Update README.md

README.md

@@ -1,15 +1,34 @@
 ---
-datasets:
-  - tmddud20/EgoSMPLX
 tags:
-  - arxiv:2605.08606
-  - computer-vision
+- arxiv:2605.08606
+- computer-vision
+- human-mesh-recovery
 ---
 
 # EgoSMPLX
 
-This repository provides the model artifacts for **EgoSMPLX**, accepted to **IEEE ICIP 2026**.
+This repository provides the pretrained model checkpoint for **EgoSMPLX**, proposed in **Egocentric Whole-Body Human Mesh Recovery with Prior-Guided Learning**, IEEE ICIP 2026.
 
-- [Paper](https://huggingface.co/papers/2605.08606)
+EgoSMPLX is a prior-guided framework for whole-body human mesh recovery from monocular egocentric images. It leverages an exocentric human mesh recovery foundation model and a diffusion-based pose prior to improve whole-body reconstruction in egocentric settings.
+
+For installation, configuration, and evaluation instructions, please refer to the official code repository.
+
+## Resources
+
+- [Paper (IEEE Xplore)](https://ieeexplore.ieee.org/document/11630020)
 - [arXiv](https://arxiv.org/abs/2605.08606)
-- [Dataset](https://huggingface.co/datasets/tmddud20/EgoSMPLX)
+- [Code](https://github.com/naso06/EgoSMPLX)
+- [Pseudo-GT Annotations](https://huggingface.co/datasets/tmddud20/EgoSMPLX)
+
+## Citation
+
+If you find our work useful, please cite:
+
+```bibtex
+@inproceedings{na2026egocentric,
+  author={Na, Soyeon and Noh, Seung Young and Chang, Ju Yong},
+  title={Egocentric Whole-Body Human Mesh Recovery with Prior-Guided Learning},
+  booktitle={2026 {IEEE} International Conference on Image Processing ({ICIP})},
+  year={2026}
+}
+```