A dataset and benchmark pipeline that generates dynamic indoor scenes and Open-Vocabulary Object Navigation episodes by placing movable objects on receptacles according to LLM-derived commonsense rules.
Towards open vocabulary learning: A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7):5092–5113, 2024
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
-
SD-OVON: A Semantics-aware Dataset and Benchmark Generation Pipeline for Open-Vocabulary Object Navigation in Dynamic Scenes
A dataset and benchmark pipeline that generates dynamic indoor scenes and Open-Vocabulary Object Navigation episodes by placing movable objects on receptacles according to LLM-derived commonsense rules.