The recent developments in the research area have significantly advanced the automation and digitisation of archaeological documentation, the classification of pediatric wrist fractures, and the detection of digital image forgeries. In the realm of archaeology, there has been a notable shift towards leveraging deep learning for the automated digitisation of legacy data, enhancing both efficiency and accuracy. This trend is exemplified by frameworks that not only automate the detection and classification of archaeological artifacts but also ensure the long-term preservation and reusability of digitised data. In the medical field, there is a growing interest in integrating multiple data modalities to improve the accuracy of fracture classification, particularly in pediatric cases. This approach has shown promising results, with models achieving performance levels comparable to experienced radiologists. Lastly, in the domain of digital forensics, there is a surge in the development of open-source libraries that simplify the process of forgery detection, making advanced methods more accessible to the broader community. These libraries are designed with modularity and extensibility in mind, facilitating the integration of new methods and datasets. Overall, these advancements highlight a move towards more automated, integrated, and accessible solutions across various fields.