# Parsing Occluded People by Flexible Compositions

arXiv: https://arxiv.org/abs/1412.1526 · HTML: https://mlsanity.com/paper/1412.1526/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2014.

## Built on by (most cited first, 8 of 8)

- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Occlusion-Aware Video Object Inpainting](https://mlsanity.com/paper/2108.06765/) (2021)
- [Occlusion-Aware Instance Segmentation via BiLayer Network Architectures](https://mlsanity.com/paper/2208.04438/) (2022)
- [Deep video representation learning: a survey](https://mlsanity.com/paper/2405.06574/) (2024)
- [Improving Multi-Person Pose Tracking with A Confidence Network](https://mlsanity.com/paper/2310.18920/) (2023)
- [A Wireless-Vision Dataset for Privacy Preserving Human Activity Recognition](https://mlsanity.com/paper/2205.11962/) (2022)
- [Efficient Online 3D Multi-Camera Multi-Object Tracking and Pose Estimation](https://mlsanity.com/paper/2604.16522/) (2026)

## Abstract (arXiv)

This paper presents an approach to parsing humans when there is significant occlusion. We model humans using a graphical model which has a tree structure building on recent work [32, 6] and exploit the connectivity prior that, even in presence of occlusion, the visible nodes form a connected subtree of the graphical model. We call each connected subtree a flexible composition of object parts. This involves a novel method for learning occlusion cues. During inference we need to search over a mixture of different flexible models. By exploiting part sharing, we show that this inference can be done extremely efficiently requiring only twice as many computations as searching for the entire object (i.e., not modeling occlusion). We evaluate our model on the standard benchmarked "We Are Family" Stickmen dataset and obtain significant performance improvements over the best alternative algorithms.