TAMFormer combines a topological affordance memory with a transformer decoder to plan high-level actions from egocentric video and replan when execution deviates.
Procedure planning in instructional videos via contextual modeling and model- based policy learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
What to Do Next? Memorizing skills from Egocentric Instructional Video
TAMFormer combines a topological affordance memory with a transformer decoder to plan high-level actions from egocentric video and replan when execution deviates.