# Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting

arXiv: https://arxiv.org/abs/2307.08243 · HTML: https://mlsanity.com/paper/2307.08243/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 55 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Builds on (most cited first, 30 of 42)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting](https://mlsanity.com/paper/2103.14023/) (2021)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Convolutional Social Pooling for Vehicle Trajectory Prediction](https://mlsanity.com/paper/1805.06771/) (2018)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Deep Kalman Filters](https://mlsanity.com/paper/1511.05121/) (2015)
- [NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation](https://mlsanity.com/paper/2203.01502/) (2022)
- [Bounding Box Regression with Uncertainty for Accurate Object Detection](https://mlsanity.com/paper/1809.08545/) (2018)
- [H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions](https://mlsanity.com/paper/1904.05349/) (2019)
- [Dynamical Variational Autoencoders: A Comprehensive Review](https://mlsanity.com/paper/2008.12595/) (2020)
- [Disentangled Sequential Autoencoder](https://mlsanity.com/paper/1803.02991/) (2018)
- [Learning the Depths of Moving People by Watching Frozen People](https://mlsanity.com/paper/1904.11111/) (2019)
- [Sequential Neural Models with Stochastic Layers](https://mlsanity.com/paper/1605.07571/) (2016)
- [SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction](https://mlsanity.com/paper/1903.02793/) (2019)
- [EGO-TOPO: Environment Affordances from Egocentric Video](https://mlsanity.com/paper/2001.04583/) (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)
- [Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning](https://mlsanity.com/paper/2008.00334/) (2020)

## Built on by (most cited first, 30 of 34)

- [General Flow as Foundation Affordance for Scalable Robot Learning](https://mlsanity.com/paper/2401.11439/) (2024)
- [Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos](https://mlsanity.com/paper/2405.04370/) (2024)
- [Challenges and Trends in Egocentric Vision: A Survey](https://mlsanity.com/paper/2503.15275/) (2025)
- [MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos](https://mlsanity.com/paper/2409.02638/) (2024)
- [EAGLE: Egocentric AGgregated Language-video Engine](https://mlsanity.com/paper/2409.17523/) (2024)
- [The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation](https://mlsanity.com/paper/2504.08654/) (2025)
- [HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction](https://mlsanity.com/paper/2412.13187/) (2024)
- [AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2406.01194/) (2024)
- [Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision](https://mlsanity.com/paper/2506.03605/) (2025)
- [PEAR: Phrase-Based Hand-Object Interaction Anticipation](https://mlsanity.com/paper/2407.21510/) (2024)
- [Novel Diffusion Models for Multimodal 3D Hand Trajectory Prediction](https://mlsanity.com/paper/2504.07375/) (2025)
- [Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions](https://mlsanity.com/paper/2508.04681/) (2025)
- [Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos](https://mlsanity.com/paper/2512.16907/) (2025)
- [Bidirectional Progressive Transformer for Interaction Intention Anticipation](https://mlsanity.com/paper/2405.05552/) (2024)
- [Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views](https://mlsanity.com/paper/2511.12878/) (2025)
- [AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment](https://mlsanity.com/paper/2605.17517/) (2026)
- [Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling](https://mlsanity.com/paper/2311.17366/) (2023)
- [Zero-Shot Temporal Interaction Localization for Egocentric Videos](https://mlsanity.com/paper/2506.03662/) (2025)
- [Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span](https://mlsanity.com/paper/2511.18470/) (2025)
- [EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos](https://mlsanity.com/paper/2508.12349/) (2025)
- [Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images](https://mlsanity.com/paper/2510.06145/) (2025)
- [SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting](https://mlsanity.com/paper/2511.18127/) (2025)
- [Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2602.14837/) (2026)
- [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)
- [Uncertainty Aware-Predictive Control Barrier Functions: Safer Human Robot Interaction through Probabilistic Motion Forecasting](https://mlsanity.com/paper/2508.20812/) (2025)
- [Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality](https://mlsanity.com/paper/2510.10742/) (2025)
- [Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality](https://mlsanity.com/paper/2603.13355/) (2026)
- [Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting](https://mlsanity.com/paper/2607.15890/) (2026)
- [From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video](https://mlsanity.com/paper/2609.08636/) (2026)

## Abstract (arXiv)

Hand trajectory forecasting from egocentric views is crucial for enabling a prompt understanding of human intentions when interacting with AR/VR systems. However, existing methods handle this problem in a 2D image space which is inadequate for 3D real-world applications. In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view. To fulfill this goal, we propose an uncertainty-aware state space Transformer (USST) that takes the merits of the attention mechanism and aleatoric uncertainty within the framework of the classical state-space model. The model can be further enhanced by the velocity constraint and visual prompt tuning (VPT) on large vision transformers. Moreover, we develop an annotation workflow to collect 3D hand trajectories with high quality. Experimental results on H2O and EgoPAT3D datasets demonstrate the superiority of USST for both 2D and 3D trajectory forecasting. The code and datasets are publicly released: https://actionlab-cv.github.io/EgoHandTrajPred.