# PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation

arXiv: https://arxiv.org/abs/2409.06535 · HTML: https://mlsanity.com/paper/2409.06535/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 76 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## Builds on (most cited first, 30 of 60)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Self-Supervised MultiModal Versatile Networks](https://mlsanity.com/paper/2006.16228/) (2020)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)

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

- [PromptHMR: Promptable Human Mesh Recovery](https://mlsanity.com/paper/2504.06397/) (2025)
- [UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing](https://mlsanity.com/paper/2411.16781/) (2024)
- [MonSTeR: a Unified Model for Motion, Scene, Text Retrieval](https://mlsanity.com/paper/2510.03200/) (2025)
- [Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision](https://mlsanity.com/paper/2603.26646/) (2026)
- [InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement](https://mlsanity.com/paper/2604.19673/) (2026)
- [Anny-Fit: All-Age Human Mesh Recovery](https://mlsanity.com/paper/2605.04728/) (2026)
- [SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification](https://mlsanity.com/paper/2506.21056/) (2025)
- [Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning](https://mlsanity.com/paper/2508.07804/) (2025)

## Abstract (arXiv)

Aligning multiple modalities in a latent space, such as images and texts, has shown to produce powerful semantic visual representations, fueling tasks like image captioning, text-to-image generation, or image grounding. In the context of human-centric vision, albeit CLIP-like representations encode most standard human poses relatively well (such as standing or sitting), they lack sufficient acuteness to discern detailed or uncommon ones. Actually, while 3D human poses have been often associated with images (e.g. to perform pose estimation or pose-conditioned image generation), or more recently with text (e.g. for text-to-pose generation), they have seldom been paired with both. In this work, we combine 3D poses, person's pictures and textual pose descriptions to produce an enhanced 3D-, visual- and semantic-aware human pose representation. We introduce a new transformer-based model, trained in a retrieval fashion, which can take as input any combination of the aforementioned modalities. When composing modalities, it outperforms a standard multi-modal alignment retrieval model, making it possible to sort out partial information (e.g. image with the lower body occluded). We showcase the potential of such an embroidered pose representation for (1) SMPL regression from image with optional text cue; and (2) on the task of fine-grained instruction generation, which consists in generating a text that describes how to move from one 3D pose to another (as a fitness coach). Unlike prior works, our model can take any kind of input (image and/or pose) without retraining.