Zero Shot Video Retrieval On Vatex
Metriken
text-to-video R@1
text-to-video R@10
video-to-text R@1
video-to-text R@10
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | text-to-video R@1 | text-to-video R@10 | video-to-text R@1 | video-to-text R@10 |
|---|---|---|---|---|
| gramian-multimodal-representation-learning | 83.9 | 99.5 | 82.7 | 99 |
| video-text-modeling-with-zero-shot-transfer | 53.2 | 90.1 | 73.6 | 97.2 |
| internvideo2-scaling-video-foundation-models | 71.5 | 97.1 | 85.3 | 99.3 |
| internvideo-general-video-foundation-models | 49.5 | - | 69.5 | - |
| internvideo2-scaling-video-foundation-models | 70.4 | 96.9 | 85.4 | 99.1 |