Video Retrieval On Tvr
Metriken
R@1
R@10
R@100
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | R@1 | R@10 | R@100 | Paper Title | Repository |
|---|---|---|---|---|---|
| Hero w/ pre-training | 4.34 | 13.97 | 21.78 | HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training | |
| XML (Lei et al., 2020) | - | 8.93 | - | TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval |
0 of 2 row(s) selected.