RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval
Open paper
Benchmark
Model
Rank
Results
video-retrieval-on-msr-vtt
RoME
#26
text-to-video R@1: 10.7
text-to-video R@5: 29.6
…
video-retrieval-on-youcook2
RoME
#9
text-to-video R@1: 6.3
text-to-video R@5: 16.9
text-to-video R@10: 25.2
…
Rank counts only results with a code link.