Phrase Grounding on Flickr30k Entities Test

Metric: R@1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	R@1▼	Extra Data	Paper	Date↕	Code
1	GLIPv2	87.7	Yes	GLIPv2: Unifying Localization and Vision-Languag...	2022-06-12	Code
2	FIBER-B	87.4	Yes	Coarse-to-Fine Vision-Language Pre-training with...	2022-06-15	Code
3	GLIP	87.1	Yes	Grounded Language-Image Pre-training	2021-12-07	Code
4	PEVL	84.4	Yes	PEVL: Position-enhanced Pre-training and Prompt ...	2022-05-23	Code
5	MDETR-ENB5	84.3	Yes	MDETR -- Modulated Detection for End-to-End Mult...	2021-04-26	Code
6	DIGN	78.73	No	Disentangled Motif-aware Graph Learning for Phra...	2021-04-13	-
7	LCMCG	76.74	No	Learning Cross-modal Context Graph for Visual Gr...	2019-11-20	Code
8	Soft-Label Chain CRF (SL-CCRF)	74.69	No	Phrase Grounding by Soft-Label Chain Conditional...	2019-09-01	Code
9	DDPN (ResNet-101)	73.3	No	Rethinking Diversified and Discriminative Propos...	2018-05-09	Code
10	VisualBERT	71.33	No	VisualBERT: A Simple and Performant Baseline for...	2019-08-09	Code
11	BAN (Bottom-Up detector)	69.69	No	Bilinear Attention Networks	2018-05-21	Code
12	MCB	48.69	No	Multimodal Compact Bilinear Pooling for Visual Q...	2016-06-06	Code
13	GroundeR 100.0% annot.	48.38	No	Grounding of Textual Phrases in Images by Recons...	2015-11-12	Code
14	DSPE	43.89	No	Learning Deep Structure-Preserving Image-Text Em...	2015-11-19	-
15	CCA - Fast RCNN	41.77	No	Flickr30k Entities: Collecting Region-to-Phrase ...	2015-05-19	Code
16	CCA - VGG19	30.83	No	Flickr30k Entities: Collecting Region-to-Phrase ...	2015-05-19	Code
17	SCRC	27.8	No	Natural Language Object Retrieval	2015-11-13	Code
18	CCA	25.3	No	Flickr30k Entities: Collecting Region-to-Phrase ...	2015-05-19	Code

#1GLIPv2SOTA
87.7
R@1· Extra Data· 2022-06-12
GLIPv2: Unifying Localization and Vision-Language Understanding Code
#2FIBER-B
87.4
R@1· Extra Data· 2022-06-15
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone Code
#3GLIPSOTA
87.1
R@1· Extra Data· 2021-12-07
Grounded Language-Image Pre-training Code
#4PEVL
84.4
R@1· Extra Data· 2022-05-23
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models Code
#5MDETR-ENB5SOTA
84.3
R@1· Extra Data· 2021-04-26
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding Code
#6DIGNSOTA
78.73
R@1· 2021-04-13
Disentangled Motif-aware Graph Learning for Phrase Grounding
#7LCMCGSOTA
76.74
R@1· 2019-11-20
Learning Cross-modal Context Graph for Visual Grounding Code
#8Soft-Label Chain CRF (SL-CCRF)SOTA
74.69
R@1· 2019-09-01
Phrase Grounding by Soft-Label Chain Conditional Random Field Code
#9DDPN (ResNet-101)SOTA
73.3
R@1· 2018-05-09
Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding Code
#10VisualBERT
71.33
R@1· 2019-08-09
VisualBERT: A Simple and Performant Baseline for Vision and Language Code
#11BAN (Bottom-Up detector)
69.69
R@1· 2018-05-21
Bilinear Attention Networks Code
#12MCBSOTA
48.69
R@1· 2016-06-06
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding Code
#13GroundeR 100.0% annot.SOTA
48.38
R@1· 2015-11-12
Grounding of Textual Phrases in Images by Reconstruction Code
#14DSPE
43.89
R@1· 2015-11-19
Learning Deep Structure-Preserving Image-Text Embeddings
#15CCA - Fast RCNNSOTA
41.77
R@1· 2015-05-19
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models Code
#16CCA - VGG19
30.83
R@1· 2015-05-19
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models Code
#17SCRC
27.8
R@1· 2015-11-13
Natural Language Object Retrieval Code
#18CCA
25.3
R@1· 2015-05-19
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models Code