Grounded Situation Recognition on SWiG (dev)
76.17Value AccuracyCoFormer
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CoFormerEvaluation Setting=Ground-Truth Verb2022.03 | 76.17 | — | 42.11 | 61.15 | 23.09 | |
| SituFormerVerb setting=Ground-Truth-Verb, Model category=Grounded Situation Recognition Models2021.12 | 76.08 | — | 42.15 | 61.82 | 24.65 | |
| GSRTRVerb prediction scenario=ground-truth verb2021.11 | 74.27 | — | 39.24 | 58.33 | 20.19 | |
| GSRTREvaluation Setting=Ground-Truth Verb2022.03 | 74.27 | — | 39.24 | 58.33 | 20.19 | |
| CAQVerb setting=Ground-Truth-Verb, Model category=Situation Recognition Models2021.12 | 73.62 | — | 38.71 | — | — | |
| JSLVerb prediction scenario=ground-truth verb2021.11 | 73.53 | — | 38.32 | 57.5 | 19.29 | |
| JSLVerb setting=Ground-Truth-Verb, Model category=Grounded Situation Recognition Models2021.12 | 73.53 | — | 38.32 | 57.5 | 19.29 | |
| JSLEvaluation Setting=Ground-Truth Verb2022.03 | 73.53 | — | 38.32 | 57.5 | 19.29 | |
| Kernel-GraphVerb setting=Ground-Truth-Verb, Model category=Situation Recognition Models2021.12 | 73.14 | — | 41.68 | — | — | |
| ISLVerb prediction scenario=ground-truth verb2021.11 | 72.77 | — | 37.49 | 52.92 | 15 | |
| ISLVerb setting=Ground-Truth-Verb, Model category=Grounded Situation Recognition Models2021.12 | 72.77 | — | 37.49 | 52.92 | 15 | |
| ISLEvaluation Setting=Ground-Truth Verb2022.03 | 72.77 | — | 37.49 | 52.92 | 15 | |
| GSRTR w/o VEVerb prediction scenario=ground-truth verb2021.11 | 72.55 | — | 37.07 | 57 | 18.93 | |
| CRF+DataAugVerb setting=Ground-Truth-Verb, Model category=Situation Recognition Models2021.12 | 70.8 | — | 34.82 | — | — | |
| VGG+RNNVerb setting=Ground-Truth-Verb, Model category=Situation Recognition Models2021.12 | 70.48 | — | 35.56 | — | — | |
| FC-GraphVerb setting=Ground-Truth-Verb, Model category=Situation Recognition Models2021.12 | 68.89 | — | 41.07 | — | — | |
| CRFVerb setting=Ground-Truth-Verb, Model category=Situation Recognition Models2021.12 | 65.9 | — | 29.5 | — | — | |
| CoFormerEvaluation Setting=Top-5 Predicted Verbs2022.03 | 57.58 | 72.98 | 34.09 | 46.7 | 19.06 | |
| Kernel-GraphVerb setting=Top-5-Verb, Model category=Situation Recognition Models2021.12 | 56.32 | 68.55 | 30.56 | — | — | |
| SituFormerVerb setting=Top-5-Verb, Model category=Grounded Situation Recognition Models2021.12 | 55.85 | 71.01 | 33.38 | 45.78 | 19.77 | |
| GSRTRVerb prediction scenario=top-5 predicted verbs2021.11 | 53.69 | 69.46 | 30.66 | 42.61 | 15.98 | |
| GSRTREvaluation Setting=Top-5 Predicted Verbs2022.03 | 53.69 | 69.46 | 30.66 | 42.61 | 15.98 | |
| GSRTR w/o VEVerb prediction scenario=top-5 predicted verbs2021.11 | 53.09 | 69.33 | 29.78 | 42.01 | 15.36 | |
| JSLVerb prediction scenario=top-5 predicted verbs2021.11 | 52.06 | 67.71 | 29.73 | 41.25 | 15.07 | |
| JSLVerb setting=Top-5-Verb, Model category=Grounded Situation Recognition Models2021.12 | 52.06 | 67.71 | 29.73 | 41.25 | 15.07 | |
| JSLEvaluation Setting=Top-5 Predicted Verbs2022.03 | 52.06 | 67.71 | 29.73 | 41.25 | 15.07 | |
| CAQVerb setting=Top-5-Verb, Model category=Situation Recognition Models2021.12 | 50.3 | 64.99 | 29.17 | — | — | |
| ISLVerb prediction scenario=top-5 predicted verbs2021.11 | 50.29 | 65.74 | 28.59 | 36.9 | 11.66 | |
| ISLVerb setting=Top-5-Verb, Model category=Grounded Situation Recognition Models2021.12 | 50.29 | 65.74 | 28.59 | 36.9 | 11.66 | |
| ISLEvaluation Setting=Top-5 Predicted Verbs2022.03 | 50.29 | 65.74 | 28.59 | 36.9 | 11.66 | |
| VGG+RNNVerb setting=Top-5-Verb, Model category=Situation Recognition Models2021.12 | 47.09 | 63.11 | 26.48 | — | — | |
| CRF+DataAugVerb setting=Top-5-Verb, Model category=Situation Recognition Models2021.12 | 46.72 | 62.21 | 25.66 | — | — | |
| FC-GraphVerb setting=Top-5-Verb, Model category=Situation Recognition Models2021.12 | 45.23 | 61.8 | 29.98 | — | — | |
| CRFVerb setting=Top-5-Verb, Model category=Situation Recognition Models2021.12 | 42.68 | 58.64 | 22.75 | — | — | |
| CoFormerEvaluation Setting=Top-1 Predicted Verb2022.03 | 35.87 | 44.41 | 22.47 | 29.37 | 12.94 | |
| SituFormerVerb setting=Top-1-Verb, Model category=Grounded Situation Recognition Models2021.12 | 35.35 | 44.32 | 22.1 | 29.17 | 13.33 | |
| Kernel-GraphVerb setting=Top-1-Verb, Model category=Situation Recognition Models2021.12 | 35.18 | 43.21 | 19.46 | — | — | |
| GSRTRVerb prediction scenario=top-1 predicted verb2021.11 | 32.52 | 41.06 | 19.63 | 26.04 | 10.44 | |
| GSRTREvaluation Setting=Top-1 Predicted Verb2022.03 | 32.52 | 41.06 | 19.63 | 26.04 | 10.44 | |
| GSRTR w/o VEVerb prediction scenario=top-1 predicted verb2021.11 | 32.05 | 40.81 | 19.31 | 25.64 | 10.31 | |
| JSLVerb prediction scenario=top-1 predicted verb2021.11 | 31.18 | 39.6 | 18.85 | 25.03 | 10.16 | |
| JSLVerb setting=Top-1-Verb, Model category=Grounded Situation Recognition Models2021.12 | 31.18 | 39.6 | 18.85 | 25.03 | 10.16 | |
| JSLEvaluation Setting=Top-1 Predicted Verb2022.03 | 31.18 | 39.6 | 18.85 | 25.03 | 10.16 | |
| ISLVerb prediction scenario=top-1 predicted verb2021.11 | 30.47 | 38.83 | 18.23 | 22.47 | 7.64 | |
| ISLVerb setting=Top-1-Verb, Model category=Grounded Situation Recognition Models2021.12 | 30.47 | 38.83 | 18.23 | 22.47 | 7.64 | |
| ISLEvaluation Setting=Top-1 Predicted Verb2022.03 | 30.47 | 38.83 | 18.23 | 22.47 | 7.64 | |
| CAQVerb setting=Top-1-Verb, Model category=Situation Recognition Models2021.12 | 30.15 | 37.96 | 18.58 | — | — | |
| VGG+RNNVerb setting=Top-1-Verb, Model category=Situation Recognition Models2021.12 | 27.74 | 36.11 | 16.6 | — | — | |
| FC-GraphVerb setting=Top-1-Verb, Model category=Situation Recognition Models2021.12 | 27.52 | 36.93 | 19.15 | — | — | |
| CRF+DataAugVerb setting=Top-1-Verb, Model category=Situation Recognition Models2021.12 | 25.39 | 34.2 | 15.61 | — | — | |
| CRFVerb setting=Top-1-Verb, Model category=Situation Recognition Models2021.12 | 24.56 | 32.25 | 14.28 | — | — |