FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment

by   Jinglin Xu, et al.
Tsinghua University

Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability. We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable. Towards this goal, we construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures. We also propose a procedure-aware approach for action quality assessment, learned by a new Temporal Segmentation Attention module. Specifically, we propose to parse pairwise query and exemplar action instances into consecutive steps with diverse semantic and temporal correspondences. The procedure-aware cross-attention is proposed to learn embeddings between query and exemplar steps to discover their semantic, spatial, and temporal correspondences, and further serve for fine-grained contrastive regression to derive a reliable scoring mechanism. Extensive experiments demonstrate that our approach achieves substantial improvements over state-of-the-art methods with better interpretability. The dataset and code are available at <>.


page 1

page 3

page 5

page 8

page 11


Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating

The fine-grained action analysis of the existing action datasets is chal...

Hand Hygiene Assessment via Joint Step Segmentation and Key Action Scorer

Hand hygiene is a standard six-step hand-washing action proposed by the ...

What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment

Can performance on the task of action quality assessment (AQA) be improv...

Semantic-aware Contrastive Learning for More Accurate Semantic Parsing

Since the meaning representations are detailed and accurate annotations ...

Group-aware Contrastive Regression for Action Quality Assessment

Assessing action quality is challenging due to the subtle differences be...

TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting

Counting repetitive actions are widely seen in human activities such as ...

Action Quality Assessment using Siamese Network-Based Deep Metric Learning

Automated vision-based score estimation models can be used as an alterna...

Code Repositories


FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment

view repo

Please sign up or login with your details

Forgot password? Click here to reset