Metric: Top-5 Verbs (higher is better)
| # | Model↕ | Top-5 Verbs▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | ClipSitu | 85.69 | No | ClipSitu: Effectively Leveraging CLIP for Condit... | 2023-07-02 | Code |
| 2 | CoFormer | 73.31 | No | Collaborative Transformers for Grounded Situatio... | 2022-03-30 | Code |
| 3 | SituFormer | 71.21 | No | Rethinking the Two-Stage Framework for Grounded ... | 2021-12-10 | Code |
| 4 | GSRTR | 69.81 | No | Grounded Situation Recognition with Transformers | 2021-11-19 | Code |
| 5 | Kernel GraphNet | 68.72 | No | - | - | - |
| 6 | JSL | 67.6 | No | Grounded Situation Recognition | 2020-03-26 | Code |
| 7 | ISL | 65.51 | No | Grounded Situation Recognition | 2020-03-26 | Code |
| 8 | CAQ + RE-VGG | 65.05 | No | - | - | Code |
| 9 | RNN + Fusion | 63.08 | No | Recurrent Models for Situation Recognition | 2017-03-18 | - |
| 10 | CRF + Aug | 62.59 | No | Commonly Uncommon: Semantic Sparsity in Situatio... | 2016-12-03 | Code |
| 11 | GraphNet | 61.9 | No | Situation Recognition with Graph Neural Networks | 2017-08-14 | Code |
| 12 | CRF | 58.88 | No | - | - | Code |