CALM generates and aligns class probability distributions across modalities via class anchors and a cross-modal probabilistic VAE, claiming superior out-of-domain performance on benchmarks.
Msr-vtt: A large video description dataset for bridging video and language
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generative Modeling of Class Probability for Multi-Modal Representation Learning
CALM generates and aligns class probability distributions across modalities via class anchors and a cross-modal probabilistic VAE, claiming superior out-of-domain performance on benchmarks.