# Multi-Grained Feature Pruning for Video-Based Human Pose Estimation

arXiv: https://arxiv.org/abs/2503.05365 · HTML: https://mlsanity.com/paper/2503.05365/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution](https://mlsanity.com/paper/2204.13062/) (2022)
- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [PoseTrack: Joint Multi-Person Pose Estimation and Tracking](https://mlsanity.com/paper/1611.07727/) (2016)
- [Learning Temporal Pose Estimation from Sparsely-Labeled Videos](https://mlsanity.com/paper/1906.04016/) (2019)
- [DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2307.16687/) (2023)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)
- [Locate and Verify: A Two-Stream Network for Improved Deepfake Detection](https://mlsanity.com/paper/2309.11131/) (2023)
- [Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2203.15227/) (2022)
- [Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video](https://mlsanity.com/paper/2303.08475/) (2023)
- [Motion Prediction via Joint Dependency Modeling in Phase Space](https://mlsanity.com/paper/2201.02365/) (2022)
- [Copy Motion From One to Another: Fake Motion Video Generation](https://mlsanity.com/paper/2205.01373/) (2022)
- [OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos](https://mlsanity.com/paper/2207.09725/) (2022)
- [Video-Based Human Pose Regression via Decoupled Space-Time Aggregation](https://mlsanity.com/paper/2403.19926/) (2024)
- [Do As I Do: Pose Guided Human Motion Copy](https://mlsanity.com/paper/2406.16601/) (2024)
- [Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization](https://mlsanity.com/paper/2306.07576/) (2023)
- [Joint-Motion Mutual Learning for Pose Estimation in Videos](https://mlsanity.com/paper/2408.02285/) (2024)
- [Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2501.14356/) (2025)
- [Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos](https://mlsanity.com/paper/2211.15868/) (2022)
- [Improving Multi-Person Pose Tracking with A Confidence Network](https://mlsanity.com/paper/2310.18920/) (2023)
- [Optimizing Human Pose Estimation Through Focused Human and Joint Regions](https://mlsanity.com/paper/2501.14439/) (2025)
- [SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos](https://mlsanity.com/paper/2501.15073/) (2025)

## Abstract (arXiv)

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatio-temporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset.