Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring

Benchmark Model Rank Results
video-retrieval-on-didemoSTAN#14text-to-video R@1: 54.6text-to-video R@5: 78.4
video-retrieval-on-lsmdcSTAN#9text-to-video R@1: 29.2text-to-video R@5: 49.5
video-retrieval-on-msr-vtt-1kaSTAN#3text-to-video R@1: 54.1text-to-video R@5: 79.5