Video Captioning Evaluation Correlation on VATEX Eval
50.8Kendall's Tau-bRIGEL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RIGELSetting=Reference-based2026.06 | 50.8 | 64 | |
| G-VEvalReference Setting=9-References, Metric Category=Multimodal - image-based2025.09 | 48.1 | — | |
| G-VEvalSetting=Reference-based2026.06 | 48.1 | — | |
| RIGELSetting=Reference-based2026.06 | 45.6 | 57.8 | |
| G-VEvalReference Setting=1-Reference, Metric Category=Multimodal - image-based2025.09 | 44.9 | — | |
| G-VEvalSetting=Reference-based2026.06 | 44.9 | — | |
| VC-Inspector-7BReference Setting=No Reference, Metric Category=Multimodal - video-based, Model Scale=7B2025.09 | 42.58 | 45.99 | |
| RIGELSetting=Reference-free2026.06 | 42.1 | 53.7 | |
| RIGELSetting=Reference-free2026.06 | 42.1 | 53.7 | |
| RefPAC-S++Setting=Reference-based2026.06 | 39.8 | 50.8 | |
| G-VEvalReference Setting=No Reference, Metric Category=Multimodal - image-based2025.09 | 39.4 | — | |
| G-VEvalSetting=Reference-free2026.06 | 39.4 | — | |
| G-VEvalSetting=Reference-free2026.06 | 39.4 | — | |
| PAC-SReference Setting=9-References, Metric Category=Multimodal - image-based2025.09 | 38.1 | — | |
| RefPAC-SSetting=Reference-based2026.06 | 38.1 | 48.8 | |
| VC-Inspector-3BReference Setting=No Reference, Metric Category=Multimodal - video-based, Model Scale=3B2025.09 | 37.99 | 42.45 | |
| EMScoreSetting=Reference-based2026.06 | 36.8 | 47.2 | |
| EMScoreReference Setting=9-References, Metric Category=Multimodal - image-based2025.09 | 36.66 | 47 | |
| Soft-SPICEReference Setting=9-References, Metric Category=Language-based2025.09 | 36.31 | 46.41 | |
| FactVCReference Setting=9-References, Metric Category=Multimodal - image-based2025.09 | 36.18 | 46.33 | |
| CLAIRReference Setting=1-Reference, Metric Category=Language-based2025.09 | 36 | — | |
| CLIPScoreReference Setting=9-References, Metric Category=Multimodal - image-based2025.09 | 35.21 | 45.28 | |
| CLAIRReference Setting=9-References, Metric Category=Language-based2025.09 | 34.8 | — | |
| Qwen2.5-VL-7BReference Setting=No Reference, Metric Category=Multimodal - video-based, Model Scale=7B2025.09 | 34.7 | 39.4 | |
| RefPAC-S++Setting=Reference-based2026.06 | 32.2 | 41.5 | |
| PAC-SReference Setting=1-Reference, Metric Category=Multimodal - image-based2025.09 | 31.4 | — | |
| RefPAC-SSetting=Reference-based2026.06 | 31.4 | 40.5 | |
| Qwen2.5-VL-3BReference Setting=No Reference, Metric Category=Multimodal - video-based, Model Scale=3B2025.09 | 31.29 | 36.43 | |
| ViCLIPScoreReference Setting=No Reference, Metric Category=Multimodal - video-based2025.09 | 30.92 | 39.86 | |
| FactVCReference Setting=1-Reference, Metric Category=Multimodal - image-based2025.09 | 28.78 | 37.22 | |
| BLEU_1Reference Setting=9-References, Metric Category=Language-based2025.09 | 28.7 | 36.88 | |
| EMScoreReference Setting=1-Reference, Metric Category=Multimodal - image-based2025.09 | 28.63 | 37.05 | |
| EMScoreSetting=Reference-based2026.06 | 28.6 | 37.1 | |
| PAC-S++Setting=Reference-free2026.06 | 28.1 | 36.4 | |
| PAC-S++Setting=Reference-free2026.06 | 28.1 | 36.4 | |
| CIDErReference Setting=9-References, Metric Category=Language-based2025.09 | 27.92 | 36.18 | |
| METEORReference Setting=9-References, Metric Category=Language-based2025.09 | 27.64 | 35.76 | |
| SPICEReference Setting=9-References, Metric Category=Language-based2025.09 | 27.41 | 35.4 | |
| CLIPScoreReference Setting=1-Reference, Metric Category=Multimodal - image-based2025.09 | 27.39 | 35.49 | |
| SPICE-factualReference Setting=9-References, Metric Category=Language-based2025.09 | 26.05 | 35.58 | |
| PAC-SReference Setting=No Reference, Metric Category=Multimodal - image-based2025.09 | 25.1 | — | |
| PAC-SSetting=Reference-free2026.06 | 25.1 | 32.6 | |
| PAC-SSetting=Reference-free2026.06 | 25.1 | 32.6 | |
| BERTScoreReference Setting=9-References, Metric Category=Language-based2025.09 | 25.05 | 32.37 | |
| ROUGE-LReference Setting=9-References, Metric Category=Language-based2025.09 | 23.94 | 31.06 | |
| EMScoreSetting=Reference-free2026.06 | 23.2 | 30.3 | |
| EMScoreSetting=Reference-free2026.06 | 23.2 | 30.3 | |
| EMScoreReference Setting=No Reference, Metric Category=Multimodal - image-based2025.09 | 22.88 | 29.79 | |
| FactVCReference Setting=No Reference, Metric Category=Multimodal - image-based2025.09 | 22.79 | 29.69 | |
| BLEU_4Reference Setting=9-References, Metric Category=Language-based2025.09 | 22.76 | 25.6 | |
| CLIPScoreReference Setting=No Reference, Metric Category=Multimodal - image-based2025.09 | 22.33 | 29.09 | |
| Soft-SPICEReference Setting=1-Reference, Metric Category=Language-based2025.09 | 21.25 | 27.61 | |
| CIDErReference Setting=1-Reference, Metric Category=Language-based2025.09 | 17.62 | 23.02 | |
| METEORReference Setting=1-Reference, Metric Category=Language-based2025.09 | 16.68 | 21.8 | |
| BERTScoreReference Setting=1-Reference, Metric Category=Language-based2025.09 | 15.24 | 19.82 | |
| SPICEReference Setting=1-Reference, Metric Category=Language-based2025.09 | 14.8 | 18.78 | |
| SPICE-factualReference Setting=1-Reference, Metric Category=Language-based2025.09 | 13.59 | 17.04 | |
| ROUGE-LReference Setting=1-Reference, Metric Category=Language-based2025.09 | 12.94 | 16.89 | |
| BLEU_1Reference Setting=1-Reference, Metric Category=Language-based2025.09 | 12.65 | 16.52 | |
| BLEU_4Reference Setting=1-Reference, Metric Category=Language-based2025.09 | 12.44 | 14.81 |