CLIP2TV: Align, Match and Distill for Video-Text Retrieval

Benchmark Model Rank Results
video-retrieval-on-msr-vttCLIP2TVtext-to-video R@1: 33.1text-to-video R@5: 58.9
video-retrieval-on-msr-vtt-1kaCLIP2TVtext-to-video R@1: 52.9text-to-video R@5: 78.5