📊 Showing 3 results | 📏 Metric: SODA
| Rank | Model | Paper | SODA | Date | Code |
|---|---|---|---|---|---|
| 1 | HiCM² 📚 | HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning | 51.20 | 2024-12-19 | 📦 ailab-kyunghee/HiCM2-DVC |
| 2 | Vid2Seq 📚 | Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning | 43.50 | 2023-02-27 | 📦 google-research/scenic 📦 antoyang/VidChapters 📦 KastanDay/video-pretrained-transformer |
| 3 | E2ESG 📚 | End-to-end Dense Video Captioning as Sequence Generation | 25.00 | 2022-04-18 | - |