PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction

TL;DR

This paper introduces PHI, a novel method that effectively reduces domain shift in long-term Action Quality Assessment by using progressive learning and contrastive regularization, achieving state-of-the-art results.

Contribution

The paper proposes Progressive Hierarchical Instruction (PHI), combining flow matching and contrastive regularization to address domain shifts in long-term AQA, a challenge not well handled by existing methods.

Findings

PHI outperforms previous methods on three long-term AQA datasets.

The flow matching approach reduces feature domain gap effectively.

Contrastive regularization improves fine-grained cue learning.

Abstract

Long-term Action Quality Assessment (AQA) aims to evaluate the quantitative performance of actions in long videos. However, existing methods face challenges due to domain shifts between the pre-trained large-scale action recognition backbones and the specific AQA task, thereby hindering their performance. This arises since fine-tuning resource-intensive backbones on small AQA datasets is impractical. We address this by identifying two levels of domain shift: task-level, regarding differences in task objectives, and feature-level, regarding differences in important features. For feature-level shifts, which are more detrimental, we propose Progressive Hierarchical Instruction (PHI) with two strategies. First, Gap Minimization Flow (GMF) leverages flow matching to progressively learn a fast flow path that reduces the domain gap between initial and desired features across shallow to deep layers. Additionally, a temporally-enhanced attention module captures long-range dependencies essential for AQA. Second, List-wise Contrastive Regularization (LCR) facilitates coarse-to-fine alignment by comprehensively comparing batch pairs to learn fine-grained cues while mitigating domain shift. Integrating these modules, PHI offers an effective solution. Experiments demonstrate that PHI achieves state-of-the-art performance on three representative long-term AQA datasets, proving its superiority in addressing the domain shift for long-term AQA.