Metric: CIDEr (higher is better)
| # | Model↕ | CIDEr▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GVL | 33.33 | No | Learning Grounded Vision-Language Representation... | 2023-03-11 | Code |
| 2 | CM² | 33.01 | No | Do You Remember? Dense Video Captioning with Cro... | 2024-04-11 | Code |
| 3 | PDVC (TSP features, no SCST) | 31.14 | No | End-to-End Dense Video Captioning with Parallel ... | 2021-08-17 | Code |
| 4 | Vid2Seq | 28 | Yes | Vid2Seq: Large-Scale Pretraining of a Visual Lan... | 2023-02-27 | Code |
| 5 | VTimeLLM | 27.6 | No | VTimeLLM: Empower LLM to Grasp Video Moments | 2023-11-30 | Code |
| 6 | ADV-INF + Global | 19.4 | No | - | - | Code |