Human action recognition (HAR) in RGB-D videos has been widely investigated since the release of affordable depth sensors. Currently, unimodal approaches (e.g., skeleton-based and RGB video-based) have realized substantial improvements with increasingly larger datasets. However, multimodal methods specifically with model-level fusion have seldom been investigated. In this paper, we propose a model-based multimodal network (MMNet) that fuses skeleton and RGB modalities via a model-based approach. The objective of our method is to improve ensemble recognition accuracy by effectively applying mutually complementary information from different data modalities. For the model-based fusion scheme, we use a spatiotemporal graph convolution network for the skeleton modality to learn attention weights that will be transferred to the network of the RGB modality. Extensive experiments are conducted on five benchmark datasets: NTU RGB+D 60, NTU RGB+D 120, PKU-MMD, Northwestern-UCLA Multiview, and Toyota Smarthome. Upon aggregating the results of multiple modalities, our method is found to outperform state-of-the-art approaches on six evaluation protocols of the five datasets; thus, the proposed MMNet can effectively capture mutually complementary features in different RGB-D video modalities and provide more discriminative features for HAR. We also tested our MMNet on an RGB video dataset Kinetics 400 that contains more outdoor actions, which shows consistent results with those of RGB-D video datasets.

Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: fine-tuning, prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning.

Skeleton-based exercise assessment focuses on evaluating the correctness or quality of an exercise performed by a subject. Skeleton data provide two groups of features (i.e., position and orientation), which existing methods have not fully harnessed. We previously proposed an ensemble-based graph convolutional network (EGCN) that considers both position and orientation features to construct a model-based approach. Integrating these types of features achieved better performance than available methods. However, EGCN lacked a fusion strategy across the data, feature, decision, and model levels. In this paper, we present an advanced framework, EGCN++, for rehabilitation exercise assessment. Based on EGCN, a new fusion strategy called MLE-PO is proposed for EGCN++; this technique considers fusion at the data and model levels. We conduct extensive cross-validation experiments and investigate the consistency between machine and human evaluations on three datasets: UI-PRMD, KIMORE, and EHE. Results demonstrate that MLE-PO outperforms other EGCN ensemble strategies and representative baselines. Furthermore, the MLE-PO's model evaluation scores are more quantitatively consistent with clinical evaluations than other ensemble strategies.

Efficient laparoscopic scene segmentation holds significant potential for surgical assistive intelligence and image-guided task autonomy in robotic surgery. However, the abdominal cavity with intricate tissues and surgical tools under varying conditions challenges the balance between segmentation accuracy and efficiency. To resolve this problem, we propose PLDKD-Net, a novel pixel-level student-teacher knowledge distillation (KD) framework, in which the student model selectively distills the teacher’s profound knowledge while exploring rich visual features with a graph-based fusion mechanism for efficient segmentation. Specifically, we first introduce our confidence-based KD (Confi-KD) scheme, in which a pixel-level confidence generator (PCG) is proposed to assess the teacher’s performance by discriminatively evaluating its probability map and the raw image, generating a confidence map that can facilitate a selective KD for the student model. To balance the model’s accuracy and efficiency, we devise a novel heterogeneous student architecture with a bi-stream visual parsing pipeline to capture multi-scale and inter-spatial visual features. These features are then fused using a relational graph convolutional network (RGCN), which can adaptively tune the fusion degrees of multi-latent knowledge, ensuring visual parsing completeness while avoiding computational redundancy. We extensively validate PLDKD-Net on two public laparoscopic benchmarks, Endovis18 and CholecSeg8K, and in-house surgical videos. Benefiting from our schemes, the experimental outcomes demonstrate superior quantitative and qualitative performance compared to state-of-the-art methods. With the selective KD mechanism, our model yields competitive or even higher performance than the cumbersome teacher model while exhibiting quasi-real-time efficiency, which demonstrates its greater potential for intelligent robotic surgical scene understanding.

Adolescence is marked by strong creative impulses but limited strategies for structured expression, often leading to frustration or disengagement. While generative AI lowers technical barriers and delivers efficient outputs, its role in fostering adolescents’ expressive growth has been overlooked. We propose MusicScaffold, an adolescent-centered framework that transforms classical AI roles from broad conceptualizations into stage-specific, actionable developmental scaffolds designed to make expressive strategies transparent and learnable and to support adolescents in mastering creative expression. In a four-week study with middle school students (ages 12–14), MusicScaffold enhanced cognitive specificity, behavioral regulation, and affective autonomy in music creation. By reframing generative AI as a scaffold rather than a generator, this work bridges the machine efficiency of generative systems with human growth in adolescent creativity education.

Restaurants, as small hospitality businesses, are inherently vulnerable, making accurate survival prediction crucial. Previous studies have demonstrated the significance of user reviews and incorporated diverse review?derived factors, yet they have largely overlooked the large?scale network formed by user–restaurant interactions. How restaurant survival is influenced by the review network remains insufficiently explored. To fill this gap, leveraging network embeddedness theory, we statistically analyze the impact of two dimensions of embeddedness, structural and positional, on each restaurant's survival. Utilizing two real-world review datasets, the newly curated OpenRice and the well-established Yelp, our results reveal that a restaurant's network embeddedness and its temporal evolution positively correlate with its survival. Building on this insight, we propose a Dynamic Embeddedness-aware Graph Neural Network, DyE-GNN, for restaurant survival prediction. DyE-GNN not only explicitly integrates network embeddedness theory to guide the model design but also leverages domain knowledge to enable robust adaptability. Extensive experiments on both datasets confirm the superiority of DyE-GNN, underscoring the importance of network embeddedness attention, temporal dynamics, and survival knowledge of peer restaurants. Visualizations further demonstrate that network embeddedness facilitates the identification of at-risk restaurants at the network margin.