FCA-NIG automatically generates navigation instructions with sub-instruction and entity-landmark alignments, producing the FCA-R2R dataset that modestly improves several VLN agents.
Matterport3d: LearningfromRGB-Ddatainindoorenvironments,in:3DV,pp.667–
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations
FCA-NIG automatically generates navigation instructions with sub-instruction and entity-landmark alignments, producing the FCA-R2R dataset that modestly improves several VLN agents.