# Toward fast and accurate human pose estimation via soft-gated skip connections

arXiv: https://arxiv.org/abs/2002.11098 · HTML: https://mlsanity.com/paper/2002.11098/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2020.

## Built on by (most cited first, 22 of 22)

- [Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs](https://mlsanity.com/paper/2310.00120/) (2023)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Novel Class Discovery without Forgetting](https://mlsanity.com/paper/2207.10659/) (2022)
- [Vision-Based Human Pose Estimation via Deep Learning: A Survey](https://mlsanity.com/paper/2308.13872/) (2023)
- [MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks](https://mlsanity.com/paper/2112.10082/) (2021)
- [Spacing Loss for Discovering Novel Categories](https://mlsanity.com/paper/2204.10595/) (2022)
- [VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation](https://mlsanity.com/paper/2210.06028/) (2022)
- [Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss](https://mlsanity.com/paper/2102.09808/) (2021)
- [Detecting Arbitrary Keypoints on Limbs and Skis with Sparse Partly Correct Segmentation Masks](https://mlsanity.com/paper/2211.09446/) (2022)
- [Recognition of Freely Selected Keypoints on Human Limbs](https://mlsanity.com/paper/2204.06326/) (2022)
- [Scene-aware Learning Network for Radar Object Detection](https://mlsanity.com/paper/2107.01469/) (2021)
- [Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?](https://mlsanity.com/paper/2104.09493/) (2021)
- [Improving Multi-Person Pose Tracking with A Confidence Network](https://mlsanity.com/paper/2310.18920/) (2023)
- [LDRNet: Enabling Real-time Document Localization on Mobile Devices](https://mlsanity.com/paper/2206.02136/) (2022)
- [Location-free Human Pose Estimation](https://mlsanity.com/paper/2205.12619/) (2022)
- [Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation](https://mlsanity.com/paper/2208.13441/) (2022)
- [Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization](https://mlsanity.com/paper/2106.15409/) (2021)
- [InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inference](https://mlsanity.com/paper/2209.13873/) (2022)
- [Unposed: Unsupervised Pose Estimation based Product Image Recommendations](https://mlsanity.com/paper/2301.07879/) (2023)
- [An Efficient and Flexible Deep Learning Method for Signal Delineation via Keypoints Estimation](https://mlsanity.com/paper/2407.20258/) (2024)
- [Joint angle based learning to refine kinematic human pose estimation](https://mlsanity.com/paper/2507.11075/) (2025)
- [LAPX: Lightweight Hourglass Network with Global Context](https://mlsanity.com/paper/2512.16089/) (2025)

## Abstract (arXiv)

This paper is on highly accurate and highly efficient human pose estimation. Recent works based on Fully Convolutional Networks (FCNs) have demonstrated excellent results for this difficult problem. While residual connections within FCNs have proved to be quintessential for achieving high accuracy, we re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art. In particular, we make the following contributions: (a) We propose gated skip connections with per-channel learnable parameters to control the data flow for each channel within the module within the macro-module. (b) We introduce a hybrid network that combines the HourGlass and U-Net architectures which minimizes the number of identity connections within the network and increases the performance for the same parameter budget. Our model achieves state-of-the-art results on the MPII and LSP datasets. In addition, with a reduction of 3x in model size and complexity, we show no decrease in performance when compared to the original HourGlass network.