A novel blind action quality assessment based on multi-headed GRU network and attention mechanism

Abstract

Objective action quality assessment (AQA) is a complex machine vision task because existing AQA assessment models can't effectively fit the subjective assessment. To address this issue, we propose a novel blind action quality assessment method. By processing the video data with spatial and temporal features, the performance of the model is effectively improved. In addition, we also proposed a new loss function to better train the model, which combines the information entropy of the data. Finally, the experimental results show that on the existing datasets AQA-7 and JIGSAWS are significantly improved, reaching 0.63 and 0.57, respectively.