MoCHA canonicalizes captions to motion-recoverable semantics before contrastive training, cutting within-motion embedding variance by 11-19% and lifting T2M R@1 by 3.1pp on HumanML3D and 10.3pp on KIT-ML.
In: ICML (2021)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Self-supervised cross-modal contrastive learning coordinates plankton image and profile data to enable accurate species recognition from minimal labeled images.
citing papers explorer
-
MoCHA: Denoising Caption Supervision for Motion-Text Retrieval
MoCHA canonicalizes captions to motion-recoverable semantics before contrastive training, cutting within-motion embedding variance by 11-19% and lifting T2M R@1 by 3.1pp on HumanML3D and 10.3pp on KIT-ML.
-
Cross-modal learning for plankton recognition
Self-supervised cross-modal contrastive learning coordinates plankton image and profile data to enable accurate species recognition from minimal labeled images.