A word embedding based re-ranking of CNN top-5 predictions adds 0.2 to 1.9 accuracy points in indoor scene classification for robots when the broad environment is known.
Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings
A word embedding based re-ranking of CNN top-5 predictions adds 0.2 to 1.9 accuracy points in indoor scene classification for robots when the broad environment is known.