EgoInteract is a new simulator for generating synthetic egocentric videos with precise control over camera, body, hand, and object motions, producing a dataset that improves model performance on real-world benchmarks for temporal action segmentation, next-active object detection, interaction Anticip
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
New dataset for complex multi-person 4D markerless motion capture with Vicon-aligned SMPL parameters shows substantial degradation in existing models but gains from fine-tuning.
citing papers explorer
-
EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation
EgoInteract is a new simulator for generating synthetic egocentric videos with precise control over camera, body, hand, and object motions, producing a dataset that improves model performance on real-world benchmarks for temporal action segmentation, next-active object detection, interaction Anticip
-
A Dataset and Evaluation for Complex 4D Markerless Human Motion Capture
New dataset for complex multi-person 4D markerless motion capture with Vicon-aligned SMPL parameters shows substantial degradation in existing models but gains from fine-tuning.