Metric: mAP (higher is better)
| # | Model↕ | mAP▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ControlCap | 18.2 | No | ControlCap: Controllable Region-level Captioning | 2024-01-31 | Code |
| 2 | GRiT (ViT-B) | 15.5 | No | GRiT: A Generative Region-to-text Transformer fo... | 2022-12-01 | Code |
| 3 | CAG-Net | 10.5 | No | Context and Attribute Grounded Dense Captioning | 2019-04-02 | - |
| 4 | FCLN | 5.4 | No | DenseCap: Fully Convolutional Localization Netwo... | 2015-11-24 | Code |