Multimodal Contrastive Learning

The dataset used in the paper is a collection of pairs of observations (xi, ˜xi) from two modalities, where xi ∈ Rd1 and ˜xi ∈ Rd2. The dataset is used to evaluate the performance of multimodal contrastive learning (MMCL) on feature learning ability.

Data and Resources

Cite this as

Ryumei Nakada, Halil Ibrahim Gulluk, Zhun Deng, Wenlong Ji, James Zou, Lijnjun Zhang (2024). Dataset: Multimodal Contrastive Learning. https://doi.org/10.57702/8qk2bm7r

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2302.06232
Author Ryumei Nakada
More Authors
Halil Ibrahim Gulluk
Zhun Deng
Wenlong Ji
James Zou
Lijnjun Zhang