VideoNIG tests whether multimodal models can turn tour videos into executable navigation instructions, and a two-stage curriculum with preference optimization improves their spatial reasoning.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2024) 3, 4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Goal-oriented Navigation Instruction Generation with Tour Video Priors
VideoNIG tests whether multimodal models can turn tour videos into executable navigation instructions, and a two-stage curriculum with preference optimization improves their spatial reasoning.