-UBR dataset demonstrate that our method achieves superior performance in terms of both accuracy and reduced forgetting across all tasks, highlighting its effectiveness in dynamic industrial environments.