REVIEW 6 cited by
Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We introduce Nymeria - a large-scale, diverse, richly annotated human motion dataset collected in the wild with multiple multimodal egocentric devices. The dataset comes with a) full-body ground-truth motion; b) multiple multimodal egocentric data from Project Aria devices with videos, eye tracking, IMUs and etc; and c) a third-person perspective by an additional observer. All devices are precisely synchronized and localized in on metric 3D world. We derive hierarchical protocol to add in-context language descriptions of human motion, from fine-grain motion narration, to simplified atomic action and high-level activity summarization. To the best of our knowledge, Nymeria dataset is the world's largest collection of human motion in the wild; first of its kind to provide synchronized and localized multi-device multimodal egocentric data; and the world's largest motion-language dataset. It provides 300 hours of daily activities from 264 participants across 50 locations, total travelling distance over 399Km. The language descriptions contain 301.5K sentences in 8.64M words from a vocabulary size of 6545. To demonstrate the potential of the dataset, we evaluate several SOTA algorithms for egocentric body tracking, motion synthesis, and action recognition. Data and code are open-sourced for research (c.f. https://www.projectaria.com/datasets/nymeria).
Forward citations
Cited by 6 Pith papers
-
Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation
A point-prompted segmentation model gains efficiency by foveated tokenization, cutting tokens from 4096 to 172 while staying competitive on mIoU benchmarks.
-
EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal
EgoHTR is a 55-sequence, 150k-frame egocentric 4D human-terrain dataset with a reconstruction pipeline, MoCap-validated benchmark, and perceptive locomotion policies deployed on a Unitree G1.
-
Towards Real-World Wearable Motion Reconstruction
A consumer-wearable MoCap dataset plus WHIP, a flow-matching model that reconstructs full-body motion from arbitrary sensor subsets and quantifies sensor complementarity.
-
EgoM2P: Egocentric Multimodal Multitask Pretraining
A masked pretraining model over RGB, depth, gaze, and camera-pose tokens matches specialist egocentric vision systems on four tasks while running at 300+ frames per second.
-
Whole-Body Conditioned Egocentric Video Prediction
An autoregressive conditional diffusion transformer predicts future egocentric video from whole-body 3D pose sequences, trained on Nymeria, with atomic action and long-horizon evaluations.
-
Data Pyramid for Embodied Manipulation
Embodied training data form a five-layer pyramid—real-robot, UMI, ego/exo, simulation, general V–L—ordered by the trade-off between scale and robot alignment, and model capabilities track how those layers are mixed.
Discussion (0). Sign in to comment.