Inserting cross-attention layers into a pretrained language model and conditioning them on point cloud features yields substantially higher 3D affordance detection performance on 3D AffordanceNet than cosine-similarity baselines.
Pre- dicting 3D Human Dynamics From Video,
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
-
Capturing Fine-Grained Alignments Improves 3D Affordance Detection
Inserting cross-attention layers into a pretrained language model and conditioning them on point cloud features yields substantially higher 3D affordance detection performance on 3D AffordanceNet than cosine-similarity baselines.