Align and Prompt: Video-and-Language Pre-training with Entity Prompts

Benchmark Model Rank Results
visual-question-answering-on-msrvtt-qaALPRO#18Accuracy: 0.421
zero-shot-video-retrieval-on-didemoALPRO#20text-to-video R@1: 23.8text-to-video R@5: 47.3…
visual-question-answering-on-msvd-qaALPRO#23Accuracy: 0.459
video-retrieval-on-didemoALPRO#29text-to-video R@1: 35.9text-to-video R@5: 67.5…
zero-shot-video-retrieval-on-msr-vttALPRO#32text-to-video R@1: 24.1text-to-video R@5: 44.7…