# AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation

arXiv: https://arxiv.org/abs/2304.12301 · HTML: https://mlsanity.com/paper/2304.12301/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 24 Apr 2023.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [Learning to Estimate 3D Hand Pose from Single RGB Images](https://mlsanity.com/paper/1705.01389/) (2017)
- [Hand Keypoint Detection in Single Images using Multiview Bootstrapping](https://mlsanity.com/paper/1704.07809/) (2017)
- [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://mlsanity.com/paper/1704.02463/) (2017)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [Embodied Hands: Modeling and Capturing Hands and Bodies Together](https://mlsanity.com/paper/2201.02610/) (2022)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [Hand Pose Estimation via Latent 2.5D Heatmap Regression](https://mlsanity.com/paper/1804.09534/) (2018)
- [V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map](https://mlsanity.com/paper/1711.07399/) (2017)
- [Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor](https://mlsanity.com/paper/1704.02201/) (2017)
- [P-CNN: Pose-based CNN Features for Action Recognition](https://mlsanity.com/paper/1506.03607/) (2015)
- [Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input](https://mlsanity.com/paper/1610.04889/) (2016)
- [UmeTrack: Unified multi-view end-to-end hand tracking for VR](https://mlsanity.com/paper/2211.00099/) (2022)
- [Generalizable Human Pose Triangulation](https://mlsanity.com/paper/2110.00280/) (2021)
- [Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey](https://mlsanity.com/paper/2206.02257/) (2022)
- [Pose for Action - Action for Pose](https://mlsanity.com/paper/1603.04037/) (2016)
- [Domain Adaptive Hand Keypoint and Pixel Localization in the Wild](https://mlsanity.com/paper/2203.08344/) (2022)

## Built on by (most cited first, 30 of 64)

- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos](https://mlsanity.com/paper/2411.19167/) (2024)
- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking](https://mlsanity.com/paper/2406.09598/) (2024)
- [A Dataset of Relighted 3D Interacting Hands](https://mlsanity.com/paper/2310.17768/) (2023)
- [Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects](https://mlsanity.com/paper/2403.16428/) (2024)
- [3D Hand Pose Estimation in Everyday Egocentric Images](https://mlsanity.com/paper/2312.06583/) (2023)
- [GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities](https://mlsanity.com/paper/2412.04244/) (2024)
- [Challenges and Trends in Egocentric Vision: A Survey](https://mlsanity.com/paper/2503.15275/) (2025)
- [EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision](https://mlsanity.com/paper/2409.02224/) (2024)
- [On the Utility of 3D Hand Poses for Action Recognition](https://mlsanity.com/paper/2403.09805/) (2024)
- [EAGLE: Egocentric AGgregated Language-video Engine](https://mlsanity.com/paper/2409.17523/) (2024)
- [AnyView: Synthesizing Any Novel View in Dynamic Scenes](https://mlsanity.com/paper/2601.16982/) (2026)
- [Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos](https://mlsanity.com/paper/2311.16444/) (2023)
- [AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild](https://mlsanity.com/paper/2407.18034/) (2024)
- [PEAR: Phrase-Based Hand-Object Interaction Anticipation](https://mlsanity.com/paper/2407.21510/) (2024)
- [EgoM2P: Egocentric Multimodal Multitask Pretraining](https://mlsanity.com/paper/2506.07886/) (2025)
- [Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects](https://mlsanity.com/paper/2511.01294/) (2025)
- [EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos](https://mlsanity.com/paper/2405.20030/) (2024)
- [FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation](https://mlsanity.com/paper/2412.02690/) (2024)
- [DyTact: Capturing Dynamic Contacts in Hand-Object Manipulation](https://mlsanity.com/paper/2506.03103/) (2025)
- [Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision](https://mlsanity.com/paper/2506.06253/) (2025)
- [SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training](https://mlsanity.com/paper/2502.15251/) (2025)
- [EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos](https://mlsanity.com/paper/2601.01050/) (2026)
- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstruction](https://mlsanity.com/paper/2505.19169/) (2025)
- [egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-World Tasks](https://mlsanity.com/paper/2510.22129/) (2025)
- [ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Images](https://mlsanity.com/paper/2403.09871/) (2024)
- [EgoEvGesture: Gesture Recognition Based on Egocentric Event Camera](https://mlsanity.com/paper/2503.12419/) (2025)
- [YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale](https://mlsanity.com/paper/2606.10244/) (2026)

## Abstract (arXiv)

We present AssemblyHands, a large-scale benchmark dataset with accurate 3D hand pose annotations, to facilitate the study of egocentric activities with challenging hand-object interactions. The dataset includes synchronized egocentric and exocentric images sampled from the recent Assembly101 dataset, in which participants assemble and disassemble take-apart toys. To obtain high-quality 3D hand pose annotations for the egocentric images, we develop an efficient pipeline, where we use an initial set of manual annotations to train a model to automatically annotate a much larger dataset. Our annotation model uses multi-view feature fusion and an iterative refinement scheme, and achieves an average keypoint error of 4.20 mm, which is 85% lower than the error of the original annotations in Assembly101. AssemblyHands provides 3.0M annotated images, including 490K egocentric images, making it the largest existing benchmark dataset for egocentric 3D hand pose estimation. Using this data, we develop a strong single-view baseline of 3D hand pose estimation from egocentric images. Furthermore, we design a novel action classification task to evaluate predicted 3D hand poses. Our study shows that having higher-quality hand poses directly improves the ability to recognize actions.