Matching images to articles is challenging and can be considered a special version of the cross-mediaretrieval problem. This notebook paper presents our solution for the MediaEval NewsImages 2023benchmarking task. We investigate the performance of pre-trained cross-modal networks. Specifically, weinvestigate two pre-trained CLIP model variations and fine-tuned one for domain adaptation. Additionally,we utilize a data augmentation technique and a method for revising the similarities produced by eitherone of the networks, i.e., a dual softmax operation, to improve our solutions’ performance. We reportthe official results for our submitted runs and additional experiments we conducted to evaluate our runsinternally. We conclude that fine-tuning benefits the performance, and it is important to consider thedata’s nature when selecting the appropriate pre-trained CLIP model.