FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment

TL;DR

FineParser introduces a fine-grained spatio-temporal action parsing approach that improves human-centric action quality assessment by focusing on target action regions, enhancing interpretability and accuracy in diverse action evaluation scenarios.

Contribution

The paper proposes FineParser, a novel model for fine-grained spatial-temporal action parsing, and introduces the FineDiving-HM dataset with detailed annotations to advance action quality assessment.

Findings

Outperforms state-of-the-art methods in action quality assessment.

Supports more fine-grained action understanding tasks.

Enhances interpretability and credibility of AQA systems.

Abstract

Existing action quality assessment (AQA) methods mainly learn deep representations at the video level for scoring diverse actions. Due to the lack of a fine-grained understanding of actions in videos, they harshly suffer from low credibility and interpretability, thus insufficient for stringent applications, such as Olympic diving events. We argue that a fine-grained understanding of actions requires the model to perceive and parse actions in both time and space, which is also the key to the credibility and interpretability of the AQA technique. Based on this insight, we propose a new fine-grained spatial-temporal action parser named \textbf{FineParser}. It learns human-centric foreground action representations by focusing on target action regions within each frame and exploiting their fine-grained alignments in time and space to minimize the impact of invalid backgrounds during the assessment. In addition, we construct fine-grained annotations of human-centric foreground action masks for the FineDiving dataset, called \textbf{FineDiving-HM}. With refined annotations on diverse target action procedures, FineDiving-HM can promote the development of real-world AQA systems. Through extensive experiments, we demonstrate the effectiveness of FineParser, which outperforms state-of-the-art methods while supporting more tasks of fine-grained action understanding. Data and code are available at \url{https://github.com/PKU-ICST-MIPL/FineParser_CVPR2024}.