| video-captioning-on-msr-vtt-1 | HiTeA | – | CIDEr: 65.1METEOR: 30.7ROUGE-L: 65.0BLEU-4: 49.2 |
| video-captioning-on-msvd-1 | HiTeA | – | CIDEr: 146.9BLEU-4: 71.0METEOR: 45.3ROUGE-L: 81.4 |
| video-question-answering-on-msrvtt-mc | HiTeA | – | Accuracy: 97.4 |
| video-question-answering-on-next-qa | HiTeA | – | Accuracy: 63.1 |
| video-retrieval-on-activitynet | HiTeA | – | text-to-video R@1: 49.7text-to-video R@5: 77.1… |
| video-retrieval-on-didemo | HiTeA | – | text-to-video R@1: 56.5text-to-video R@5: 81.7… |
| video-retrieval-on-lsmdc | HiTeA | – | text-to-video R@1: 28.7text-to-video R@5: 50.3… |
| video-retrieval-on-msr-vtt-1ka | HiTeA | – | text-to-video R@1: 46.8text-to-video R@5: 71.2… |
| video-retrieval-on-ssv2-label-retrieval | HiTeA | – | text-to-video R@1: 55.2text-to-video R@5: 89.1… |
| video-retrieval-on-ssv2-template-retrieval | HiTeA | – | text-to-video R@1: 85.6text-to-video R@10: 100text-to-video R@5: 100 |
| visual-question-answering-on-msrvtt-qa-1 | HiTeA | – | Accuracy: 0.459 |
| visual-question-answering-on-msvd-qa-1 | HiTeA | – | Accuracy: 0.556 |
| zero-shot-video-retrieval-on-didemo | HiTeA-17M | – | text-to-video R@1: 43.2text-to-video R@5: 69.3… |
| zero-shot-video-retrieval-on-didemo | HiTeA-5M | – | text-to-video R@1: 36.1text-to-video R@5: 60.1… |
| zero-shot-video-retrieval-on-lsmdc | HiTeA-17M | – | text-to-video R@1: 18.3text-to-video R@5: 36.7… |
| zero-shot-video-retrieval-on-lsmdc | HiTeA-5M | – | text-to-video R@1: 15.5text-to-video R@5: 31.1… |
| zero-shot-video-retrieval-on-msr-vtt | HiTeA-17M | – | text-to-video R@1: 34.4text-to-video R@5: 60.0… |
| zero-shot-video-retrieval-on-msr-vtt | HiTeA-5M | – | text-to-video R@1: 29.9text-to-video R@5: 54.2… |