A soft-weighted contrastive loss using rank-gap affinity and disparity terms learns globally consistent ordinal embeddings and reaches SOTA on age, BIQA, and BVQA benchmarks.
To enhance the temporal representations, we further refine the extracted temporal feature maps using a transformer module
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Contrastive Order Learning: A General Framework for Ordinal Regression
A soft-weighted contrastive loss using rank-gap affinity and disparity terms learns globally consistent ordinal embeddings and reaches SOTA on age, BIQA, and BVQA benchmarks.