MotorSense: A Video-EMG Dataset of Motoric Representations for Action Understanding
MotorSense: A Video-EMG Dataset of Motoric Representations for Action Understanding
This paper introduces MotorSense, the first large-scale dataset pairing egocentric video with bimanual surface electromyography (EMG) and IMU signals across 100 hours of unscripted manipulation. The authors argue that EMG provides a dense, occlusion-free signal for capturing finger movement, hand configuration, and contact forces, offering a scalable alternative to manual annotation. Using MotorSense, they demonstrate sensorimotor alignment via cross-modal pre-training between video and EMG, which improves performance on action recognition, 3D hand reconstruction, and 3D contact reconstruction compared to baseline self-supervised methods. Additionally, the dataset supports generative applications where EMG signals condition a video diffusion model for fine-grained hand manipulation videos.
The authors present MotorSense, a new dataset pairing egocentric video with bimanual EMG and IMU signals across 100 hours of unscripted manipulation, claiming it enables sensorimotor alignment that outperforms conventional self-supervised methods on four action-centric tasks.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
hours of unscripted manipulation
100 hours
View original evidence
IMU, and audio across 100 hours of unscripted manipulation. EMG offers a powerful scalable alternative to manual annotation: it captures finger movement, hand configuration, and the forces exerted between hand and environment as a dense signal free of occlusion and labeler bias, whereas manual annotation is costly, subjective, and unreliable under occlusion. We use MotorSense to learn sensorimotor alignment, producin
Open source S3action-centric computer vision tasks
4
View original evidence
to condition a video diffusion model, yielding videos of fine-grained hand manipulation. Across four action-centric computer vision tasks and eight popular video datasets, we demonstrate that sensorimotor alignment provides a stronger foundation for visual representation learning than conventional self-supervised learning methods over video, outperforming every baseline across all tasks and datasets evaluated.
Open source S5popular video datasets
8
View original evidence
to condition a video diffusion model, yielding videos of fine-grained hand manipulation. Across four action-centric computer vision tasks and eight popular video datasets, we demonstrate that sensorimotor alignment provides a stronger foundation for visual representation learning than conventional self-supervised learning methods over video, outperforming every baseline across all tasks and datasets evaluated.
Open source S5downstream tasks
3
View original evidence
g an organization of action that is shared across the visual and motoric spaces, through cross-modal pre-training between video and EMG. The resultant vision models are then transferred to downstream tasks that benefit from sensorimotor alignment: in this case, action recognition, 3D hand reconstruction, and 3D contact reconstruction. We further demonstrate a generative application in which EMG motor signals are used
Open source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2610.41127v1 Announce Type: cross Abstract: Computer vision models learn hand action only from its visual consequences, without access to the underlying embodied motor signals. We address this absence with MotorSense, the first large-scale paired egocentric video and surface electromyography (EMG) dataset. MotorSense pairs bimanual EMG bands with egocentric video and yields synchronized video, bimanual EMG and
Open source S2
IMU, and audio across 100 hours of unscripted manipulation. EMG offers a powerful scalable alternative to manual annotation: it captures finger movement, hand configuration, and the forces exerted between hand and environment as a dense signal free of occlusion and labeler bias, whereas manual annotation is costly, subjective, and unreliable under occlusion. We use MotorSense to learn sensorimotor alignment, producin
Open source S3
to condition a video diffusion model, yielding videos of fine-grained hand manipulation. Across four action-centric computer vision tasks and eight popular video datasets, we demonstrate that sensorimotor alignment provides a stronger foundation for visual representation learning than conventional self-supervised learning methods over video, outperforming every baseline across all tasks and datasets evaluated.
Open source S5
g an organization of action that is shared across the visual and motoric spaces, through cross-modal pre-training between video and EMG. The resultant vision models are then transferred to downstream tasks that benefit from sensorimotor alignment: in this case, action recognition, 3D hand reconstruction, and 3D contact reconstruction. We further demonstrate a generative application in which EMG motor signals are used
Open source S4
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org