Video on MSVD

Metric: text-to-video Median Rank (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	text-to-video Median Rank▼	Extra Data	Paper	Date↕	Code
1	SSML	6	No	Noise Estimation Using Density Estimation for Se...	2020-03-06	Code
2	Collaborative Experts	6	No	Use What You Have: Video Retrieval Using Represe...	2019-07-31	Code
3	CLIP	3	No	A Straightforward Framework For Video Retrieval ...	2021-02-24	Code
4	FROZEN	3	Yes	Frozen in Time: A Joint Video and Image Encoder ...	2021-04-01	Code
5	DMAE (ViT-B/32)	2	No	Dual-Modal Attention-Enhanced Text-Video Retriev...	2023-09-20	Code
6	QB-Norm+CLIP2Video	2	Yes	Cross Modal Retrieval with Querybank Normalisation	2021-12-23	Code
7	PAU	2	No	Prototype-based Aleatoric Uncertainty Quantifica...	2023-09-29	Code
8	X-Pool	2	Yes	X-Pool: Cross-Modal Language-Video Attention for...	2022-03-28	Code
9	DiffusionRet	2	No	DiffusionRet: Generative Text-Video Retrieval wi...	2023-03-17	Code
10	CLIP4Clip	2	Yes	CLIP4Clip: An Empirical Study of CLIP for End to...	2021-04-18	Code
11	HunYuan_tvr (huge)	1	Yes	Tencent Text-Video Retrieval: Hierarchical Cross...	2022-04-07	-
12	HunYuan_tvr	1	Yes	Tencent Text-Video Retrieval: Hierarchical Cross...	2022-04-07	-
13	MDMMT-2	1	Yes	MDMMT-2: Multidomain Multimodal Transformer for ...	2022-03-14	-
14	Side4Video	1	No	Side4Video: Spatial-Temporal Side Network for Me...	2023-11-27	Code
15	CAMoE	1	Yes	Improving Video-Text Retrieval by Multi-Stream C...	2021-09-09	Code
16	Cap4Video	1	No	Cap4Video: What Can Auxiliary Captions Do for Te...	2022-12-31	Code
17	CenterCLIP (ViT-B/16)	1	Yes	CenterCLIP: Token Clustering for Efficient Text-...	2022-05-02	Code

#1SSML
6
text-to-video Median Rank· 2020-03-06
Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning Code
#2Collaborative ExpertsSOTA
6
text-to-video Median Rank· 2019-07-31
Use What You Have: Video Retrieval Using Representations From Collaborative Experts Code
#3CLIP
3
text-to-video Median Rank· 2021-02-24
A Straightforward Framework For Video Retrieval Using CLIP Code
#4FROZEN
3
text-to-video Median Rank· Extra Data· 2021-04-01
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval Code
#5DMAE (ViT-B/32)
2
text-to-video Median Rank· 2023-09-20
Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning Code
#6QB-Norm+CLIP2Video
2
text-to-video Median Rank· Extra Data· 2021-12-23
Cross Modal Retrieval with Querybank Normalisation Code
#7PAU
2
text-to-video Median Rank· 2023-09-29
Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval Code
#8X-Pool
2
text-to-video Median Rank· Extra Data· 2022-03-28
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval Code
#9DiffusionRet
2
text-to-video Median Rank· 2023-03-17
DiffusionRet: Generative Text-Video Retrieval with Diffusion Model Code
#10CLIP4Clip
2
text-to-video Median Rank· Extra Data· 2021-04-18
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval Code
#11HunYuan_tvr (huge)
1
text-to-video Median Rank· Extra Data· 2022-04-07
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
#12HunYuan_tvr
1
text-to-video Median Rank· Extra Data· 2022-04-07
Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations
#13MDMMT-2
1
text-to-video Median Rank· Extra Data· 2022-03-14
MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization
#14Side4Video
1
text-to-video Median Rank· 2023-11-27
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning Code
#15CAMoE
1
text-to-video Median Rank· Extra Data· 2021-09-09
Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss Code
#16Cap4Video
1
text-to-video Median Rank· 2022-12-31
Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?Code
#17CenterCLIP (ViT-B/16)
1
text-to-video Median Rank· Extra Data· 2022-05-02
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval Code