# Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

arXiv: https://arxiv.org/abs/2501.14356 · HTML: https://mlsanity.com/paper/2501.14356/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2025.

## Built on by (most cited first, 5 of 5)

- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [Multi-Grained Feature Pruning for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2503.05365/) (2025)
- [Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation](https://mlsanity.com/paper/2603.05929/) (2026)
- [NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose Estimation](https://mlsanity.com/paper/2603.20323/) (2026)
- [IMPose: Interactive Multi-person Pose Estimation with Dynamic Correction Propagation](https://mlsanity.com/paper/2606.04480/) (2026)

## Abstract (arXiv)

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. textitIn the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. textitIn the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (textite.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets.