Video Captioning on ActivityNet Captions (val)
20.04METEORPRISM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| PRISM2026.01 | 20.04 | — | 1.02 | |
| ADV-INF + Global2026.01 | 16.36 | — | 9.45 | |
| Mun et al.RL optimization=true, Full Dataset available=true2020.05 | 13.07 | 4.41 | 1.28 | |
| MCCL2026.01 | 12.52 | — | 3.89 | |
| iPerceive2026.01 | 12.27 | — | 2.98 | |
| PDVCInput Features=TSN features2026.01 | 11.27 | — | 3.07 | |
| Zhou et al.RL optimization=false, Full Dataset available=true2020.05 | 11.16 | 5.76 | 2.71 | |
| Iashin et al.RL optimization=false, Full Dataset available=false2020.05 | 11.07 | 4.52 | 1.98 | |
| Bi-modal Transformer (BMT)RL optimization=false, Full Dataset available=false2020.05 | 10.9 | 4.63 | 1.99 | |
| BMT2026.01 | 10.9 | — | 1.99 | |
| Wang et al.RL optimization=false, Full Dataset available=true2020.05 | 10.89 | — | — | |
| Li et al.RL optimization=true, Full Dataset available=true2020.05 | 10.33 | 4.55 | 1.62 | |
| GVL2026.01 | 10.03 | — | 1.11 | |
| Streaming Vid2Seq2026.01 | 10 | — | — | |
| Li et al.RL optimization=false, Full Dataset available=true2020.05 | 9.31 | 4.51 | 1.71 | |
| Streaming GIT2026.01 | 9 | — | — | |
| Krishna et al.RL optimization=false, Full Dataset available=true2020.05 | 8.88 | 4.09 | 1.6 | |
| TSP2026.01 | 8.75 | — | 2.02 | |
| PR-DETR2026.01 | 8.72 | — | 2.58 | |
| CM^22026.01 | 8.55 | — | 2.38 | |
| Vid2Seq2026.01 | 8.5 | — | — | |
| Rahman et al.RL optimization=false, Full Dataset available=false2020.05 | 7.23 | 3.04 | 1.46 |