MTL-AQA

Overview edit

Variants: MTL-AQA

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Action Recognition - Metrics: Position Accuracy, Armstand Accuracy, Rotation Type Accuracy, No. of Somersaults Accuracy, No. of Twists Accuracy
• Action Quality Assessment - Metrics: Spearman Correlation, RL2(*100)

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• RICA2: Rubric-Informed, Calibrated Assessment of Actions (2024) -
• FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment (2024) -
• Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment (2024) -
• Auto-Encoding Score Distribution Regression for Action Quality Assessment (2021) -
• Group-aware Contrastive Regression for Action Quality Assessment (2021) -
• Improving Action Quality Assessment using Weighted Aggregation (2021) -
• Uncertainty-aware Score Distribution Learning for Action Quality Assessment (2020) -
• What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment (2019) -