Action assessment is a task of assessing the performance of an action. It is widely applicable to many real-world scenarios such as medical treatment and sporting events. However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e.g.,between persons and objects); and this limitation undermines their ability to assess actions containing asymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions. In this work, we model the asymmetric interactions among agents for action assessment. In particular, we propose anasymmetric interaction module (AIM), to explicitly model asymmetric interactions between intelligent agents within an action, where we group these agents into a primary one (e.g., human) and secondary ones(e.g., objects). We perform experiments on JIGSAWS dataset containing surgical actions, and additionally collect a new dataset,TASD-2,for interactive sporting actions. The experimental results on two interactive action datasets show the effectiveness of our model, and ourmethod achieves state-of-the-art performance. The extended experimenton AQA-7dataset also demonstrates the generalization capability of our framework to conventional action assessment.
© Copyright 2020 Computer Vision - ECCV 2020. Lecture Notes in Computer Science. Published by Springer. All rights reserved.