PlumX Metrics
Embed PlumX Metrics

Auto-encoding score distribution regression for action quality assessment

Neural Computing and Applications, ISSN: 1433-3058, Vol: 36, Issue: 2, Page: 929-942
2024
  • 5
    Citations
  • 0
    Usage
  • 10
    Captures
  • 0
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Citations
    5
    • Citation Indexes
      5
  • Captures
    10

Article Description

Assessing the quality of actions in videos is a challenging vision task, as the relationship between videos and action scores can be difficult to model. Consequently, extensive research has been conducted on action quality assessment (AQA) in the literature. Traditional AQA methods treat the problem as a regression task to learn the underlying mappings between videos and action scores. However, previous approaches overlook the presence of data uncertainty in AQA datasets. To address aleatoric uncertainty, we have developed a plug-and-play module called distribution auto-encoder (DAE). DAE encodes videos into distributions and utilizes the reparameterization trick to sample scores, which enables a more accurate mapping between videos and scores. Additionally, we use a likelihood loss to learn the uncertainty parameters. We have evaluated our approach on publicly available datasets, and extensive experiments demonstrate that DAE achieves state-of-the-art performance with the Spearman’s correlation metric of 82.58%, 92.32%, and 76.00% on the AQA-7, MTL-AQA, and JIGSAWSS datasets, respectively. Furthermore, plug-and-play experiments also demonstrate the extensibility of DAE. Our code is available at https://github.com/InfoX-SEU/DAE-AQA .

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know