# Dynamic Kernel Distillation for Efficient Pose Estimation in Videos

arXiv: https://arxiv.org/abs/1908.09216 · HTML: https://mlsanity.com/paper/1908.09216/

## Key facts

- Cited by 30 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 24 Aug 2019.

## Built on by (most cited first, 30 of 30)

- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)
- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention](https://mlsanity.com/paper/2401.06312/) (2024)
- [ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search](https://mlsanity.com/paper/2105.10154/) (2021)
- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)
- [Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2203.15227/) (2022)
- [Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels](https://mlsanity.com/paper/2201.05986/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos](https://mlsanity.com/paper/2203.03996/) (2022)
- [Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation](https://mlsanity.com/paper/2107.12087/) (2021)
- [System-status-aware Adaptive Network for Online Streaming Video Understanding](https://mlsanity.com/paper/2303.15742/) (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)
- [Event Neural Networks](https://mlsanity.com/paper/2112.00891/) (2021)
- [A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimation](https://mlsanity.com/paper/2209.07034/) (2022)
- [MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos](https://mlsanity.com/paper/2210.09887/) (2022)
- [Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos](https://mlsanity.com/paper/2211.15868/) (2022)
- [High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2510.11017/) (2025)
- [2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints](https://mlsanity.com/paper/2212.02163/) (2022)
- [Track-On2: Enhancing Online Point Tracking with Memory](https://mlsanity.com/paper/2509.19115/) (2025)
- [Kinematics Modeling Network for Video-based Human Pose Estimation](https://mlsanity.com/paper/2207.10971/) (2022)
- [Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptors](https://mlsanity.com/paper/2209.11795/) (2022)
- [ResQ: Residual Quantization for Video Perception](https://mlsanity.com/paper/2308.09511/) (2023)
- [A Stochastic-Geometrical Framework for Object Pose Estimation based on Mixture Models Avoiding the Correspondence Problem](https://mlsanity.com/paper/2311.18107/) (2023)
- [SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity](https://mlsanity.com/paper/2410.20790/) (2024)
- [A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network](https://mlsanity.com/paper/2508.11212/) (2025)

## Abstract (arXiv)

Existing video-based human pose estimation methods extensively apply large networks onto every frame in the video to localize body joints, which suffer high computational cost and hardly meet the low-latency requirement in realistic applications. To address this issue, we propose a novel Dynamic Kernel Distillation (DKD) model to facilitate small networks for estimating human poses in videos, thus significantly lifting the efficiency. In particular, DKD introduces a light-weight distillator to online distill pose kernels via leveraging temporal cues from the previous frame in a one-shot feed-forward manner. Then, DKD simplifies body joint localization into a matching procedure between the pose kernels and the current frame, which can be efficiently computed via simple convolution. In this way, DKD fast transfers pose knowledge from one frame to provide compact guidance for body joint localization in the following frame, which enables utilization of small networks in video-based pose estimation. To facilitate the training process, DKD exploits a temporally adversarial training strategy that introduces a temporal discriminator to help generate temporally coherent pose kernels and pose estimation results within a long range. Experiments on Penn Action and Sub-JHMDB benchmarks demonstrate outperforming efficiency of DKD, specifically, 10x flops reduction and 2x speedup over previous best model, and its state-of-the-art accuracy.