Learning Effective Skeletal Representations on RGB Video for Fine-Grained Human Action Quality Assessment

In this paper, we propose an integrated action classification and regression learning framework for the fine-grained human action quality assessment of RGB videos. On the basis of 2D skeleton data obtained per frame of RGB video sequences, we present an effective representation of joint trajectories to train action classifiers and a class-specific regression model for a fine-grained assessment of the quality of human actions. To manage the challenge of view changes due to camera motion, we develop a self-similarity feature descriptor extracted from joint trajectories and a joint displacement sequence to represent dynamic patterns of the movement and posture of the human body. To weigh the impact of joints for different action categories, a class-specific regression model is developed to obtain effective fine-grained assessment functions. In the testing stage, with the supervision of the action classifier's output, the regression model of a specific action category is selected to assess the quality of skeleton motion extracted from the action video. We take advantage of the discrimination of the action classifier and the viewpoint invariance of the self-similarity feature to boost the performance of the learning-based quality assessment method in a realistic scene. We evaluate our proposed method using diving and figure skating videos of the publicly available MIT Olympic Scoring dataset, and gymnastic vaulting videos of the recent benchmark University of Nevada Las Vegas (UNLV) Olympic Scoring dataset. The experimental results show that the proposed method achieved an improved performance, which is measured by the mean rank correlation coe fficient between the predicted regression scores and the ground truths.