Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Text-to-Video-Audio Retrieval on VALOR-32K

78.7Recall@1

MiCo

Updated 1mo ago

Evaluation Results

Method	Links
MiCo 2024.06		78.7
SOTA 2024.06		73.2

SOTA Paper

MiCo

Explore the Limits of Omni-modal Pretraining at Scale

Dataset

VALOR

Follow for update

@wizwand_team Discord

Related Benchmarks

Text-to-Image Retrieval on Flickr Text-to-Video-Audio Retrieval on YouCook2 Depth Perception on NYU-D Thermal Sensing on SYSU IMU Perception on Ego4D

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs