# EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting

arXiv: https://arxiv.org/abs/2605.07642 · HTML: https://mlsanity.com/paper/2605.07642/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 52 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators](https://mlsanity.com/paper/2306.10900/) (2023)
- [Compositional Human Pose Regression](https://mlsanity.com/paper/1704.00159/) (2017)
- [Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild](https://mlsanity.com/paper/2406.09905/) (2024)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints](https://mlsanity.com/paper/2003.09282/) (2020)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [LeRobot: An Open-Source Library for End-to-End Robot Learning](https://mlsanity.com/paper/2602.22818/) (2026)
- [Future Transformer for Long-term Action Anticipation](https://mlsanity.com/paper/2205.14022/) (2022)
- [EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation](https://mlsanity.com/paper/2406.18070/) (2024)
- [Memory-and-Anticipation Transformer for Online Action Understanding](https://mlsanity.com/paper/2308.07893/) (2023)
- [Anticipating human actions by correlating past with the future with Jaccard similarity measures](https://mlsanity.com/paper/2105.12414/) (2021)
- [Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting](https://mlsanity.com/paper/2307.08243/) (2023)
- [Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models](https://mlsanity.com/paper/2405.20305/) (2024)

## Built on by (most cited first, 1 of 1)

- [Multi-modal Representation Fusion for Long-term Microsurgical Anastomosis Trajectory Anticipation](https://mlsanity.com/paper/2610.14492/) (2026)

## Abstract (arXiv)

Forecasting future 3D hand pose sequences from egocentric video is essential for understanding human intention and enabling embodied applications such as AR/VR assistance and human-robot interaction. However, this task remains a highly challenging problem because egocentric hand motion is driven by complex human intent, exhibits highly dexterous articulations, and is observed under drastic viewpoint shifts induced by ego-motion. In this work, we introduce EggHand, a foundation-model-based framework for egocentric hand pose forecasting that unifies multimodal semantic reasoning with dynamic motion modeling. Our approach couples an action decoder from a Vision-Language-Action (VLA) model, which captures the structured temporal dynamics of hand motion, with an egocentric video-text encoder that provides viewpoint-aware contextual information learned from large-scale first-person video. Together, these components overcome the brittleness of generic visual encoders under ego-motion and enable joint reasoning over motion, context, and high-level intent-without relying on body pose or external tracking. Experiments on the EgoExo4D dataset show that EggHand sets a new state of the art in forecasting accuracy, remains robust under severe ego-motion, and further enables controllable prediction via language-based task prompts. Project page: https://jyoun9.github.io/EggHand