# TRB: A Novel Triplet Representation for Understanding 2D Human Body

arXiv: https://arxiv.org/abs/1910.11535 · HTML: https://mlsanity.com/paper/1910.11535/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2019.

## Built on by (most cited first, 10 of 10)

- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [Pose for Everything: Towards Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2207.10387/) (2022)
- [ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search](https://mlsanity.com/paper/2105.10154/) (2021)
- [ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2208.11547/) (2022)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization](https://mlsanity.com/paper/2201.08613/) (2022)
- [You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception](https://mlsanity.com/paper/2312.05525/) (2023)
- [MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection](https://mlsanity.com/paper/2302.04589/) (2023)
- [Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information](https://mlsanity.com/paper/2403.15048/) (2024)

## Abstract (arXiv)

Human pose and shape are two important components of 2D human body. However, how to efficiently represent both of them in images is still an open question. In this paper, we propose the Triplet Representation for Body (TRB) -- a compact 2D human body representation, with skeleton keypoints capturing human pose information and contour keypoints containing human shape information. TRB not only preserves the flexibility of skeleton keypoint representation, but also contains rich pose and human shape information. Therefore, it promises broader application areas, such as human shape editing and conditional image generation. We further introduce the challenging problem of TRB estimation, where joint learning of human pose and shape is required. We construct several large-scale TRB estimation datasets, based on popular 2D pose datasets: LSP, MPII, COCO. To effectively solve TRB estimation, we propose a two-branch network (TRB-net) with three novel techniques, namely X-structure (Xs), Directional Convolution (DC) and Pairwise Mapping (PM), to enforce multi-level message passing for joint feature learning. We evaluate our proposed TRB-net and several leading approaches on our proposed TRB datasets, and demonstrate the superiority of our method through extensive evaluations.