# CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow

arXiv: https://arxiv.org/abs/2511.21653 · HTML: https://mlsanity.com/paper/2511.21653/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 55 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport](https://mlsanity.com/paper/2006.00104/) (2020)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment](https://mlsanity.com/paper/2204.03646/) (2022)
- [Learning To Score Olympic Events](https://mlsanity.com/paper/1611.05125/) (2016)
- [Uncertainty-aware Score Distribution Learning for Action Quality Assessment](https://mlsanity.com/paper/2006.07665/) (2020)
- [Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model](https://mlsanity.com/paper/2309.06284/) (2023)
- [Group-aware Contrastive Regression for Action Quality Assessment](https://mlsanity.com/paper/2108.07797/) (2021)
- [On the Design Fundamentals of Diffusion Models: A Survey](https://mlsanity.com/paper/2306.04542/) (2023)
- [Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering](https://mlsanity.com/paper/2207.12647/) (2022)
- [LOGO: A Long-Form Video Dataset for Group Action Quality Assessment](https://mlsanity.com/paper/2404.05029/) (2024)
- [FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment](https://mlsanity.com/paper/2405.06887/) (2024)
- [Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation](https://mlsanity.com/paper/2502.05534/) (2025)
- [Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs](https://mlsanity.com/paper/2203.03990/) (2022)
- [Masked Images Are Counterfactual Samples for Robust Fine-tuning](https://mlsanity.com/paper/2303.03052/) (2023)
- [Multimodal Action Quality Assessment](https://mlsanity.com/paper/2402.09444/) (2024)
- [A Comprehensive Survey of Action Quality Assessment: Method and Benchmark](https://mlsanity.com/paper/2412.11149/) (2024)
- [CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment](https://mlsanity.com/paper/2404.13999/) (2024)
- [Visual Causal Scene Refinement for Video Question Answering](https://mlsanity.com/paper/2305.04224/) (2023)
- [MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment](https://mlsanity.com/paper/2403.04398/) (2024)
- [Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2212.08526/) (2022)
- [PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction](https://mlsanity.com/paper/2505.19972/) (2025)
- [FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment](https://mlsanity.com/paper/2503.23911/) (2025)
- [Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization](https://mlsanity.com/paper/2510.06842/) (2025)

## Abstract (arXiv)

Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially challenging since it requires modeling extended temporal dynamics while remaining robust to contextual confounders. Existing approaches either depend on costly annotations or rely on unidirectional temporal modeling, making them vulnerable to spurious correlations and unstable long-term representations. To this end, we propose CaFlow, a unified framework that integrates counterfactual de-confounding with bidirectional time-conditioned flow. The Causal Counterfactual Regularization (CCR) module disentangles causal and confounding features in a self-supervised manner and enforces causal robustness through counterfactual interventions, while the BiT-Flow module models forward and backward dynamics with a cycle-consistency constraint to produce smoother and more coherent representations. Extensive experiments on multiple long-term AQA benchmarks demonstrate that CaFlow achieves state-of-the-art performance. Code is available at https://github.com/Harrison21/CaFlow