16k on QVHighlights

Metric: mAP (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	mAP▼	Augmentations	Paper	Date↕	Code
1	SG-DETR (w/ PT)	44.7	Yes	Saliency-Guided DETR for Moment Retrieval and Hi...	2024-10-02	Code
2	FlashVTG	44.09	No	FlashVTG: Feature Layering and Adaptive Score Ha...	2024-12-18	Code
3	SG-DETR	43.76	No	Saliency-Guided DETR for Moment Retrieval and Hi...	2024-10-02	Code
4	VideoLights-B-pt	42.84	Yes	VideoLights: Feature Refinement and Cross-Task A...	2024-12-02	Code
5	HL-CLIP	41.94	No	Unleash the Potential of CLIP for Video Highligh...	2024-04-02	Code
6	R^2-Tuning	40.75	No	$R^2$-Tuning: Efficient Image-to-Video Transfer ...	2024-03-31	Code
7	CG-DETR (w/ PT)	40.71	Yes	Correlation-Guided Query-Dependency Calibration ...	2023-11-15	Code
8	NumPro	40.54	No	Number it: Temporal Grounding Videos like Flippi...	2024-11-15	Code
9	UniVTG (w/ PT)	40.54	Yes	UniVTG: Towards Unified Video-Language Temporal ...	2023-07-31	Code
10	CG-DETR	40.33	No	Correlation-Guided Query-Dependency Calibration ...	2023-11-15	Code
11	LLMEPET	40.33	No	Prior Knowledge Integration via LLM Encoding and...	2024-07-21	Code
12	UMT (w. PT)	39.12	No	UMT: Unified Multi-modal Transformers for Joint ...	2022-03-23	Code
13	QD-DETR	39.04	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
14	QD-DETR (only Video)	38.94	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
15	QD-DETR (w/ PT)	38.52	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
16	UniVTG	38.2	No	UniVTG: Towards Unified Video-Language Temporal ...	2023-07-31	Code
17	UMT	38.18	No	UMT: Unified Multi-modal Transformers for Joint ...	2022-03-23	Code
18	Moment-DETR w/ PT	37.43	No	QVHighlights: Detecting Moments and Highlights i...	2021-07-20	Code
19	VideoChat-T (FT)	27	No	TimeSuite: Improving MLLMs for Long Video Unders...	2024-10-25	Code
20	VideoChat-T (ZS)	26.5	No	-	-	-

#1SG-DETR (w/ PT)SOTA
44.7
mAP· Augmentations· 2024-10-02
Saliency-Guided DETR for Moment Retrieval and Highlight Detection Code
#2FlashVTG
44.09
mAP· 2024-12-18
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding Code
#3SG-DETR
43.76
mAP· 2024-10-02
Saliency-Guided DETR for Moment Retrieval and Highlight Detection Code
#4VideoLights-B-pt
42.84
mAP· Augmentations· 2024-12-02
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval Code
#5HL-CLIPSOTA
41.94
mAP· 2024-04-02
Unleash the Potential of CLIP for Video Highlight Detection Code
#6R^2-TuningSOTA
40.75
mAP· 2024-03-31
$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding Code
#7CG-DETR (w/ PT)SOTA
40.71
mAP· Augmentations· 2023-11-15
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding Code
#8NumPro
40.54
mAP· 2024-11-15
Number it: Temporal Grounding Videos like Flipping Manga Code
#9UniVTG (w/ PT)SOTA
40.54
mAP· Augmentations· 2023-07-31
UniVTG: Towards Unified Video-Language Temporal Grounding Code
#10CG-DETR
40.33
mAP· 2023-11-15
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding Code
#11LLMEPET
40.33
mAP· 2024-07-21
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval Code
#12UMT (w. PT)SOTA
39.12
mAP· 2022-03-23
UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection Code
#13QD-DETR
39.04
mAP· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#14QD-DETR (only Video)
38.94
mAP· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#15QD-DETR (w/ PT)
38.52
mAP· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#16UniVTG
38.2
mAP· 2023-07-31
UniVTG: Towards Unified Video-Language Temporal Grounding Code
#17UMT
38.18
mAP· 2022-03-23
UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection Code
#18Moment-DETR w/ PTSOTA
37.43
mAP· 2021-07-20
QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries Code
#19VideoChat-T (FT)
27
mAP· 2024-10-25
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning Code
#20VideoChat-T (ZS)
26.5
mAP
No paper