Video and Text Matching with Conditioned Embeddings

Benchmark Model Rank Results
video-retrieval-on-activitynetOurs#26text-to-video R@1: 25.4text-to-video R@5: 59.1video-to-text R@1: 26.1
video-retrieval-on-lsmdcOurs#24text-to-video R@1: 14.9text-to-video R@5: 33.2video-to-text R@1: 15.3
video-retrieval-on-msr-vttOurs#21text-to-video R@1: 26text-to-video R@5: 56.7