In recent years, human action recognition has received increasing attention as a significant function of human–machine interaction. The human skeleton is one of the most effective representations of human actions because it is highly compact and informative. Many recent skeleton-based action recognition methods are based on graph convolutional networks (GCNs) as they preserve the topology of the human skeleton while extracting features. Although many of these methods give impressive results, there are some limitations in robustness, interoperability, and scalability. Furthermore, most of these methods ignore the underlying information of view direction and rely on the model to learn how to adjust the view from training data. In this work, we propose VW-SC3D, a spatial–temporal model with view weighting for skeleton-based action recognition. In brief, our model uses a sparse 3D CNN to extract spatial features for each frame and uses a transformer encoder to obtain temporal information within the frames. Compared to GCN-based methods, our method performs better in extracting spatial–temporal features and is more adaptive to different types of 3D skeleton data. The sparse 3D CNN makes our model more computationally efficient and more flexible. In addition, a learnable view weighting module enhances the robustness of the proposed model against viewpoint changes. A test on two different types of datasets shows a competitive result with SOTA methods, and the performance is even better in view-changing situations.

Colon adenocarcinoma (COAD) is the third most common malignancy globally, with recurrence and metastasis driving cancer-related mortality. Improved biomarkers and preventive strategies are urgently needed. Coiled-coil domain containing 78 (CCDC78) is believed to be linked with tumor progression, yet its specific role in COAD remains largely uncharacterized. This study elucidates the prognostic and functional roles of CCDC78 in COAD through integrated bioinformatics and experimental validation. Multi-omics data, The Cancer Genome Atlas (TCGA)-COAD cohort and GSE39582 database, revealed CCDC78 overexpression correlated with advanced TNM stages (p < 0.001), reduced drug sensitivity, and poorer overall survival (HR = 1.84, 95% CI: 1.23–2.74). Cox regression identified CCDC78 as an independent prognostic factor, integrated into a validated nomogram. Functional enrichment linked CCDC78 to cell cycle regulation, with GSCA analysis showing copy number variation (CNV)-driven pathway activation. Experimental validation demonstrated CCDC78 knockdown suppressed proliferation and migration in COAD cells. Mechanistically, CCDC78 potentially downregulates CDKN1A-CDK4 and activates E2F1 signaling. These findings establish CCDC78 as both a prognostic biomarker and therapeutic target. The study bridges computational predictions with functional evidence, proposing CCDC78 as a novel oncogenic driver in COAD through cell cycle dysregulation. Future investigations will employ in vivo models to delineate its molecular mechanisms.