Moment Retrieval On Qvhighlights

Metriken

R@1 IoU=0.5

R@1 IoU=0.7

mAP

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	R@1 IoU=0.5	R@1 IoU=0.7	mAP	[email protected]	[email protected]	Paper Title	Repository
SG-DETR	72.20	56.60	54.10	73.20	55.80	Saliency-Guided DETR for Moment Retrieval and Highlight Detection	-
LLMEPET	66.73	49.94	44.05	65.76	43.91	Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval	-
DenoiseLoc	59.27	45.07	-	-	-	Boundary-Denoising for Video Activity Localization	-
BAM-DETR	62.71	48.64	45.36	64.57	46.33	BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos	-
UMT	-	-	36.12	-	-	UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection	-
VideoLights-B-pt	70.36	55.25	47.94	69.53	49.17	VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval	-
UniVTG (w/ PT)	65.43	50.06	43.63	64.06	45.02	UniVTG: Towards Unified Video-Language Temporal Grounding	-
UVCOM (w/ PT ASR Captions)	64.53	48.31	43.8	64.78	43.65	Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection	-
QD-DETR (only Video)	62.40	44.98	39.86	62.52	39.88	Query-Dependent Video Representation for Moment Retrieval and Highlight Detection	-
R^2-Tuning	68.03	49.35	46.17	69.04	47.56	$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding	-
FlashVTG	70.69	53.96	52.00	72.33	53.85	FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding	-
SeViLA-Localizer	54.5	36.5	32.3	-	-	-	-
QD-DETR (w/ audio)	63.06	45.10	40.19	63.04	40.10	Query-Dependent Video Representation for Moment Retrieval and Highlight Detection	-
BAM-DETR (w/ audio)	64.07	48.12	46.91	65.61	47.51	BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos	-
CG-DETR	65.43	48.38	42.86	64.51	42.77	Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding	-
UnLoc-L	66.1	46.7	-	-	-	UnLoc: A Unified Framework for Video Localization Tasks	-
LD-DETR	66.80	51.04	46.41	67.61	46.99	LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection	-
LA-DETR	63.94	51.10	47.93	65.65	49.44	Length-Aware DETR for Robust Moment Retrieval	-
LLaVA-MR	76.59	61.48	52.73	69.41	54.40	LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval	-
BM-DETR	60.12	43.05	40.08	63.08	40.18	Background-aware Moment Detection for Video Moment Retrieval	-

0 of 32 row(s) selected.