Cross-Modal Information Retrieval on COCO 2014

Metric: Text-to-image R@10 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Text-to-image R@10▼	Extra Data	Paper	Date↕	Code
1	VAST	92.8	Yes	VAST: A Vision-Audio-Subtitle-Text Omni-Modality...	2023-05-29	Code
2	VK-OOD	92.8	Yes	-	-	Code
3	X2-VLM (large)	92.5	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
4	XFM (base)	92.4	Yes	Toward Building General Foundation Models for La...	2023-01-12	Code
5	X2-VLM (base)	92.2	Yes	X$^2$-VLM: All-In-One Pre-trained Model For Visi...	2022-11-22	Code
6	PTP-BLIP (14M)	92.2	Yes	Position-guided Text Prompt for Vision-Language ...	2022-12-19	Code
7	DSMD	92	No	Dynamic Self-adaptive Multiscale Distillation fr...	2024-04-16	Code
8	OmniVL (14M)	91.6	Yes	OmniVL:One Foundation Model for Image-Language a...	2022-09-15	-
9	VSE-Gradient	91.5	Yes	Dissecting Deep Metric Learning Losses for Image...	2022-10-21	Code
10	X-VLM (base)	91.5	Yes	Multi-Grained Vision Language Pre-Training: Alig...	2021-11-16	Code
11	Aurora (ours, r=128)	91	Yes	-	-	-
12	VALOR	90.9	Yes	VALOR: Vision-Audio-Language Omni-Perception Pre...	2023-04-17	Code
13	ALBEF	90.5	Yes	Align before Fuse: Vision and Language Represent...	2021-07-16	Code
14	ERNIE-ViL 2.0	90.1	Yes	ERNIE-ViL 2.0: Multi-view Contrastive Learning f...	2022-09-30	Code
15	METER	90.07	Yes	An Empirical Study of Training End-to-End Vision...	2021-11-03	Code
16	TCL	89.9	Yes	Vision-Language Pre-Training with Triple Contras...	2022-02-21	Code
17	ALIGN	89.8	Yes	Scaling Up Visual and Vision-Language Representa...	2021-02-11	Code
18	Oscar	89.8	Yes	Oscar: Object-Semantics Aligned Pre-training for...	2020-04-13	Code
19	BEiT-3	87.7	Yes	Image as a Foreign Language: BEiT Pretraining fo...	2022-08-22	Code
20	3SHNet	87.7	No	3SHNet: Boosting Image-Sentence Retrieval via Vi...	2024-04-26	Code
21	ViSTA	87.6	Yes	ViSTA: Vision and Scene Text Aggregation for Cro...	2022-03-31	-
22	ALADIN	87.5	Yes	ALADIN: Distilling Fine-grained Alignment Scores...	2022-07-29	Code
23	RCAR	83.2	No	Plug-and-Play Regulators for Image-Text Matching	2023-03-23	Code
24	ViLT-B/32	83.1	Yes	ViLT: Vision-and-Language Transformer Without Co...	2021-02-05	Code
25	VisualSparta	82.4	Yes	VisualSparta: An Embarrassingly Simple Approach ...	2021-01-01	Code
26	LILE	82.2	No	LILE: Look In-Depth before Looking Elsewhere -- ...	2022-03-02	-
27	SGRAF	81.3	No	Similarity Reasoning and Filtration for Image-Te...	2021-01-05	Code
28	VSRN	81.1	No	Visual Semantic Reasoning for Image-Text Matching	2019-09-06	Code
29	SCAN	80.4	No	Stacked Cross Attention for Image-Text Matching	2018-03-21	Code
30	IMRAM	79.8	No	IMRAM: Iterative Matching with Recurrent Attenti...	2020-03-08	Code
31	SCO (ResNet)	75.5	No	Learning Semantic Concepts and Order for Image a...	2017-12-06	-
32	PVSE	75	No	Polysemous Visual-Semantic Embedding for Cross-M...	2019-06-11	Code
33	Dual-Path (ResNet)	66.4	No	Deep Visual-Semantic Alignments for Generating I...	2014-12-07	Code

#1VASTSOTA
92.8
Text-to-image R@10· Extra Data· 2023-05-29
VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset Code
#2VK-OOD
92.8
Text-to-image R@10· Extra Data
No paperCode
#3X2-VLM (large)SOTA
92.5
Text-to-image R@10· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#4XFM (base)
92.4
Text-to-image R@10· Extra Data· 2023-01-12
Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks Code
#5X2-VLM (base)
92.2
Text-to-image R@10· Extra Data· 2022-11-22
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks Code
#6PTP-BLIP (14M)
92.2
Text-to-image R@10· Extra Data· 2022-12-19
Position-guided Text Prompt for Vision-Language Pre-training Code
#7DSMD
92
Text-to-image R@10· 2024-04-16
Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning Code
#8OmniVL (14M)SOTA
91.6
Text-to-image R@10· Extra Data· 2022-09-15
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
#9VSE-Gradient
91.5
Text-to-image R@10· Extra Data· 2022-10-21
Dissecting Deep Metric Learning Losses for Image-Text Retrieval Code
#10X-VLM (base)SOTA
91.5
Text-to-image R@10· Extra Data· 2021-11-16
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts Code
#11Aurora (ours, r=128)
91
Text-to-image R@10· Extra Data
No paper
#12VALOR
90.9
Text-to-image R@10· Extra Data· 2023-04-17
VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset Code
#13ALBEFSOTA
90.5
Text-to-image R@10· Extra Data· 2021-07-16
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation Code
#14ERNIE-ViL 2.0
90.1
Text-to-image R@10· Extra Data· 2022-09-30
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training Code
#15METER
90.07
Text-to-image R@10· Extra Data· 2021-11-03
An Empirical Study of Training End-to-End Vision-and-Language Transformers Code
#16TCL
89.9
Text-to-image R@10· Extra Data· 2022-02-21
Vision-Language Pre-Training with Triple Contrastive Learning Code
#17ALIGN
89.8
Text-to-image R@10· Extra Data· 2021-02-11
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Code
#18OscarSOTA
89.8
Text-to-image R@10· Extra Data· 2020-04-13
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks Code
#19BEiT-3
87.7
Text-to-image R@10· Extra Data· 2022-08-22
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks Code
#203SHNet
87.7
Text-to-image R@10· 2024-04-26
3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting Code
#21ViSTA
87.6
Text-to-image R@10· Extra Data· 2022-03-31
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
#22ALADIN
87.5
Text-to-image R@10· Extra Data· 2022-07-29
ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval Code
#23RCAR
83.2
Text-to-image R@10· 2023-03-23
Plug-and-Play Regulators for Image-Text Matching Code
#24ViLT-B/32
83.1
Text-to-image R@10· Extra Data· 2021-02-05
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision Code
#25VisualSparta
82.4
Text-to-image R@10· Extra Data· 2021-01-01
VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words Code
#26LILE
82.2
Text-to-image R@10· 2022-03-02
LILE: Look In-Depth before Looking Elsewhere -- A Dual Attention Network using Transformers for Cross-Modal Information Retrieval in Histopathology Archives
#27SGRAF
81.3
Text-to-image R@10· 2021-01-05
Similarity Reasoning and Filtration for Image-Text Matching Code
#28VSRNSOTA
81.1
Text-to-image R@10· 2019-09-06
Visual Semantic Reasoning for Image-Text Matching Code
#29SCANSOTA
80.4
Text-to-image R@10· 2018-03-21
Stacked Cross Attention for Image-Text Matching Code
#30IMRAM
79.8
Text-to-image R@10· 2020-03-08
IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval Code
#31SCO (ResNet)SOTA
75.5
Text-to-image R@10· 2017-12-06
Learning Semantic Concepts and Order for Image and Sentence Matching
#32PVSE
75
Text-to-image R@10· 2019-06-11
Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval Code
#33Dual-Path (ResNet)SOTA
66.4
Text-to-image R@10· 2014-12-07
Deep Visual-Semantic Alignments for Generating Image Descriptions Code