Whareformer learns feed-forward track assignment over relative appearance and 3D distances with a New Track token, reaching SOTA OSNOM performance across EPIC-KITCHENS, IT3DEgo and HD-EPIC from 56 training videos.
IEEE Robotics and Automation Letters (RA-L)7(2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Whareformer: Learning to Track What is Where in Long Egocentric Videos
Whareformer learns feed-forward track assignment over relative appearance and 3D distances with a New Track token, reaching SOTA OSNOM performance across EPIC-KITCHENS, IT3DEgo and HD-EPIC from 56 training videos.