| action-classification-on-kinetics-400 | CoCa (finetuned) | #16 | Acc@1: 88.9 |
| action-classification-on-kinetics-400 | CoCa (frozen) | #23 | Acc@1: 88.0 |
| action-classification-on-kinetics-600 | CoCa (finetuned) | #13 | Top-1 Accuracy: 89.4 |
| action-classification-on-kinetics-600 | CoCa (frozen) | #16 | Top-1 Accuracy: 88.5 |
| action-classification-on-kinetics-700 | CoCa (finetuned) | #8 | Top-1 Accuracy: 82.7 |
| action-classification-on-kinetics-700 | CoCa (frozen) | #10 | Top-1 Accuracy: 81.1 |
| action-classification-on-moments-in-time-2 | CoCa (finetuned) | #1 | Top 1 Accuracy: 49.0 |
| action-classification-on-moments-in-time-2 | CoCa (frozen) | #2 | Top 1 Accuracy: 47.4 |
| image-captioning-on-coco-captions | CoCa | #15 | BLEU-4: 40.9CIDER: 143.6METEOR: 33.9SPICE: 24.7 |
| image-classification-on-imagenet | CoCa (finetuned) | #1 | Top 1 Accuracy: 91.0%Number of params: 2100M |
| image-classification-on-objectnet | CoCa | #1 | Top-1 Accuracy: 82.7 |
| video-retrieval-on-msr-vtt | CoCa (zero-shot) | #17 | text-to-video R@1: 30.0text-to-video R@5: 52.4… |
| visual-entailment-on-snli-ve-test | CoCa | #3 | Accuracy: 87.1 |
| visual-entailment-on-snli-ve-val | CoCa | #3 | Accuracy: 87.0 |
| visual-question-answering-on-vqa-v2-test-dev-1 | CoCa | #1 | Accuracy: 82.3 |
| visual-reasoning-on-nlvr2-dev | CoCa | #5 | Accuracy: 86.1 |
| visual-reasoning-on-nlvr2-test | CoCa | #4 | Accuracy: 87.0 |
| zero-shot-cross-modal-retrieval-on-coco-2014 | CoCa | #9 | Image-to-text R@1: 66.3Image-to-text R@5: 86.2… |
| zero-shot-cross-modal-retrieval-on-flickr30k | CoCa | #5 | Image-to-text R@1: 92.5Image-to-text R@5: 99.5… |
| zero-shot-transfer-image-classification-on-1 | CoCa | #2 | Accuracy (Private): 86.3 |
| zero-shot-transfer-image-classification-on-3 | CoCa | #2 | Accuracy (Private): 80.7 |
| zero-shot-transfer-image-classification-on-4 | CoCa | #1 | Accuracy: 96.5 |
| zero-shot-transfer-image-classification-on-5 | CoCa | #1 | Accuracy (Private): 90.2 |
| zero-shot-transfer-image-classification-on-6 | CoCa | #3 | Accuracy (Private): 82.7 |
| zero-shot-transfer-image-classification-on-8 | CoCa | #1 | Accuracy (Private): 77.6 |