Zero-Shot Video Retrieval on MSR-VTT-full

Metric: text-to-video R@10 (higher is better)

LeaderboardDataset
Loading chart...
#Modeltext-to-video R@10Extra DataPaperDateCode
1InternVL-G79.6YesInternVL: Scaling up Vision Foundation Models an...2023-12-21Code
2InternVL-C78.4NoInternVL: Scaling up Vision Foundation Models an...2023-12-21Code
3VideoCoCa67YesVideoCoCa: Video-Text Modeling with Zero-Shot Tr...2022-12-09-