PerLA improves 3D question answering and dense captioning by combining Hilbert-curve partitioned local point-cloud details with global context through cross-attention and graph convolution.
Crossvit: Cross-attention multi-scale vision transformer for image classification
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
PerLA: Perceptive 3D Language Assistant
PerLA improves 3D question answering and dense captioning by combining Hilbert-curve partitioned local point-cloud details with global context through cross-attention and graph convolution.