Holistic Features are almost Sufficient for Text-to-Video Retrieval

Benchmark Model Rank Results
video-retrieval-on-msr-vtt-1kaTeachCLIP (ViT-B/16)#22text-to-video R@1: 48.0text-to-video R@5: 75.9
video-retrieval-on-msr-vtt-1kaTeachCLIP#27text-to-video R@1: 46.8text-to-video R@5: 74.3
video-retrieval-on-vatexTeachCLIP#9text-to-video R@1: 63.6text-to-video R@5: 91.9