# Action Quality Assessment Across Multiple Actions

## TL;DR

This paper investigates whether a single model can assess the quality of different actions by transferring knowledge across multiple actions, using a new dataset with expert-judged quality scores.

## Contribution

It introduces a new dataset and demonstrates that a unified model can effectively evaluate multiple actions, highlighting the potential for knowledge transfer in action quality assessment.

## Key findings

- Single model improves across multiple actions
- Knowledge transfer enhances assessment accuracy
- Unified approach reduces the need for action-specific models

## Abstract

Can learning to measure the quality of an action help in measuring the quality of other actions? If so, can consolidated samples from multiple actions help improve the performance of current approaches? In this paper, we carry out experiments to see if knowledge transfer is possible in the action quality assessment (AQA) setting. Experiments are carried out on our newly released AQA dataset (http://rtis.oit.unlv.edu/datasets.html) consisting of 1106 action samples from seven actions with quality scores as measured by expert human judges. Our experimental results show that there is utility in learning a single model across multiple actions.