Hyperbolic Gramian Volumes for Multimodal Alignment
Open paper
Benchmark
Model
Rank
Results
zero-shot-video-retrieval-on-msr-vtt
HyperGRAM (extra data)
–
text-to-video R@1: 56.6
zero-shot-video-retrieval-on-msr-vtt-video-to-text
HyperGRAM (extra data)
–
R@1: 53.6
Rank counts only results with a code link.