Share your thoughts, 1 month free Claude Pro on usSee more

Text-to-Video Retrieval on MSVD

77.08R@1

Gemini Embedding 2

Updated 7d ago

Evaluation Results

Method
Gemini Embedding 2 2026.05	77.08	-	-	-	-	-	-
UMT 2024.03	71.9	94.5	97.8	-	-	-	-
mPLUG2+ 2025.12	69.1	84.5	93.8	-	-	-	-
OmniRetriever-7B 2026.05	66.88	-	-	-	-	-	-
mPLUG2+ 2025.12	66.8	82.7	90.3	-	-	-	-
mPLUG2 2025.12	65.3	82	90.6	-	-	-	-
mPLUG2 2025.12	62.1	77.3	87.9	-	-	-	-
InternVideo2s2-6B 2024.03	61.4	-	-	-	-	-	-
VidVec 2026.02	60.9	-	-	-	-	-	-
PEAV-B 2025.12	60.8	-	-	-	-	-	-
PEAV-L 2025.12	60.8	-	-	-	-	-	-
PEAV-B 2025.12	60.7	-	-	-	-	-	-
PEAV-L 2025.12	60.5	-	-	-	-	-	-
PEAV-S 2025.12	60.1	-	-	-	-	-	-
PEAV-S 2025.12	59.8	-	-	-	-	-	-
PE-Core-G 2026.02	59.7	-	-	-	-	-	-
PE-G 2025.12	59.7	-	-	-	-	-	-
PE-coreG 2026.05	59.7	-	-	-	-	-	-
InternVideo2_S2-6B 2024.12	59.3	84.4	89.6	-	-	-	-
InternVideo2-6B 2026.02	59.3	-	-	-	-	-	-
InternVideo2_s2-6B 2025.07	59.3	84.4	89.6	-	-	-	-
InternVideo2-6B 2025.03	59.3	84.4	89.6	-	-	-	-
CLIP2video 2022.06	58.7	-	-	-	-	-	-
InternVideo 2023.05	58.4	84.5	90.4	-	-	233.3	-
InternVideo 2023.03	58.4	84.5	90.4	-	-	-	-
InternVideo(ViT-L) 2024.03	58.4	84.5	90.4	-	-	-	-
InternVideo 2024.03	58.4	-	-	-	-	-	-
UMT-L 2023.03	58.2	83.9	89.6	-	-	-	-
UMT-L 2024.03	58.2	-	-	-	-	-	-
UMT-L 2024.03	58.2	-	-	-	-	-	-
InternVideo2 2025.12	58.1	-	-	-	-	-	-
InternVideo2-1B 2026.05	58.1	-	-	-	-	-	-
UMT-L + vid-TLDR 2024.03	57.9	-	-	-	-	-	-
VLAB_G 2023.05	57.5	83.6	89.9	-	-	231.1	-
HAT-VTR 2026.02	57.46	85.97	92.84	-	-	-	-
UMT-L 2023.03	57.4	83	88.5	-	-	-	-
PE-L 2025.12	57.2	-	-	-	-	-	-
PE-coreL 2026.05	57.2	-	-	-	-	-	-
Xpool 2026.02	55.97	85.37	91.79	-	-	-	-
Tent 2026.02	55.97	85.52	91.79	-	-	-	-
READ 2026.02	55.97	85.22	91.79	-	-	-	-
SAR 2026.02	55.97	85.52	91.79	-	-	-	-
EATA 2026.02	55.97	85.22	91.79	-	-	-	-
VidLA 2024.03	55.9	82.3	88.3	-	-	-	-
SigLIP2-g-opt 2025.12	55.8	-	-	-	-	-	-
SigLIP-2-g-opt 2026.05	55.8	-	-	-	-	-	-
LanguageBind 2025.12	55.6	-	-	-	-	-	-
VLAB_L 2023.05	55.4	82.5	89.2	-	-	227.1	-
TCR 2026.02	55.37	85.67	91.34	-	-	-	-
HAT-VTR 2026.02	54.78	84.33	90.45	-	-	-	-
CLIP4Clip 2026.02	54.63	80.9	90.9	-	-	-	-
READ 2026.02	54.63	80.9	90.9	-	-	-	-
EATA 2026.02	54.63	81.19	90.45	-	-	-	-
U-MARVEL 2025.07	54.6	80.9	87.7	-	-	-	-
Tent 2026.02	54.48	80.9	90.9	-	-	-	-
SAR 2026.02	54.48	80.9	90.9	-	-	-	-
FluxViT-B 2025.03	54.2	-	-	-	-	-	-
TCR 2026.02	54.18	80.9	90.45	-	-	-	-
LanguageBind-L 2025.03	54.1	-	-	-	-	-	-
LanguageBind-H 2025.03	53.9	-	-	-	-	-	-
LanguageBind 2026.02	53.9	-	-	-	-	-	-
LanguageBind (CLIP-H/14) 2026.05	53.9	-	-	-	-	-	-
FluxViT-B 2025.03	53.8	-	-	-	-	-	-
UMT-L 2023.03	53.7	80.5	86.8	-	-	-	-
SigLIP2-L/16 2025.12	53.7	-	-	-	-	-	-
SigLIP-2-L/16 2026.05	53.7	-	-	-	-	-	-
FluxViT-B 2025.03	53.4	-	-	-	-	-	-
NarVid 2025.03	53.1	81.4	88.8	-	-	-	-
U-MARVEL+ 2025.07	53.1	79.9	87.1	-	-	-	-
LLaVE-7B 2025.07	52.9	80.1	87	-	-	-	-
LLaVE-7B 2025.03	52.9	80.1	87	-	-	-	-
FluxViT-B 2025.03	52.8	-	-	-	-	-	-
HunYuan_tvr 2022.06	52.7	-	-	-	-	-	-
VidLA 2024.03	52.7	80.4	87	-	-	-	-
OmniVL 2023.05	52.4	79.5	85.4	-	-	217.3	-
LamRA 2024.12	52.4	79.8	87	-	-	-	-
LamRA 2025.07	52.4	79.8	87	-	-	-	-
LamRA 2025.03	52.4	79.8	87	-	-	-	-
Uni-Perceiver-L + Conditional MoEs 2022.06	52.3	-	-	-	-	-	-
FluxViT-B 2025.03	52.1	-	-	-	-	-	-
BridgeFormer 2024.03	52	82.8	90	-	-	-	-
Cap4Video 2024.03	51.8	80.8	88.3	-	-	-	-
Cap4Video 2025.03	51.8	80.8	88.3	-	-	-	-
VidLA 2024.03	51.5	79.9	86.9	-	-	-	-
EagleNet 2026.03	50.9	80.7	88.3	-	-	-	-
Uni-Perceiver-L 2022.06	50.8	-	-	-	-	-	-
UMT-B 2023.03	50.8	79.7	86.2	-	-	-	-
UMT-B 2024.03	50.8	-	-	-	-	-	-
FluxViT-B 2025.03	50.7	-	-	-	-	-	-
UMT-B + vid-TLDR 2024.03	50.5	-	-	-	-	-	-
X-CLIP 2022.07	50.4	80.6	-	-	8.4	-	-
X-CLIP 2023.05	50.4	80.6	-	-	-	-	-
X-CLIP 2026.05	50.4	-	-	-	-	-	-
PE-coreB 2026.05	50.4	-	-	-	-	-	-
Uni-Perceiver-L + Conditional MoEs 2022.06	50.3	-	-	-	-	-	-
LAVENDER 2023.05	50.1	79.6	87.2	-	-	216.9	-
LAVENDER 2023.03	50.1	79.6	87.2	-	-	-	-
LAVENDER 2024.03	50.1	-	-	-	-	-	-
DCR 2023.05	50	81.5	89.5	-	-	221	-
DRL 2024.03	50	81.5	89.5	-	-	-	-

Showing 100 of 296 rows