📊 Showing 2 results | 📏 Metric: CIDEr
| Rank | Model | Paper | CIDEr | Date | Code |
|---|---|---|---|---|---|
| 1 | Shot2Story | Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos | 10.70 | 2023-12-16 | 📦 bytedance/Shot2Story |
| 2 | Shotluck-Holmes (3.1B) | Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization | 8.70 | 2024-05-31 | 📦 Skyline-9/Shotluck-Holmes |