Moment Retrieval on QVHighlights

Metric: mAP@0.5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	mAP@0.5▼	Extra Data	Paper	Date↕	Code
1	SG-DETR (w/ PT)	76.2	Yes	Saliency-Guided DETR for Moment Retrieval and Hi...	2024-10-02	Code
2	SG-DETR	73.2	No	Saliency-Guided DETR for Moment Retrieval and Hi...	2024-10-02	Code
3	FlashVTG	72.33	No	FlashVTG: Feature Layering and Adaptive Score Ha...	2024-12-18	Code
4	VideoLights-B-pt	69.53	Yes	VideoLights: Feature Refinement and Cross-Task A...	2024-12-02	Code
5	LLaVA-MR	69.41	No	LLaVA-MR: Large Language-and-Vision Assistant fo...	2024-11-21	Code
6	CG-DETR (w/ PT)	69.4	Yes	Correlation-Guided Query-Dependency Calibration ...	2023-11-15	Code
7	R^2-Tuning	69.04	No	$R^2$-Tuning: Efficient Image-to-Video Transfer ...	2024-03-31	Code
8	LD-DETR	67.61	No	LD-DETR: Loop Decoder DEtection TRansformer for ...	2025-01-18	Code
9	SG-DETR (ZS)	67.5	Yes	Saliency-Guided DETR for Moment Retrieval and Hi...	2024-10-02	Code
10	BAM-DETR (w/ PT ASR Captions)	66.33	Yes	BAM-DETR: Boundary-Aligned Moment Detection Tran...	2023-11-30	Code
11	LLMEPET	65.76	No	Prior Knowledge Integration via LLM Encoding and...	2024-07-21	Code
12	LA-DETR	65.65	No	Length-Aware DETR for Robust Moment Retrieval	2024-12-30	Code
13	BAM-DETR (w/ audio)	65.61	No	BAM-DETR: Boundary-Aligned Moment Detection Tran...	2023-11-30	Code
14	UVCOM (w/ PT ASR Captions)	64.78	Yes	Bridging the Gap: A Unified Video Comprehension ...	2023-11-28	Code
15	BAM-DETR	64.57	No	BAM-DETR: Boundary-Aligned Moment Detection Tran...	2023-11-30	Code
16	CG-DETR	64.51	No	Correlation-Guided Query-Dependency Calibration ...	2023-11-15	Code
17	video-mamba-suite	64.37	No	Video Mamba Suite: State Space Model as a Versat...	2024-03-14	Code
18	QD-DETR (w/ PT)	64.3	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
19	UniVTG (w/ PT)	64.06	Yes	UniVTG: Towards Unified Video-Language Temporal ...	2023-07-31	Code
20	QD-DETR (only Video w/ PT ASR Captions)	63.4	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
21	UVCOM	63.37	No	Bridging the Gap: A Unified Video Comprehension ...	2023-11-28	Code
22	BM-DETR	63.08	No	Background-aware Moment Detection for Video Mome...	2023-06-05	Code
23	QD-DETR (w/ audio)	63.04	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
24	QD-DETR (only Video)	62.52	No	Query-Dependent Video Representation for Moment ...	2023-03-24	Code
25	Moment-DETR (w/ PT ASR Cpations)	60.51	No	QVHighlights: Detecting Moments and Highlights i...	2021-07-20	Code
26	UniVTG	57.6	No	UniVTG: Towards Unified Video-Language Temporal ...	2023-07-31	Code
27	VTG-GPT	54.17	No	VTG-GPT: Tuning-Free Zero-Shot Video Temporal Gr...	2024-03-04	Code

#1SG-DETR (w/ PT)SOTA
76.2
mAP@0.5· Extra Data· 2024-10-02
Saliency-Guided DETR for Moment Retrieval and Highlight Detection Code
#2SG-DETR
73.2
mAP@0.5· 2024-10-02
Saliency-Guided DETR for Moment Retrieval and Highlight Detection Code
#3FlashVTG
72.33
mAP@0.5· 2024-12-18
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding Code
#4VideoLights-B-pt
69.53
mAP@0.5· Extra Data· 2024-12-02
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval Code
#5LLaVA-MR
69.41
mAP@0.5· 2024-11-21
LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval Code
#6CG-DETR (w/ PT)SOTA
69.4
mAP@0.5· Extra Data· 2023-11-15
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding Code
#7R^2-Tuning
69.04
mAP@0.5· 2024-03-31
$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding Code
#8LD-DETR
67.61
mAP@0.5· 2025-01-18
LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection Code
#9SG-DETR (ZS)
67.5
mAP@0.5· Extra Data· 2024-10-02
Saliency-Guided DETR for Moment Retrieval and Highlight Detection Code
#10BAM-DETR (w/ PT ASR Captions)
66.33
mAP@0.5· Extra Data· 2023-11-30
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos Code
#11LLMEPET
65.76
mAP@0.5· 2024-07-21
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval Code
#12LA-DETR
65.65
mAP@0.5· 2024-12-30
Length-Aware DETR for Robust Moment Retrieval Code
#13BAM-DETR (w/ audio)
65.61
mAP@0.5· 2023-11-30
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos Code
#14UVCOM (w/ PT ASR Captions)
64.78
mAP@0.5· Extra Data· 2023-11-28
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection Code
#15BAM-DETR
64.57
mAP@0.5· 2023-11-30
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos Code
#16CG-DETR
64.51
mAP@0.5· 2023-11-15
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding Code
#17video-mamba-suite
64.37
mAP@0.5· 2024-03-14
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding Code
#18QD-DETR (w/ PT)SOTA
64.3
mAP@0.5· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#19UniVTG (w/ PT)
64.06
mAP@0.5· Extra Data· 2023-07-31
UniVTG: Towards Unified Video-Language Temporal Grounding Code
#20QD-DETR (only Video w/ PT ASR Captions)
63.4
mAP@0.5· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#21UVCOM
63.37
mAP@0.5· 2023-11-28
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection Code
#22BM-DETR
63.08
mAP@0.5· 2023-06-05
Background-aware Moment Detection for Video Moment Retrieval Code
#23QD-DETR (w/ audio)
63.04
mAP@0.5· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#24QD-DETR (only Video)
62.52
mAP@0.5· 2023-03-24
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection Code
#25Moment-DETR (w/ PT ASR Cpations)SOTA
60.51
mAP@0.5· 2021-07-20
QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries Code
#26UniVTG
57.6
mAP@0.5· 2023-07-31
UniVTG: Towards Unified Video-Language Temporal Grounding Code
#27VTG-GPT
54.17
mAP@0.5· 2024-03-04
VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT Code