Our new X account is live! Follow @wizwand_team for updates

Video-to-text retrieval on ActivityNet Captions

72.9R@1

VidLA-B/16

Updated 2d ago

Evaluation Results

Method	Links
VidLA-B/16 2024.03		72.9	90.6	94.9	-	-	-	86.1
VidLA-B/32 2024.03		69.1	88.8	93.7	-	-	-	83.9
PEAV-L 2025.12		67.7	-	-	-	-	-	-
PEAV-L 2025.12		66.5	-	-	-	-	-	-
PEAV-B 2025.12		65.9	-	-	-	-	-	-
PEAV-S 2025.12		65.5	-	-	-	-	-	-
PEAV-B 2025.12		64.9	-	-	-	-	-	-
PEAV-S 2025.12		64.8	-	-	-	-	-	-
VidLA-B/16 2024.03		63.4	87.5	93.2	-	-	-	81.4
InternVideo 2024.03		62.8	-	-	-	-	-	-
VidLA-B/32 2024.03		60.8	85	91.8	-	-	-	79.2
UMT 2024.03		56	83.5	91.7	-	-	-	77.1
InternVideo2 2025.12		54.8	-	-	-	-	-	-
PE-G 2025.12		51.2	-	-	-	-	-	-
CAMOE 2024.03		49.9	77.4	-	-	-	-	-
LanguageBind 2025.12		48.8	-	-	-	-	-	-
DiffusionRet 2023.03		47.4	76.3	86.7	210.4	2	6.7	-
DiffusionRet 2024.03		47.4	76.3	86.7	-	-	-	70.1
CenterCLIP 2024.03		46.7	77.1	88	-	-	-	70.6
DRL 2024.03		45.7	76.5	87.8	-	-	-	70
CenterCLIP 2024.03		44.5	75.7	86.2	-	-	-	68.8
DiffusionRet 2023.03		43.8	75.3	86.7	205.8	2	6.3	-
EMCL-Net 2023.03		42.7	74	-	-	2	-	-
CLIP4Clip 2024.03		42.5	74.1	85.8	-	-	-	67.5
HBI 2023.03		42.4	73	86	201.4	2	6.5	-
DRL 2024.03		42.2	74	86.2	-	-	-	67.5
PE-L 2025.12		42.1	-	-	-	-	-	-
CLIP4Clip 2023.03		41.4	73.7	85.3	200.4	2	6.7	-
UMT-L 2025.12		39.4	-	-	-	-	-	-
ImageBind 2025.12		34.1	-	-	-	-	-	-
SigLIP2-g-opt 2025.12		33.4	-	-	-	-	-	-
VideoCoCa 2022.12		33	61.6	75.3	-	-	-	-
VideoCoCa 2022.12		33	61.6	75.3	-	-	-	-
SigLIP2-L/16 2025.12		31.5	-	-	-	-	-	-
InternVideo 2022.12		31.4	-	-	-	-	-	-
InternVideo 2022.12		31.4	-	-	-	-	-	-
VideoCoCa 2022.12		26.8	54.7	70	-	-	-	-
VideoCoCa (w.o. videos) 2022.12		26.8	54.7	70	-	-	-	-
TT-CE 2023.03		23	56.1	-	-	4	-	-
CoCa 2022.12		21.9	49.5	64.1	-	-	-	-
CoCa 2022.12		21.9	49.5	64.1	-	-	-	-