Highlight Detection on QVHighlights

Metric: Hit@1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Hit@1▼	Extra Data	Paper	Date↕	Code
1	FlashVTG	71.01	No	FlashVTG: Feature Layering and Adaptive Score Ha...	2024-12-18	Code
2	SG-DETR (w/ PT)	71	Yes	Saliency-Guided DETR for Moment Retrieval and Hi...	2024-10-02	Code
3	NumPro	70.71	No	Number it: Temporal Grounding Videos like Flippi...	2024-11-15	Code
4	HL-CLIP	70.6	No	Unleash the Potential of CLIP for Video Highligh...	2024-04-02	Code
5	VideoLights-B-pt	70.56	Yes	VideoLights: Feature Refinement and Cross-Task A...	2024-12-02	Code
6	SG-DETR	69.13	No	Saliency-Guided DETR for Moment Retrieval and Hi...	2024-10-02	Code
7	CG-DETR (w/ PT)	66.6	Yes	Correlation-Guided Query-Dependency Calibration ...	2023-11-15	Code
8	UniVTG (w/ PT)	66.28	Yes	UniVTG: Towards Unified Video-Language Temporal ...	2023-07-31	Code
9	CG-DETR	66.21	No	Correlation-Guided Query-Dependency Calibration ...	2023-11-15	Code
10	LLMEPET	65.69	No	Prior Knowledge Integration via LLM Encoding and...	2024-07-21	Code
11	R^2-Tuning	64.2	No	$R^2$-Tuning: Efficient Image-to-Video Transfer ...	2024-03-31	Code
12	QD-DETR	62.87	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
13	QD-DETR (only Video)	62.4	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
14	QD-DETR (w/ PT)	62.27	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
15	QD-DETR (only Video w/ PT)	61.91	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
16	UniVTG	60.96	No	UniVTG: Towards Unified Video-Language Temporal ...	2023-07-31	Code
17	Moment-DETR w/ PT	60.17	No	QVHighlights: Detecting Moments and Highlights i...	2021-07-20	Code
18	VideoChat-T (FT)	55.3	No	TimeSuite: Improving MLLMs for Long Video Unders...	2024-10-25	Code
19	VideoChat-T (ZS)	54.1	No	-	-	-

#1FlashVTGSOTA
71.01
Hit@1· 2024-12-18
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding Code
#2SG-DETR (w/ PT)SOTA
71
Hit@1· Extra Data· 2024-10-02
Saliency-Guided DETR for Moment Retrieval and Highlight Detection Code
#3NumPro
70.71
Hit@1· 2024-11-15
Number it: Temporal Grounding Videos like Flipping Manga Code
#4HL-CLIPSOTA
70.6
Hit@1· 2024-04-02
Unleash the Potential of CLIP for Video Highlight Detection Code
#5VideoLights-B-pt
70.56
Hit@1· Extra Data· 2024-12-02
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval Code
#6SG-DETR
69.13
Hit@1· 2024-10-02
Saliency-Guided DETR for Moment Retrieval and Highlight Detection Code
#7CG-DETR (w/ PT)SOTA
66.6
Hit@1· Extra Data· 2023-11-15
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding Code
#8UniVTG (w/ PT)SOTA
66.28
Hit@1· Extra Data· 2023-07-31
UniVTG: Towards Unified Video-Language Temporal Grounding Code
#9CG-DETR
66.21
Hit@1· 2023-11-15
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding Code
#10LLMEPET
65.69
Hit@1· 2024-07-21
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval Code
#11R^2-Tuning
64.2
Hit@1· 2024-03-31
$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding Code
#12QD-DETRSOTA
62.87
Hit@1· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#13QD-DETR (only Video)
62.4
Hit@1· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#14QD-DETR (w/ PT)
62.27
Hit@1· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#15QD-DETR (only Video w/ PT)
61.91
Hit@1· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#16UniVTG
60.96
Hit@1· 2023-07-31
UniVTG: Towards Unified Video-Language Temporal Grounding Code
#17Moment-DETR w/ PTSOTA
60.17
Hit@1· 2021-07-20
QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries Code
#18VideoChat-T (FT)
55.3
Hit@1· 2024-10-25
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning Code
#19VideoChat-T (ZS)
54.1
Hit@1
No paper