RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval

Benchmark Model Rank Results
video-retrieval-on-msr-vttRoME#26text-to-video R@1: 10.7text-to-video R@5: 29.6
video-retrieval-on-youcook2RoME#9text-to-video R@1: 6.3text-to-video R@5: 16.9text-to-video R@10: 25.2