# EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos

arXiv: https://arxiv.org/abs/2405.20030 · HTML: https://mlsanity.com/paper/2405.20030/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 61 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints](https://mlsanity.com/paper/1806.01482/) (2018)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video](https://mlsanity.com/paper/2005.02190/) (2020)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos](https://mlsanity.com/paper/2104.07905/) (2021)
- [Ego-Body Pose Estimation via Ego-Head Pose Estimation](https://mlsanity.com/paper/2212.04636/) (2022)
- [A Short Note on the Kinetics-700-2020 Human Action Dataset](https://mlsanity.com/paper/2010.10864/) (2020)
- [What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction](https://mlsanity.com/paper/1903.07933/) (2019)
- [AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation](https://mlsanity.com/paper/2304.12301/) (2023)
- [Estimating Egocentric 3D Human Pose in Global Space](https://mlsanity.com/paper/2104.13454/) (2021)
- [E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition](https://mlsanity.com/paper/2112.03596/) (2021)
- [Learning Cross-modal Contrastive Features for Video Domain Adaptation](https://mlsanity.com/paper/2108.11974/) (2021)
- [Egocentric Audio-Visual Object Localization](https://mlsanity.com/paper/2303.13471/) (2023)
- [Mimetics: Towards Understanding Human Actions Out of Context](https://mlsanity.com/paper/1912.07249/) (2019)

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

- [The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation](https://mlsanity.com/paper/2504.08654/) (2025)
- [PEAR: Phrase-Based Hand-Object Interaction Anticipation](https://mlsanity.com/paper/2407.21510/) (2024)
- [Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos](https://mlsanity.com/paper/2512.16907/) (2025)
- [Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views](https://mlsanity.com/paper/2511.12878/) (2025)
- [SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting](https://mlsanity.com/paper/2511.18127/) (2025)
- [EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting](https://mlsanity.com/paper/2605.07642/) (2026)
- [Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation](https://mlsanity.com/paper/2605.20085/) (2026)
- [EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset](https://mlsanity.com/paper/2609.17189/) (2026)

## Abstract (arXiv)

Predicting future human behavior from egocentric videos is a challenging but critical task for human intention understanding. Existing methods for forecasting 2D hand positions rely on visual representations and mainly focus on hand-object interactions. In this paper, we investigate the hand forecasting task and tackle two significant issues that persist in the existing methods: (1) 2D hand positions in future frames are severely affected by ego-motions in egocentric videos; (2) prediction based on visual information tends to overfit to background or scene textures, posing a challenge for generalization on novel scenes or human behaviors. To solve the aforementioned problems, we propose EMAG, an ego-motion-aware and generalizable 2D hand forecasting method. In response to the first problem, we propose a method that considers ego-motion, represented by a sequence of homography matrices of two consecutive frames. We further leverage modalities such as optical flow, trajectories of hands and interacting objects, and ego-motions, thereby alleviating the second issue. Extensive experiments on two large-scale egocentric video datasets, Ego4D and EPIC-Kitchens 55, verify the effectiveness of the proposed method. In particular, our model outperforms prior methods by 1.7% and 7.0% on intra and cross-dataset evaluations, respectively. Project page: https://masashi-hatano.github.io/EMAG/