List your company

Video-Text Retrieval on MSRVTT

44.7GFLOPSvid-TLDR
35.77696.013156.25216.487Mar 20, 2024

Evaluation results

MethodLinks
vid-TLDRbackbone=UMT-B, pretraining_pairs=25M, eval_protocol=zero-shot2024.0344.733.354.733.3
vid-TLDRbackbone=UMT-B, pretraining_pairs=5M, eval_protocol=zero-shot2024.0350.227.749.858.3
vid-TLDRbackbone=UMT-B, pretraining_pairs=17M, eval_protocol=zero-shot2024.0350.633.85766.6
UMT + ToMebackbone=UMT-B, pretraining_pairs=5M, eval_protocol=zero-shot2024.0366.226.446.755.9
UMT + ToMebackbone=UMT-B, pretraining_pairs=17M, eval_protocol=zero-shot2024.0366.232.554.163.9
UMT + ToMebackbone=UMT-B, pretraining_pairs=25M, eval_protocol=zero-shot2024.0366.231.152.831.1
UMT (Base)backbone=UMT-B, pretraining_pairs=5M, eval_protocol=zero-shot2024.0378.527.949.858.4
UMT (Base)backbone=UMT-B, pretraining_pairs=17M, eval_protocol=zero-shot2024.0378.533.656.466.4
UMT (Base)backbone=UMT-B, pretraining_pairs=25M, eval_protocol=zero-shot2024.0378.532.854.332.8
vid-TLDRbackbone=UMT-L, pretraining_pairs=25M, eval_protocol=zero-shot2024.03146.539.261.239.2
UMT + ToMebackbone=UMT-L, pretraining_pairs=25M, eval_protocol=zero-shot2024.03160.936.35936.3
vid-TLDRbackbone=UMT-L, pretraining_pairs=17M, eval_protocol=zero-shot2024.0316339.961.970.9
vid-TLDRbackbone=UMT-L, pretraining_pairs=5M, eval_protocol=zero-shot2024.03164.832.755.164.6
UMT + ToMebackbone=UMT-L, pretraining_pairs=5M, eval_protocol=zero-shot2024.03182.130.452.462.9
UMT + ToMebackbone=UMT-L, pretraining_pairs=17M, eval_protocol=zero-shot2024.03182.137.660.168.9
UMT (Base)backbone=UMT-L, pretraining_pairs=5M, eval_protocol=zero-shot2024.03267.831.854.764.2
UMT (Base)backbone=UMT-L, pretraining_pairs=17M, eval_protocol=zero-shot2024.03267.840.66271.4
UMT (Base)backbone=UMT-L, pretraining_pairs=25M, eval_protocol=zero-shot2024.03267.838.961.138.9