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

Video-to-Text Retrieval on ActivityNet

58.2R@1

VideoMatch

Updated 23d ago

Evaluation Results

Method
VideoMatch 2021.10	58.2	88.1	1	-	-	-	-
HSE 2021.10	44.2	76.7	2	-	-	-	-
Dense full 2021.10	18	36	32	-	-	-	-
FSE 2021.10	16.7	43.1	7.3	-	-	-	-
No Context 2021.10	7	18	56	-	-	-	-
InternVideo2s2-6B 2024.03	0.697	-	-	-	-	-	-
MAVIS 2026.06	0.6915	0.924	-	-	-	0.968	-
MERLIN (Round 5) 2026.06	0.6844	0.9195	-	-	-	0.9663	-
GRAM Model 2024.12	0.669	-	-	-	-	95.4	-
GRAM Model 2024.12	0.669	-	-	-	-	-	-
VAST 2024.12	0.667	-	-	-	-	95.3	-
VAST 2024.12	0.667	-	-	-	-	-	-
PMRL 2025.07	0.664	-	-	-	-	-	-
MERLIN (Round 3) 2026.06	0.6605	0.9097	-	-	-	0.9554	-
VAST 2025.07	0.654	-	-	-	-	-	-
GRAM 2025.07	0.65	-	-	-	-	-	-
UMT-L 2024.12	0.646	-	-	-	-	-	-
GRAM Model 2024.12	0.646	-	-	-	-	95.1	-
GRAM Model 2024.12	0.646	-	-	-	-	-	-
UMT-L 2024.03	0.644	-	-	-	-	-	-
UMT-L 2024.12	0.644	-	-	-	-	-	-
UMT-L 2025.07	0.644	-	-	-	-	-	-
InternVideo2-6B 2026.06	0.632	0.856	-	-	-	0.925	-
InternVideo 2022.12	0.628	-	-	-	-	-	-
InternVideo-L 2024.12	0.628	-	-	-	-	-	-
InternVideo-L 2025.07	0.628	-	-	-	-	-	-
MERLIN (Round 0) 2026.06	0.5658	0.8477	-	-	-	0.9173	-
Marengo-2.6 2026.06	0.5536	0.8255	-	-	-	-	-
VAST 2026.06	0.552	0.825	-	-	-	0.906	-
MoVA 2026.07	0.544	0.799	1	5.7	-	0.886	-
VideoPrism-g 2026.06	0.527	0.794	-	-	-	-	-
UniAlign* 2026.02	0.525	-	-	-	-	-	-
MAMA 2026.01	0.523	0.808	-	-	-	0.901	-
UniAlign 2026.02	0.517	-	-	-	-	-	-
GRAM 2024.12	0.509	-	-	-	-	-	-
GRAM Model 2024.12	0.509	-	-	-	-	0.854	-
Vid2Seq 2026.01	0.509	0.795	-	-	-	0.896	-
EMCL-Net 2022.11	0.506	0.789	1	-	0.984	-	-
GRAM 2024.12	0.504	-	-	-	-	-	-
GRAM Model 2024.12	0.504	-	-	-	-	0.858	-
GRAM 2026.02	0.504	-	-	-	-	-	-
LaViLa 2026.01	0.503	0.787	-	-	-	0.884	-
CLIP-ViP 2026.01	0.502	0.783	-	-	-	0.875	-
CAMoE 2021.09	0.499	0.774	-	-	-	-	-
PMRL 2025.07	0.496	-	-	-	-	-	-
Cap4Video 2026.06	0.492	0.773	-	-	-	0.851	-
VAST 2025.07	0.488	-	-	-	-	-	-
T-MASS 2026.06	0.485	0.764	-	-	-	0.842	-
GRAM 2025.07	0.483	-	-	-	-	-	-
ViCLIP 2024.03	0.481	-	-	-	-	-	-
ViCLIP 2024.12	0.481	-	-	-	-	-	-
ViCLIP 2024.12	0.481	-	-	-	-	-	-
ViCLIP 2025.07	0.481	-	-	-	-	-	-
VideoPrism-b 2024.12	0.479	-	-	-	-	-	-
VideoPrism-b 2024.12	0.479	-	-	-	-	-	-
VideoPrism-b 2026.02	0.479	-	-	-	-	-	-
VideoPrism-b 2025.07	0.479	-	-	-	-	-	-
VindLU 2026.01	0.471	0.775	-	-	-	0.866	-
VAST 2024.12	0.468	-	-	-	-	-	-
VAST 2024.12	0.468	-	-	-	-	0.774	-
VAST 2026.02	0.468	-	-	-	-	-	-
MoVA 2026.07	0.467	0.766	2	6.3	-	0.868	-
X-CLIP 2022.12	0.464	-	-	-	-	-	-
X-CLIP 2026.06	0.464	0.759	-	-	-	0.845	-
ProST 2026.07	0.437	0.739	2	7	-	0.847	-
DGL 2026.07	0.434	0.736	2	7.9	-	0.851	-
CLIP4Clip 2026.07	0.429	0.753	2	6.4	-	0.866	-
EMCL-Net 2022.11	0.427	0.74	2	-	0.983	-	-
DRL 2026.07	0.427	0.738	2	7.7	-	0.845	-
CLIP4Clip 2026.01	0.426	0.734	-	-	-	0.856	-
CLIP4Clip 2022.11	0.425	0.741	2	-	0.981	-	-
DRL 2026.01	0.422	0.74	-	-	-	0.862	-
TeachCLIP 2026.06	0.422	0.727	-	-	-	0.84	-
X-CLIP 2026.07	0.422	0.746	2	6.9	-	0.855	-
CLIP4Clip 2022.12	0.416	-	-	-	-	-	-
CLIP4Clip 2024.03	0.416	-	-	-	-	-	-
CLIP4Clip 2024.12	0.416	-	-	-	-	-	-
CLIP4Clip 2024.12	0.416	-	-	-	-	-	-
CLIP4Clip 2025.07	0.416	-	-	-	-	-	-
InternVideo 2026.07	0.416	0.738	2	7.1	-	0.85	-
LanguageBind 2023.10	0.41	0.684	-	-	-	0.8	-
LanguageBind-H 2026.06	0.41	0.684	-	-	-	0.808	-
DiCoSA 2026.07	0.406	0.718	2	7.7	-	0.838	-
CLIP4Clip 2026.06	0.405	0.724	-	-	-	0.801	-
UMT-L 2024.12	0.394	-	-	-	-	-	-
UMT-L 2024.12	0.394	-	-	-	-	-	-
UMT-L 2026.02	0.394	-	-	-	-	-	-
UMT-L 2025.07	0.394	-	-	-	-	-	-
LanguageBind 2024.12	0.391	-	-	-	-	-	-
LanguageBind 2024.12	0.391	-	-	-	-	0.811	-
LanguageBind 2026.02	0.391	-	-	-	-	-	-
LanguageBind 2025.07	0.391	-	-	-	-	-	-
Full 2022.11	0.389	0.701	2	8.4	-	0.819	-
LanguageBind 2023.10	0.384	0.666	-	-	-	0.779	-
VideoCLIP-XL 2026.07	0.377	0.682	2	10.1	-	0.811	-
LanguageBind 2023.10	0.369	0.651	-	-	-	0.772	-
VoPF+P 2022.11	0.363	0.659	3	10.1	-	0.792	-
VoPF+C 2022.11	0.356	0.659	3	10.4	-	0.778	-
VoPF 2022.11	0.355	0.651	3	10.2	-	0.774	-
LanguageBind 2023.10	0.351	0.634	-	-	-	0.766	-

Showing 100 of 194 rows