Natural Language Moment Retrieval on ActivityNet Captions

8개 결과 · ⬇ CSV · JSON

R@1,IoU=0.5

Rank	Model	R@1,IoU=0.5	R@1,IoU=0.7	R@5,IoU=0.5	R@5,IoU=0.7	Paper	Code	Year
1	GVL (paragraph-level)	60.67	38.55	–	–	Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos	zjr2000/gvl	2023
2	LLaVA-MR	55.16	35.68	–	–	LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval	swordlidev/LLaVA-MR	2024
3	GVL	49.18	29.69	–	–	Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos	zjr2000/gvl	2023
4	UnLoc-L	48.3	30.2	79.2	61.3	UnLoc: A Unified Framework for Video Localization Tasks	google-research/scenic	2023
5	UnLoc-B	48.0	29.7	81.5	61.4	UnLoc: A Unified Framework for Video Localization Tasks	google-research/scenic	2023
6	VLG-Net	46.32	29.82	77.15	63.33	VLG-Net: Video-Language Graph Matching Network for Video Grounding	Soldelli/VLG-Net	2020
7	DRN	45.45	24.36	77.97	50.30	Dense Regression Network for Video Grounding	alvin-zeng/drn	2020
8	UniMD+Sync.	–	–	80.54	57.04	UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection	yingsen1/unimd	2024