Video on MiT

Metric: Top 1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Top 1 Accuracy▼	Extra Data	Paper	Date↕	Code
1	OmniVec2	53.1	Yes	-	-	-
2	InternVideo2-1B	50.9	Yes	InternVideo2: Scaling Foundation Models for Mult...	2024-03-22	Code
3	UMT-L (ViT-L/16)	48.7	Yes	Unmasked Teacher: Towards Training-Efficient Vid...	2023-03-28	Code
4	UniFormerV2-L	47.8	Yes	-	-	Code
5	MTV-H (WTS 60M)	47.2	Yes	Multiview Transformers for Video Recognition	2022-01-12	Code
6	CoVeR(JFT-3B)	46.1	Yes	Co-training Transformer with Videos and Images I...	2021-12-14	-
7	CoVeR(JFT-300M)	45	Yes	Co-training Transformer with Videos and Images I...	2021-12-14	-
8	VATT-Large	41.1	Yes	VATT: Transformers for Multimodal Self-Supervise...	2021-04-22	Code
9	MoViNet-A6	40.2	No	MoViNets: Mobile Video Networks for Efficient Vi...	2021-03-21	Code
10	MoViNet-A5	39.1	No	MoViNets: Mobile Video Networks for Efficient Vi...	2021-03-21	Code
11	MoViNet-A4	37.9	No	MoViNets: Mobile Video Networks for Efficient Vi...	2021-03-21	Code
12	VTN	37.4	Yes	Video Transformer Network	2021-02-01	Code
13	MBT (AV)	37.3	No	Attention Bottlenecks for Multimodal Fusion	2021-06-30	Code
14	MoViNet-A3	35.6	No	MoViNets: Mobile Video Networks for Efficient Vi...	2021-03-21	Code
15	MoViNet-A2	34.3	No	MoViNets: Mobile Video Networks for Efficient Vi...	2021-03-21	Code
16	SRTG r3d-101	33.56	No	Learn to cycle: Time-consistent feature discover...	2020-06-15	Code
17	MoViNet-A1	32	No	MoViNets: Mobile Video Networks for Efficient Vi...	2021-03-21	Code
18	SRTG r(2+1)d-50	31.6	No	Learn to cycle: Time-consistent feature discover...	2020-06-15	Code
19	SRTG r3d-50	30.72	No	Learn to cycle: Time-consistent feature discover...	2020-06-15	Code
20	SRTG r(2+1)d-34	28.97	No	Learn to cycle: Time-consistent feature discover...	2020-06-15	Code
21	SRTG r3d-34	28.55	No	Learn to cycle: Time-consistent feature discover...	2020-06-15	Code
22	TRN-Multiscale	28.27	No	Moments in Time Dataset: one million videos for ...	2018-01-09	Code
23	MoViNet-A0	27.5	No	MoViNets: Mobile Video Networks for Efficient Vi...	2021-03-21	Code

#1OmniVec2
53.1
Top 1 Accuracy· Extra Data
No paper
#2InternVideo2-1BSOTA
50.9
Top 1 Accuracy· Extra Data· 2024-03-22
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding Code
#3UMT-L (ViT-L/16)SOTA
48.7
Top 1 Accuracy· Extra Data· 2023-03-28
Unmasked Teacher: Towards Training-Efficient Video Foundation Models Code
#4UniFormerV2-L
47.8
Top 1 Accuracy· Extra Data
No paperCode
#5MTV-H (WTS 60M)SOTA
47.2
Top 1 Accuracy· Extra Data· 2022-01-12
Multiview Transformers for Video Recognition Code
#6CoVeR(JFT-3B)SOTA
46.1
Top 1 Accuracy· Extra Data· 2021-12-14
Co-training Transformer with Videos and Images Improves Action Recognition
#7CoVeR(JFT-300M)
45
Top 1 Accuracy· Extra Data· 2021-12-14
Co-training Transformer with Videos and Images Improves Action Recognition
#8VATT-LargeSOTA
41.1
Top 1 Accuracy· Extra Data· 2021-04-22
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text Code
#9MoViNet-A6SOTA
40.2
Top 1 Accuracy· 2021-03-21
MoViNets: Mobile Video Networks for Efficient Video Recognition Code
#10MoViNet-A5
39.1
Top 1 Accuracy· 2021-03-21
MoViNets: Mobile Video Networks for Efficient Video Recognition Code
#11MoViNet-A4
37.9
Top 1 Accuracy· 2021-03-21
MoViNets: Mobile Video Networks for Efficient Video Recognition Code
#12VTNSOTA
37.4
Top 1 Accuracy· Extra Data· 2021-02-01
Video Transformer Network Code
#13MBT (AV)
37.3
Top 1 Accuracy· 2021-06-30
Attention Bottlenecks for Multimodal Fusion Code
#14MoViNet-A3
35.6
Top 1 Accuracy· 2021-03-21
MoViNets: Mobile Video Networks for Efficient Video Recognition Code
#15MoViNet-A2
34.3
Top 1 Accuracy· 2021-03-21
MoViNets: Mobile Video Networks for Efficient Video Recognition Code
#16SRTG r3d-101SOTA
33.56
Top 1 Accuracy· 2020-06-15
Learn to cycle: Time-consistent feature discovery for action recognition Code
#17MoViNet-A1
32
Top 1 Accuracy· 2021-03-21
MoViNets: Mobile Video Networks for Efficient Video Recognition Code
#18SRTG r(2+1)d-50
31.6
Top 1 Accuracy· 2020-06-15
Learn to cycle: Time-consistent feature discovery for action recognition Code
#19SRTG r3d-50
30.72
Top 1 Accuracy· 2020-06-15
Learn to cycle: Time-consistent feature discovery for action recognition Code
#20SRTG r(2+1)d-34
28.97
Top 1 Accuracy· 2020-06-15
Learn to cycle: Time-consistent feature discovery for action recognition Code
#21SRTG r3d-34
28.55
Top 1 Accuracy· 2020-06-15
Learn to cycle: Time-consistent feature discovery for action recognition Code
#22TRN-MultiscaleSOTA
28.27
Top 1 Accuracy· 2018-01-09
Moments in Time Dataset: one million videos for event understanding Code
#23MoViNet-A0
27.5
Top 1 Accuracy· 2021-03-21
MoViNets: Mobile Video Networks for Efficient Video Recognition Code