Referring Expression Segmentation on J-HMDB

Metric: IoU mean (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	IoU mean▼	Extra Data	Paper	Date↕	Code
1	SgMg (Video-Swin-B)	0.725	Yes	Spectrum-guided Multi-granularity Referring Vide...	2023-07-25	Code
2	SOC (Video-Swin-B)	0.723	Yes	SOC: Semantic-Assisted Object Cluster for Referr...	2023-05-26	Code
3	SOC (Video-Swin-T)	0.701	No	SOC: Semantic-Assisted Object Cluster for Referr...	2023-05-26	Code
4	MTTR (w=10)	0.698	No	End-to-End Referring Video Object Segmentation w...	2021-11-29	Code
5	MTTR (w=8)	0.679	No	End-to-End Referring Video Object Segmentation w...	2021-11-29	Code
6	VLIDE	0.666	No	Deeply Interleaved Two-Stream Encoder for Referr...	2022-03-30	-
7	ClawCraneNet	0.655	No	ClawCraneNet: Leveraging Object-level Relation f...	2021-03-19	-
8	HINet	0.627	No	-	-	-
9	CMPC-V	0.617	No	Cross-Modal Progressive Comprehension for Referr...	2021-05-15	Code
10	Hui et al.	0.604	No	Collaborative Spatial-Temporal Modeling for Lang...	2021-05-14	-
11	ACGA	0.584	No	-	-	Code
12	CMSA+CFSA	0.581	No	Referring Segmentation in Images and Videos with...	2021-02-09	-
13	AAMN	0.576	No	Actor and Action Modular Network for Text-based ...	2020-11-02	-
14	CMDy	0.576	No	-	-	-
15	Gavrilyuk et al. (Optical flow)	0.57	No	Actor and Action Video Segmentation from a Sente...	2018-03-20	Code
16	RefVOS	0.568	No	-	-	-
17	VT-Capsule	0.55	No	-	-	-
18	Gavrilyuk et al.	0.542	No	Actor and Action Video Segmentation from a Sente...	2018-03-20	Code
19	Hu et al.	0.528	No	Segmentation from Natural Language Expressions	2016-03-20	Code
20	Li et al.	0.491	No	-	-	-

#1SgMg (Video-Swin-B)SOTA
0.725
IoU mean· Extra Data· 2023-07-25
Spectrum-guided Multi-granularity Referring Video Object Segmentation Code
#2SOC (Video-Swin-B)SOTA
0.723
IoU mean· Extra Data· 2023-05-26
SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation Code
#3SOC (Video-Swin-T)
0.701
IoU mean· 2023-05-26
SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation Code
#4MTTR (w=10)SOTA
0.698
IoU mean· 2021-11-29
End-to-End Referring Video Object Segmentation with Multimodal Transformers Code
#5MTTR (w=8)
0.679
IoU mean· 2021-11-29
End-to-End Referring Video Object Segmentation with Multimodal Transformers Code
#6VLIDE
0.666
IoU mean· 2022-03-30
Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation
#7ClawCraneNetSOTA
0.655
IoU mean· 2021-03-19
ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation
#8HINet
0.627
IoU mean
No paper
#9CMPC-V
0.617
IoU mean· 2021-05-15
Cross-Modal Progressive Comprehension for Referring Segmentation Code
#10Hui et al.
0.604
IoU mean· 2021-05-14
Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
#11ACGA
0.584
IoU mean
No paperCode
#12CMSA+CFSASOTA
0.581
IoU mean· 2021-02-09
Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
#13AAMNSOTA
0.576
IoU mean· 2020-11-02
Actor and Action Modular Network for Text-based Video Segmentation
#14CMDy
0.576
IoU mean
No paper
#15Gavrilyuk et al. (Optical flow)SOTA
0.57
IoU mean· 2018-03-20
Actor and Action Video Segmentation from a Sentence Code
#16RefVOS
0.568
IoU mean
No paper
#17VT-Capsule
0.55
IoU mean
No paper
#18Gavrilyuk et al.
0.542
IoU mean· 2018-03-20
Actor and Action Video Segmentation from a Sentence Code
#19Hu et al.SOTA
0.528
IoU mean· 2016-03-20
Segmentation from Natural Language Expressions Code
#20Li et al.
0.491
IoU mean
No paper