Object-based environment inference via kernel density estimates on learned object features achieves zero-shot room retrieval and beats scene-based CLIP.
Clip- graphs: Multimodal graph networks to infer object-room affinities
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
-
OBSER: Object-Based Sub-Environment Recognition for Zero-Shot Environmental Inference
Object-based environment inference via kernel density estimates on learned object features achieves zero-shot room retrieval and beats scene-based CLIP.