Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning
Open paper
Benchmark
Model
Rank
Results
video-retrieval-on-msr-vtt-1ka
EERCF
#4
text-to-video R@1: 54.1
text-to-video R@5: 78.8
…
Rank counts only results with a code link.