# MEBOW: Monocular Estimation of Body Orientation In the Wild

arXiv: https://arxiv.org/abs/2011.13688 · HTML: https://mlsanity.com/paper/2011.13688/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 14 of 14)

- [Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion](https://mlsanity.com/paper/2307.13463/) (2023)
- [FeatureSORT: Essential Features for Effective Tracking](https://mlsanity.com/paper/2407.04249/) (2024)
- [PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimation](https://mlsanity.com/paper/2204.11548/) (2022)
- [MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose](https://mlsanity.com/paper/2205.12583/) (2022)
- [Joint Multi-Person Body Detection and Orientation Estimation via One Unified Embedding](https://mlsanity.com/paper/2210.15586/) (2022)
- [Bodily expressed emotion understanding through integrating Laban movement analysis](https://mlsanity.com/paper/2304.02187/) (2023)
- [A Feasibility Study on Indoor Localization and Multi-person Tracking Using Sparsely Distributed Camera Network with Edge Computing](https://mlsanity.com/paper/2305.05062/) (2023)
- [Learning to Adapt to Online Streams with Distribution Shifts](https://mlsanity.com/paper/2303.01630/) (2023)
- [DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detection](https://mlsanity.com/paper/2405.10577/) (2024)
- [Economical Quaternion Extraction from a Human Skeletal Pose Estimate using 2-D Cameras](https://mlsanity.com/paper/2303.08657/) (2023)
- [FSD: Fully-Specialized Detector via Neural Architecture Search](https://mlsanity.com/paper/2305.16649/) (2023)
- [CCPA: Long-term Person Re-Identification via Contrastive Clothing and Pose Augmentation](https://mlsanity.com/paper/2402.14454/) (2024)
- [Generalized Jersey Number Recognition Using Multi-task Learning With Orientation-guided Weight Refinement](https://mlsanity.com/paper/2406.01033/) (2024)
- [Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation](https://mlsanity.com/paper/2507.08513/) (2025)

## Abstract (arXiv)

Body orientation estimation provides crucial visual cues in many applications, including robotics and autonomous driving. It is particularly desirable when 3-D pose estimation is difficult to infer due to poor image resolution, occlusion or indistinguishable body parts. We present COCO-MEBOW (Monocular Estimation of Body Orientation in the Wild), a new large-scale dataset for orientation estimation from a single in-the-wild image. The body-orientation labels for around 130K human bodies within 55K images from the COCO dataset have been collected using an efficient and high-precision annotation pipeline. We also validated the benefits of the dataset. First, we show that our dataset can substantially improve the performance and the robustness of a human body orientation estimation model, the development of which was previously limited by the scale and diversity of the available training data. Additionally, we present a novel triple-source solution for 3-D human pose estimation, where 3-D pose labels, 2-D pose labels, and our body-orientation labels are all used in joint training. Our model significantly outperforms state-of-the-art dual-source solutions for monocular 3-D human pose estimation, where training only uses 3-D pose labels and 2-D pose labels. This substantiates an important advantage of MEBOW for 3-D human pose estimation, which is particularly appealing because the per-instance labeling cost for body orientations is far less than that for 3-D poses. The work demonstrates high potential of MEBOW in addressing real-world challenges involving understanding human behaviors. Further information of this work is available at https://chenyanwu.github.io/MEBOW/.