# AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities

arXiv: https://arxiv.org/abs/2509.23888 · HTML: https://mlsanity.com/paper/2509.23888/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 22 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2309.17448/) (2023)
- [The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose](https://mlsanity.com/paper/2007.00394/) (2020)
- [OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion](https://mlsanity.com/paper/2403.19417/) (2024)
- [AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation](https://mlsanity.com/paper/2304.12301/) (2023)
- [Home Action Genome: Cooperative Compositional Action Understanding](https://mlsanity.com/paper/2105.05226/) (2021)
- [Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects](https://mlsanity.com/paper/2403.16428/) (2024)
- [HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding](https://mlsanity.com/paper/2307.05721/) (2023)
- [Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer](https://mlsanity.com/paper/2407.12322/) (2024)
- [ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding](https://mlsanity.com/paper/2304.08210/) (2023)

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

- [DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions](https://mlsanity.com/paper/2512.02727/) (2025)

## Abstract (arXiv)

Bimanual human activities inherently involve coordinated movements of both hands and body. However, the impact of this coordination in activity understanding has not been systematically evaluated due to the lack of suitable datasets. Such evaluation demands kinematic-level annotations (e.g., 3D pose) for the hands and body, yet existing 3D activity datasets typically annotate either hand or body pose. Another line of work employs marker-based motion capture to provide full-body pose, but the physical markers introduce visual artifacts, thereby limiting models' generalization to natural, markerless videos. To address these limitations, we present AssemblyHands-X, the first markerless 3D hand-body benchmark for bimanual activities, designed to study the effect of hand-body coordination for action recognition. We begin by constructing a pipeline for 3D pose annotation from synchronized multi-view videos. Our approach combines multi-view triangulation with SMPL-X mesh fitting, yielding reliable 3D registration of hands and upper body. We then validate different input representations (e.g., video, hand pose, body pose, or hand-body pose) across recent action recognition models based on graph convolution or spatio-temporal attention. Our extensive experiments show that pose-based action inference is more efficient and accurate than video baselines. Moreover, joint modeling of hand and body cues improves action recognition over using hands or upper body alone, highlighting the importance of modeling interdependent hand-body dynamics for a holistic understanding of bimanual activities.