Zero-Shot Video Retrieval on VATEX

Metric: text-to-video R@5 (higher is better)

LeaderboardDataset
Loading chart...
#Modeltext-to-video R@5Extra DataPaperDateCode
1InternVideo2-6B94YesInternVideo2: Scaling Foundation Models for Mult...2024-03-22Code
2InternVideo2-1B93.4YesInternVideo2: Scaling Foundation Models for Mult...2024-03-22Code
3VideoCoCa83.3YesVideoCoCa: Video-Text Modeling with Zero-Shot Tr...2022-12-09-