Video on LSMDC

Metric: text-to-video R@5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	text-to-video R@5▼	Extra Data	Paper	Date↕	Code
1	HunYuan_tvr (huge)	80.1	Yes	Tencent Text-Video Retrieval: Hierarchical Cross...	2022-04-07	-
2	UMT-L (ViT-L/16)	65.5	Yes	Unmasked Teacher: Towards Training-Efficient Vid...	2023-03-28	Code
3	vid-TLDR (UMT-L)	64.5	Yes	vid-TLDR: Training Free Token merging for Light-...	2024-03-20	Code
4	VALOR	56	Yes	VALOR: Vision-Audio-Language Omni-Perception Pre...	2023-04-17	Code
5	mPLUG-2	55.2	Yes	mPLUG-2: A Modularized Multi-modal Foundation Mo...	2023-02-01	Code
6	CLIP-ViP	51.4	Yes	CLIP-ViP: Adapting Pre-trained Image-Text Model ...	2022-09-14	Code
7	HiTeA	50.3	Yes	HiTeA: Hierarchical Temporal-Aware Video-Languag...	2022-12-30	-
8	STAN	49.5	Yes	Revisiting Temporal Modeling for CLIP-based Imag...	2023-01-26	Code
9	MDMMT-2	46.7	Yes	MDMMT-2: Multidomain Multimodal Transformer for ...	2022-03-14	-
10	HunYuan_tvr	46.4	Yes	Tencent Text-Video Retrieval: Hierarchical Cross...	2022-04-07	-
11	EMCL-Net++	46.4	No	Expectation-Maximization Contrastive Learning fo...	2022-11-21	Code
12	CenterCLIP (ViT-B/16)	46.2	Yes	CenterCLIP: Token Clustering for Efficient Text-...	2022-05-02	Code
13	CAMoE	46.1	Yes	Improving Video-Text Retrieval by Multi-Stream C...	2021-09-09	Code
14	Clover	44	No	Clover: Towards A Unified Video-Language Alignme...	2022-07-16	Code
15	X-Pool	43.7	Yes	X-Pool: Cross-Modal Language-Video Attention for...	2022-03-28	Code
16	VIOLETv2	43.5	No	An Empirical Study of End-to-End Video-Language ...	2022-09-04	Code
17	DiffusionRet	43.1	No	DiffusionRet: Generative Text-Video Retrieval wi...	2023-03-17	Code
18	EMCL-Net	42.4	No	Expectation-Maximization Contrastive Learning fo...	2022-11-21	Code
19	CLIP4Clip	41.8	Yes	CLIP4Clip: An Empirical Study of CLIP for End to...	2021-04-18	Code
20	QB-Norm+CLIP4Clip	40.1	Yes	Cross Modal Retrieval with Querybank Normalisation	2021-12-23	Code
21	MDMMT	38.5	Yes	MDMMT: Multidomain Multimodal Transformer for Vi...	2021-03-19	Code
22	HD-VILA	34.1	No	Advancing High-Resolution Video-Language Represe...	2021-11-19	Code
23	Ours	33.2	No	Video and Text Matching with Conditioned Embeddi...	2021-10-21	Code
24	FROZEN	30.8	Yes	Frozen in Time: A Joint Video and Image Encoder ...	2021-04-01	Code
25	MMT-Pretrained	29.9	Yes	Multi-modal Transformer for Video Retrieval	2020-07-21	Code
26	MMT	29.2	No	Multi-modal Transformer for Video Retrieval	2020-07-21	Code
27	Collaborative Experts	26.9	No	Use What You Have: Video Retrieval Using Represe...	2019-07-31	Code
28	MoEE	25.6	Yes	Learning a Text-Video Embedding from Incomplete ...	2018-04-07	Code
29	CLIP	22.7	No	A Straightforward Framework For Video Retrieval ...	2021-02-24	Code
30	JSFusion	21.2	No	A Joint Sequence Fusion Model for Video Question...	2018-08-07	Code
31	Text-Video Embedding	19.6	No	HowTo100M: Learning a Text-Video Embedding by Wa...	2019-06-07	Code
32	Large-Scale Discriminative Clustering	19.2	No	Learning from Video and Text via Large-Scale Dis...	2017-07-27	Code
33	CT-SAN	16.3	No	End-to-end Concept Word Detection for Video Capt...	2016-10-10	-

#1HunYuan_tvr (huge)SOTA
80.1
text-to-video R@5· Extra Data· 2022-04-07
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
#2UMT-L (ViT-L/16)
65.5
text-to-video R@5· Extra Data· 2023-03-28
Unmasked Teacher: Towards Training-Efficient Video Foundation Models Code
#3vid-TLDR (UMT-L)
64.5
text-to-video R@5· Extra Data· 2024-03-20
vid-TLDR: Training Free Token merging for Light-weight Video Transformer Code
#4VALOR
56
text-to-video R@5· Extra Data· 2023-04-17
VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset Code
#5mPLUG-2
55.2
text-to-video R@5· Extra Data· 2023-02-01
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video Code
#6CLIP-ViP
51.4
text-to-video R@5· Extra Data· 2022-09-14
CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment Code
#7HiTeA
50.3
text-to-video R@5· Extra Data· 2022-12-30
HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training
#8STAN
49.5
text-to-video R@5· Extra Data· 2023-01-26
Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring Code
#9MDMMT-2SOTA
46.7
text-to-video R@5· Extra Data· 2022-03-14
MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization
#10HunYuan_tvr
46.4
text-to-video R@5· Extra Data· 2022-04-07
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
#11EMCL-Net++
46.4
text-to-video R@5· 2022-11-21
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations Code
#12CenterCLIP (ViT-B/16)
46.2
text-to-video R@5· Extra Data· 2022-05-02
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval Code
#13CAMoESOTA
46.1
text-to-video R@5· Extra Data· 2021-09-09
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss Code
#14Clover
44
text-to-video R@5· 2022-07-16
Clover: Towards A Unified Video-Language Alignment and Fusion Model Code
#15X-Pool
43.7
text-to-video R@5· Extra Data· 2022-03-28
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval Code
#16VIOLETv2
43.5
text-to-video R@5· 2022-09-04
An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling Code
#17DiffusionRet
43.1
text-to-video R@5· 2023-03-17
DiffusionRet: Generative Text-Video Retrieval with Diffusion Model Code
#18EMCL-Net
42.4
text-to-video R@5· 2022-11-21
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations Code
#19CLIP4ClipSOTA
41.8
text-to-video R@5· Extra Data· 2021-04-18
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval Code
#20QB-Norm+CLIP4Clip
40.1
text-to-video R@5· Extra Data· 2021-12-23
Cross Modal Retrieval with Querybank Normalisation Code
#21MDMMTSOTA
38.5
text-to-video R@5· Extra Data· 2021-03-19
MDMMT: Multidomain Multimodal Transformer for Video Retrieval Code
#22HD-VILA
34.1
text-to-video R@5· 2021-11-19
Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions Code
#23Ours
33.2
text-to-video R@5· 2021-10-21
Video and Text Matching with Conditioned Embeddings Code
#24FROZEN
30.8
text-to-video R@5· Extra Data· 2021-04-01
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval Code
#25MMT-PretrainedSOTA
29.9
text-to-video R@5· Extra Data· 2020-07-21
Multi-modal Transformer for Video Retrieval Code
#26MMT
29.2
text-to-video R@5· 2020-07-21
Multi-modal Transformer for Video Retrieval Code
#27Collaborative ExpertsSOTA
26.9
text-to-video R@5· 2019-07-31
Use What You Have: Video Retrieval Using Representations From Collaborative Experts Code
#28MoEESOTA
25.6
text-to-video R@5· Extra Data· 2018-04-07
Learning a Text-Video Embedding from Incomplete and Heterogeneous Data Code
#29CLIP
22.7
text-to-video R@5· 2021-02-24
A Straightforward Framework For Video Retrieval Using CLIP Code
#30JSFusion
21.2
text-to-video R@5· 2018-08-07
A Joint Sequence Fusion Model for Video Question Answering and Retrieval Code
#31Text-Video Embedding
19.6
text-to-video R@5· 2019-06-07
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips Code
#32Large-Scale Discriminative ClusteringSOTA
19.2
text-to-video R@5· 2017-07-27
Learning from Video and Text via Large-Scale Discriminative Clustering Code
#33CT-SANSOTA
16.3
text-to-video R@5· 2016-10-10
End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering