Using CroCo's geometric features as both the encoder and reconstruction target improves object discovery in slot-attention video models, with a one-pass attentional decoder.
Contrastive Learning of Structured World Models,
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
-
Efficient Object-centric Representation Learning with Pre-trained Geometric Prior
Using CroCo's geometric features as both the encoder and reconstruction target improves object discovery in slot-attention video models, with a one-pass attentional decoder.