On page 7 the authors mentioned that each dataset is partitioned into the training 60 validation 10 and testing 30 sets But I am not sure how all the experiments were conducted using five-fold cross-v

Five-fold cross-validation can still be used even if the dataset has been explicitly split into training, validation, and testing sets. In this case, the training set is divided into five equal parts, and each part is used as a validation set while the remaining four parts are used as the training set. This process is repeated five times, with each part used once as the validation set. The final performance is then reported as the average performance across the five iterations. This technique helps to reduce the impact of random variations in the dataset and provides a more reliable estimate of the model's performance