Natural Language Moment Retrieval on TACoS

13개 결과 · ⬇ CSV · JSON

R@1,IoU=0.3

Rank	Model	R@1,IoU=0.3	R@1,IoU=0.5	R@1,IoU=0.7	R@5,IoU=0.1	R@5,IoU=0.3	R@5,IoU=0.5	mIoU	Extra Training Data	Paper	Code	Year
1	SG-DETR (w/ PT)	58.10	46.40	33.90	–	–	–	42.40	✓	Saliency-Guided DETR for Moment Retrieval and Highlight Detection	ai-forever/sg-detr	2024
2	LD-DETR	57.61	44.31	26.24	–	–	–	40.30		LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection	qingchen239/ld-detr	2025
3	DeCafNet	57.36	46.79	–	81.05	71.13	–	–		DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos	zijialewislu/cvpr2025-decafnet	2025
4	SG-DETR	56.71	44.70	29.90	–	–	–	40.90		Saliency-Guided DETR for Moment Retrieval and Highlight Detection	ai-forever/sg-detr	2024
5	BAM-DETR	56.69	41.54	26.77	–	–	–	39.31		BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos	Pilhyeon/BAM-DETR	2023
6	FlashVTG	53.71	41.76	24.74	–	–	–	37.61		FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding	zhuo-cao/flashvtg	2024
7	LLMEPET	52.73	40.12	22.78	–	–	–	36.55		Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval	fletcherjiang/llmepet	2024
8	CG-DETR	52.23	39.61	22.23	–	–	–	36.48		Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding	wjun0830/qd-detr · wjun0830/cgdetr	2023
9	UniVTG	51.44	34.97	21.07	–	–	–	35.76		UniVTG: Towards Unified Video-Language Temporal Grounding	showlab/univtg	2023
10	GVL (paragraph-level)	48.29	36.07	–	–	–	–	–		Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos	zjr2000/gvl	2023
11	GVL	45.92	34.57	–	–	–	–	–		Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos	zjr2000/gvl	2023
12	VLG-Net	45.46	34.19	–	81.80	70.38	56.56	–		VLG-Net: Video-Language Graph Matching Network for Video Grounding	Soldelli/VLG-Net	2020
13	UVCOM	–	36.39	23.32	–	–	–	–		Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection	easonxiao-888/uvcom	2023