The field of spatiotemporal analysis and AI applications is moving towards more accurate and efficient methods for analyzing and understanding complex data from various domains, including forestry and healthcare. Researchers are leveraging deep learning-based frameworks and self-supervised learning techniques to develop innovative solutions for real-world problems. Notably, the use of 3D video classification and joint spatiotemporal representation learning is showing great potential for applications such as operational monitoring, efficiency analysis, and intelligent surgical systems. In the realm of healthcare, automated measurement techniques are being developed to support dynamic evaluation and monitoring of critical biomarkers. Some noteworthy papers in this area include:

• A study on spatiotemporal analysis of forest machine operations, which demonstrated strong performance in classifying forestry operations from dashcam video footage.
• An introduction of a large-scale self-supervised video foundation model for intelligent surgery, which achieved state-of-the-art results in capturing dynamic surgical contexts.
• A novel method for automated measurement of optic nerve sheath diameter using ocular ultrasound video, which showed high accuracy and potential for clinical application.