Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval

Benchmark Model Rank Results
video-retrieval-on-querydFrozen#4text-to-video R@1: 53.8text-to-video R@5: 75.7…
video-retrieval-on-msr-vttFROZEN#18text-to-video R@1: 32.5text-to-video R@5: 61.5…
video-retrieval-on-msvdFROZEN#18text-to-video R@1: 33.7text-to-video R@5: 64.7…
video-retrieval-on-lsmdcFROZEN#23text-to-video R@1: 15.0text-to-video R@5: 30.8…
zero-shot-video-retrieval-on-didemoFROZEN#23text-to-video R@1: 21.1text-to-video R@5: 46.0…
zero-shot-video-retrieval-on-didemoM. Bain et. al.#24text-to-video R@1: 20.2text-to-video R@5: 46.4…
video-retrieval-on-didemoFROZEN#30text-to-video R@1: 31.0text-to-video R@5: 59.8…
zero-shot-video-retrieval-on-msr-vttFROZEN#31text-to-video R@1: 24.7text-to-video R@5: 46.9…
video-retrieval-on-msr-vtt-1kaFROZEN#45text-to-video R@1: 31.0text-to-video R@5: 59.5…