EgoMe is a large-scale egocentric dataset of 7,902 paired observe-then-imitate videos with gaze, IMU, and multi-level annotations, plus six benchmarks for imitation learning.
Hiervl: Learning hierarchical video- language embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World
EgoMe is a large-scale egocentric dataset of 7,902 paired observe-then-imitate videos with gaze, IMU, and multi-level annotations, plus six benchmarks for imitation learning.