Action Quality Assessment Across Multiple Actions

15 Dec 2018  ·  Paritosh Parmar, Brendan Tran Morris ·

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.

PDF Abstract

Datasets


Introduced in the Paper:

AQA-7

Used in the Paper:

UCF101 Sports-1M

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Quality Assessment AQA-7 Single-Action C3D-SVR Spearman Correlation 69.37% # 7
Action Quality Assessment AQA-7 Single-Action C3D-LSTM Spearman Correlation 61.65% # 9
Action Quality Assessment AQA-7 All-Action C3D-LSTM Spearman Correlation 64.78% # 8

Methods


No methods listed for this paper. Add relevant methods here