In today's digital age, we are bombarded with IMAGEs from the internet, social media, and online magazines. It is fascinating how we can remember so many of these IMAGEs and their details. However, not every IMAGE is equally memorable; some stay with us more than others. Scientists have explored why this is the case. In our research, we are particularly interested in how IMAGEs that showcase Iranian life and culture stick in the memories of Iranian adults. To investigate this, we created a new collection called the SemMem dataset, which is full of culturally relevant IMAGEs. We adapted a memory game from earlier studies to test how memorable these IMAGEs are. To analyze memorability, we used two deep learning architectures, ResNet 50 and ResNet 101. These architectures helped us estimate which IMAGEs are likely to be remembered. Our findings confirmed that IMAGEs connected to Iranian culture are indeed more memorable to Iranians, highlighting the impact of familiar cultural elements on memory retention.

Document IMAGEs segmentation is one of the recent activities that have attracted researchers' attention. Unfortunately, there is no report on a benchmark dataset for Farsi document IMAGEs UNDERSTANDING and segmentations applications that be available in the web. In the current article, a benchmark IMAGE dataset for the sake of the Farsi document IMAGEs segmentation is presented, which includes 5598 IMAGEs. The provided IMAGEs are taken from the newspapers, textbooks and academic articles. Objects in the IMAGEs are categorized and labeled into six different groups to be used easily in the subsequent applications. The object groups used in the dataset are paragraph(text), figure, table, logo, mathematical equation and header. To asset the effectiveness of the proposed document IMAGE dataset, three existing well-known methods based on deep learning are implemented on it and the results are presented.