List your company

Video-to-Text Retrieval on MSRVTT

50.1R@1MAMA
36.0639.70543.3546.995Jun 10, 2025Jul 19, 2025Aug 27, 2025Oct 5, 2025Nov 13, 2025Dec 22, 2025Jan 31, 2026

Evaluation results

MethodLinks
MAMABase Model=CLIP-ViP2026.0150.176.884.8——
DiscoVLABackbone=CLIP (ViT-B/16), # Params (M)=0.562025.0649.27684.7209.98.6
Vid2SeqBase Model=CLIP-ViP2026.0149.174.182.5——
LaViLaBase Model=CLIP-ViP2026.014974.583.4——
CLIP-ViP2026.014872.482.9——
DiscoVLABackbone=CLIP (ViT-B/32), # Params (M)=0.562025.0647.773.683.6204.910
TempMeBackbone=CLIP (ViT-B/16), # Params (M)=0.502025.0647.675.385.4208.39
VindLU2026.014671.880.2——
DGLBackbone=CLIP (ViT-B/16), # Params (M)=0.832025.0645.77482.9202.610.9
TempMeBackbone=CLIP (ViT-B/32), # Params (M)=0.502025.0645.672.481.2199.210.2
MV-AdapterBackbone=CLIP (ViT-B/16), # Params (M)=3.62025.0645.67483.8203.4—
RAPBackbone=CLIP (ViT-B/16), # Params (M)=1.062025.0645.376.484.8206.59.1
DRL2026.0145.172.983.5——
DGLBackbone=CLIP (ViT-B/32), # Params (M)=0.832025.0644.570.780.6195.811.5
RAPBackbone=CLIP (ViT-B/32), # Params (M)=1.062025.064471.982.4198.310.1
AdapterBackbone=CLIP (ViT-B/32), # Params (M)=0.262025.0643.669.980.1193.611.5
VoP F+PBackbone=CLIP (ViT-B/32), # Params (M)=0.42025.0643.671.281.219611
CLIP2Video2026.0143.572.382.1——
Full fine-tuningBackbone=CLIP (ViT-B/32), # Params (M)=123.542025.0643.170.581.2194.812.4
CLIP4Clip2026.0143.170.581.2——
LORABackbone=CLIP (ViT-B/32), # Params (M)=0.492025.064370.282.2195.412
PromptBackbone=CLIP (ViT-B/32), # Params (M)=0.082025.0642.269.779.2191.112.4
VoP F+CBackbone=CLIP (ViT-B/32), # Params (M)=14.102025.0642.17080.6192.713.4
VIOLET2026.0136.664.175.1——