Video Captioning On Shot2Story20K
Metriken
BLEU-4
CIDEr
METEOR
ROUGE
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | BLEU-4 | CIDEr | METEOR | ROUGE | Paper Title | Repository |
|---|---|---|---|---|---|---|
| Shotluck-Holmes (3.1B) | 8.7 | 63.2 | 25.7 | 36.2 | Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization | |
| Shot2Story | 10.7 | 37.4 | 16.2 | 29.6 | Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos |
0 of 2 row(s) selected.