# Key Frame Proposal Network for Efficient Pose Estimation in Videos

arXiv: https://arxiv.org/abs/2007.15217 · HTML: https://mlsanity.com/paper/2007.15217/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2203.15227/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition](https://mlsanity.com/paper/2308.12774/) (2023)
- [Relation-Based Associative Joint Location for Human Pose Estimation in Videos](https://mlsanity.com/paper/2107.03591/) (2021)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos](https://mlsanity.com/paper/2211.15868/) (2022)
- [Active Transfer Learning for Efficient Video-Specific Human Pose Estimation](https://mlsanity.com/paper/2311.05041/) (2023)
- [High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2510.11017/) (2025)
- [Kinematics Modeling Network for Video-based Human Pose Estimation](https://mlsanity.com/paper/2207.10971/) (2022)
- [Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance](https://mlsanity.com/paper/2505.18342/) (2025)

## Abstract (arXiv)

Human pose estimation in video relies on local information by either estimating each frame independently or tracking poses across frames. In this paper, we propose a novel method combining local approaches with global context. We introduce a light weighted, unsupervised, key frame proposal network (K-FPN) to select informative frames and a learned dictionary to recover the entire pose sequence from these frames. The K-FPN speeds up the pose estimation and provides robustness to bad frames with occlusion, motion blur, and illumination changes, while the learned dictionary provides global dynamic context. Experiments on Penn Action and sub-JHMDB datasets show that the proposed method achieves state-of-the-art accuracy, with substantial speed-up.