Zero-Shot Video Retrieval on MSR-VTT

Metric: text-to-video R@10 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	text-to-video R@10▼	Extra Data	Paper	Date↕	Code
1	InternVideo2-6B	85.1	Yes	InternVideo2: Scaling Foundation Models for Mult...	2024-03-22	Code
2	GRAM	83.9	Yes	Gramian Multimodal Representation Learning and A...	2024-12-16	Code
3	InternVideo2-1B	82.5	Yes	InternVideo2: Scaling Foundation Models for Mult...	2024-03-22	Code
4	VAST, HowToCaption-finetuned	81.4	No	HowToCaption: Prompting LLMs to Transform Video ...	2023-10-07	Code
5	FluxViT-B	79.6	Yes	Make Your Training Flexible: Towards Deployment-...	2025-03-18	Code
6	mPLUG-2	79	No	mPLUG-2: A Modularized Multi-modal Foundation Mo...	2023-02-01	Code
7	LanguageBind(ViT-H/14)	78.7	Yes	LanguageBind: Extending Video-Language Pretraini...	2023-10-03	Code
8	LanguageBind(ViT-L/14)	76	Yes	LanguageBind: Extending Video-Language Pretraini...	2023-10-03	Code
9	FluxViT-S	75.8	Yes	Make Your Training Flexible: Towards Deployment-...	2025-03-18	Code
10	VAST	73.9	Yes	VAST: A Vision-Audio-Subtitle-Text Omni-Modality...	2023-05-29	Code
11	BT-Adapter	73.5	No	BT-Adapter: Video Conversation is Feasible Witho...	2023-09-27	Code
12	HowToCaption	73.3	No	HowToCaption: Prompting LLMs to Transform Video ...	2023-10-07	Code
13	UMT-L (ViT-L/16)	73.1	Yes	Unmasked Teacher: Towards Training-Efficient Vid...	2023-03-28	Code
14	Florence	72.6	No	Florence: A New Foundation Model for Computer Vi...	2021-11-22	Code
15	vid-TLDR (UMT-L)	72.4	Yes	vid-TLDR: Training Free Token merging for Light-...	2024-03-20	Code
16	ImageBind	70	No	ImageBind: One Embedding Space To Bind Them All	2023-05-09	Code
17	HiTeA-17M	69.9	No	HiTeA: Hierarchical Temporal-Aware Video-Languag...	2022-12-30	-
18	CLIP4Clip	66.9	No	CLIP4Clip: An Empirical Study of CLIP for End to...	2021-04-18	Code
19	Singularity-17M	66.7	Yes	Revealing Single Frame Bias for Video-and-Langua...	2022-06-07	Code
20	OmniVL	66.6	Yes	OmniVL:One Foundation Model for Image-Language a...	2022-09-15	-
21	Yatai Ji et. al.	65	No	Seeing What You Miss: Vision-Language Pre-traini...	2022-11-24	Code
22	HiTeA-5M	62.9	No	HiTeA: Hierarchical Temporal-Aware Video-Languag...	2022-12-30	-
23	Clover	60	No	Clover: Towards A Unified Video-Language Alignme...	2022-07-16	Code
24	VIOLET	59.7	No	VIOLET : End-to-End Video-Language Transformers ...	2021-11-24	Code
25	Singularity-5M	59.5	Yes	Revealing Single Frame Bias for Video-and-Langua...	2022-06-07	Code
26	FROZEN	57.2	No	Frozen in Time: A Joint Video and Image Encoder ...	2021-04-01	Code
27	MILES	56.9	No	MILES: Visual BERT Pre-training with Injected La...	2022-04-26	Code
28	Y. Ge et. al.	56.4	No	Bridging Video-text Retrieval with Multiple Choi...	2022-01-13	Code
29	OA-Trans	55.6	No	Object-aware Video-language Pre-training for Ret...	2021-12-01	Code
30	ALPRO	55.4	No	Align and Prompt: Video-and-Language Pre-trainin...	2021-12-17	Code
31	LaT	53.3	No	LaT: Latent Translation with Cycle-Consistency f...	2022-07-11	-
32	A. Nagrani et. al.	50.3	Yes	Learning Audio-Video Modalities from Image Capti...	2022-04-01	-
33	HD-VILA	44.1	No	Advancing High-Resolution Video-Language Represe...	2021-11-19	Code
34	TACo	33.4	No	TACo: Token-aware Cascade Contrastive Learning f...	2021-08-23	-
35	MIL-NCE	32.4	No	End-to-End Learning of Visual Representations fr...	2019-12-13	Code
36	VideoCLIP	30	No	VideoCLIP: Contrastive Pre-training for Zero-sho...	2021-09-28	Code
37	VATT-MBS	29.7	No	VATT: Transformers for Multimodal Self-Supervise...	2021-04-22	Code
38	SSML	29.3	No	Noise Estimation Using Density Estimation for Se...	2020-03-06	Code

#1InternVideo2-6BSOTA
85.1
text-to-video R@10· Extra Data· 2024-03-22
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding Code
#2GRAM
83.9
text-to-video R@10· Extra Data· 2024-12-16
Gramian Multimodal Representation Learning and Alignment Code
#3InternVideo2-1B
82.5
text-to-video R@10· Extra Data· 2024-03-22
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding Code
#4VAST, HowToCaption-finetunedSOTA
81.4
text-to-video R@10· 2023-10-07
HowToCaption: Prompting LLMs to Transform Video Annotations at Scale Code
#5FluxViT-B
79.6
text-to-video R@10· Extra Data· 2025-03-18
Make Your Training Flexible: Towards Deployment-Efficient Video Models Code
#6mPLUG-2SOTA
79
text-to-video R@10· 2023-02-01
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video Code
#7LanguageBind(ViT-H/14)
78.7
text-to-video R@10· Extra Data· 2023-10-03
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment Code
#8LanguageBind(ViT-L/14)
76
text-to-video R@10· Extra Data· 2023-10-03
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment Code
#9FluxViT-S
75.8
text-to-video R@10· Extra Data· 2025-03-18
Make Your Training Flexible: Towards Deployment-Efficient Video Models Code
#10VAST
73.9
text-to-video R@10· Extra Data· 2023-05-29
VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset Code
#11BT-Adapter
73.5
text-to-video R@10· 2023-09-27
BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning Code
#12HowToCaption
73.3
text-to-video R@10· 2023-10-07
HowToCaption: Prompting LLMs to Transform Video Annotations at Scale Code
#13UMT-L (ViT-L/16)
73.1
text-to-video R@10· Extra Data· 2023-03-28
Unmasked Teacher: Towards Training-Efficient Video Foundation Models Code
#14FlorenceSOTA
72.6
text-to-video R@10· 2021-11-22
Florence: A New Foundation Model for Computer Vision Code
#15vid-TLDR (UMT-L)
72.4
text-to-video R@10· Extra Data· 2024-03-20
vid-TLDR: Training Free Token merging for Light-weight Video Transformer Code
#16ImageBind
70
text-to-video R@10· 2023-05-09
ImageBind: One Embedding Space To Bind Them All Code
#17HiTeA-17M
69.9
text-to-video R@10· 2022-12-30
HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training
#18CLIP4ClipSOTA
66.9
text-to-video R@10· 2021-04-18
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval Code
#19Singularity-17M
66.7
text-to-video R@10· Extra Data· 2022-06-07
Revealing Single Frame Bias for Video-and-Language Learning Code
#20OmniVL
66.6
text-to-video R@10· Extra Data· 2022-09-15
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
#21Yatai Ji et. al.
65
text-to-video R@10· 2022-11-24
Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning Code
#22HiTeA-5M
62.9
text-to-video R@10· 2022-12-30
HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training
#23Clover
60
text-to-video R@10· 2022-07-16
Clover: Towards A Unified Video-Language Alignment and Fusion Model Code
#24VIOLET
59.7
text-to-video R@10· 2021-11-24
VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling Code
#25Singularity-5M
59.5
text-to-video R@10· Extra Data· 2022-06-07
Revealing Single Frame Bias for Video-and-Language Learning Code
#26FROZENSOTA
57.2
text-to-video R@10· 2021-04-01
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval Code
#27MILES
56.9
text-to-video R@10· 2022-04-26
MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval Code
#28Y. Ge et. al.
56.4
text-to-video R@10· 2022-01-13
Bridging Video-text Retrieval with Multiple Choice Questions Code
#29OA-Trans
55.6
text-to-video R@10· 2021-12-01
Object-aware Video-language Pre-training for Retrieval Code
#30ALPRO
55.4
text-to-video R@10· 2021-12-17
Align and Prompt: Video-and-Language Pre-training with Entity Prompts Code
#31LaT
53.3
text-to-video R@10· 2022-07-11
LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
#32A. Nagrani et. al.
50.3
text-to-video R@10· Extra Data· 2022-04-01
Learning Audio-Video Modalities from Image Captions
#33HD-VILA
44.1
text-to-video R@10· 2021-11-19
Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions Code
#34TACo
33.4
text-to-video R@10· 2021-08-23
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
#35MIL-NCESOTA
32.4
text-to-video R@10· 2019-12-13
End-to-End Learning of Visual Representations from Uncurated Instructional Videos Code
#36VideoCLIP
30
text-to-video R@10· 2021-09-28
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding Code
#37VATT-MBS
29.7
text-to-video R@10· 2021-04-22
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text Code
#38SSML
29.3
text-to-video R@10· 2020-03-06
Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning Code