# Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos

arXiv: https://arxiv.org/abs/1703.10898 · HTML: https://mlsanity.com/paper/1703.10898/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2017.

## Built on by (most cited first, 30 of 40)

- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2307.16687/) (2023)
- [Test-Time Personalization with a Transformer for Human Pose Estimation](https://mlsanity.com/paper/2107.02133/) (2021)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)
- [ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search](https://mlsanity.com/paper/2105.10154/) (2021)
- [Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning](https://mlsanity.com/paper/2203.14333/) (2022)
- [Shape-aware Multi-Person Pose Estimation from Multi-View Images](https://mlsanity.com/paper/2110.02330/) (2021)
- [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)
- [VideoMAC: Video Masked Autoencoders Meet ConvNets](https://mlsanity.com/paper/2402.19082/) (2024)
- [Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video](https://mlsanity.com/paper/2303.08475/) (2023)
- [Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning](https://mlsanity.com/paper/2109.13499/) (2021)
- [Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation](https://mlsanity.com/paper/2207.03714/) (2022)
- [Semantic-Aware Fine-Grained Correspondence](https://mlsanity.com/paper/2207.10456/) (2022)
- [Spatial-then-Temporal Self-Supervised Learning for Video Correspondence](https://mlsanity.com/paper/2209.07778/) (2022)
- [Relation-Based Associative Joint Location for Human Pose Estimation in Videos](https://mlsanity.com/paper/2107.03591/) (2021)
- [Joint-Motion Mutual Learning for Pose Estimation in Videos](https://mlsanity.com/paper/2408.02285/) (2024)
- [Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning](https://mlsanity.com/paper/2105.05838/) (2021)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [Deep Learning Approaches for Seizure Video Analysis: A Review](https://mlsanity.com/paper/2312.10930/) (2023)
- [Transfer of Representations to Video Label Propagation: Implementation Factors Matter](https://mlsanity.com/paper/2203.05553/) (2022)
- [A Temporal Densely Connected Recurrent Network for Event-based Human Pose Estimation](https://mlsanity.com/paper/2209.07034/) (2022)
- [Learning Fine-Grained Features for Pixel-wise Video Correspondences](https://mlsanity.com/paper/2308.03040/) (2023)
- [Human Modelling and Pose Estimation Overview](https://mlsanity.com/paper/2406.19290/) (2024)
- [High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2510.11017/) (2025)
- [Self-supervised Secondary Landmark Detection via 3D Representation Learning](https://mlsanity.com/paper/2110.00543/) (2021)
- [Improving Multi-Person Pose Tracking with A Confidence Network](https://mlsanity.com/paper/2310.18920/) (2023)
- [Kinematics Modeling Network for Video-based Human Pose Estimation](https://mlsanity.com/paper/2207.10971/) (2022)
- [ResQ: Residual Quantization for Video Perception](https://mlsanity.com/paper/2308.09511/) (2023)

## Abstract (arXiv)

Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no examples in training data sets. Temporal information can provide additional cues about the location of body joints and help to alleviate these issues. In this paper, we propose a deep structured model to estimate a sequence of human poses in unconstrained videos. This model can be efficiently trained in an end-to-end manner and is capable of representing appearance of body joints and their spatio-temporal relationships simultaneously. Domain knowledge about the human body is explicitly incorporated into the network providing effective priors to regularize the skeletal structure and to enforce temporal consistency. The proposed end-to-end architecture is evaluated on two widely used benchmarks (Penn Action dataset and JHMDB dataset) for video-based pose estimation. Our approach significantly outperforms the existing state-of-the-art methods.