Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Highlight Detection On Qvhighlights

Metriken

Hit@1

mAP

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Hit@1	mAP	Paper Title	Repository
SG-DETR	69.13	43.76	Saliency-Guided DETR for Moment Retrieval and Highlight Detection	-
SG-DETR (w/ PT)	71.00	44.70	Saliency-Guided DETR for Moment Retrieval and Highlight Detection	-
VideoLights-B-pt	70.56	42.84	VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval	-
HL-CLIP	70.60	41.94	Unleash the Potential of CLIP for Video Highlight Detection	-
UniVTG (w/ PT)	66.28	40.54	UniVTG: Towards Unified Video-Language Temporal Grounding	-
LLMEPET	65.69	40.33	Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval	-
Moment-DETR w/ PT	60.17	37.43	QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries	-
QD-DETR (only Video w/ PT)	61.91	-	Query-Dependent Video Representation for Moment Retrieval and Highlight Detection	-
CG-DETR (w/ PT)	66.60	40.71	Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding	-
QD-DETR	62.87	39.04	Query-Dependent Video Representation for Moment Retrieval and Highlight Detection	-
QD-DETR (w/ PT)	62.27	38.52	Query-Dependent Video Representation for Moment Retrieval and Highlight Detection	-
NumPro	70.71	40.54	Number it: Temporal Grounding Videos like Flipping Manga	-
QD-DETR (only Video)	62.40	38.94	Query-Dependent Video Representation for Moment Retrieval and Highlight Detection	-
UMT (w. PT)	-	39.12	UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection	-
UMT	-	38.18	UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection	-
R^2-Tuning	64.20	40.75	$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding	-
CG-DETR	66.21	40.33	Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding	-
FlashVTG	71.01	44.09	FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding	-
UniVTG	60.96	38.20	UniVTG: Towards Unified Video-Language Temporal Grounding	-

0 of 19 row(s) selected.

Highlight Detection On Qvhighlights | SOTA | HyperAI