Video Object Segmentation on Refer-YouTube-VOS

Metric: J (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

#	Model↕	J▼	Extra Data	Paper	Date↕	Code
1	FindTrack	71.8	Yes	Find First, Track Next: Decoupling Identificatio...	2025-03-05	Code
2	GLEE-Pro	68.2	Yes	General Object Foundation Model for Images and V...	2023-12-14	Code
3	GLEE-Plus	65.6	Yes	General Object Foundation Model for Images and V...	2023-12-14	Code
4	HTR	65.3	Yes	Temporally Consistent Referring Video Object Seg...	2024-03-28	Code
5	SOC	64.1	Yes	SOC: Semantic-Assisted Object Cluster for Referr...	2023-05-26	Code
6	SgMg	63.9	Yes	Spectrum-guided Multi-granularity Referring Vide...	2023-07-25	Code
7	VATEX	63.3	No	Vision-Aware Text Features in Referring Image Se...	2024-04-12	Code
8	VLT	61.9	Yes	VLT: Vision-Language Transformer and Query Gener...	2022-10-28	Code
9	HTML-SwinL	61.5	Yes	-	-	-
10	HTML-Video-SwinB	61.5	Yes	-	-	-
11	ReferFormer (Large)	61.3	Yes	Language as Queries for Referring Video Object S...	2022-01-03	Code
12	HTML-Video-SwinS	59.9	Yes	-	-	-
13	HTML-Video-SwinT	59.5	Yes	-	-	-
14	R2VOS (Swin-T)	58.9	No	Towards Robust Referring Video Object Segmentati...	2022-07-04	Code
15	HTML-ResNet101	57.3	Yes	-	-	-
16	HTML-ResNet50	56.5	Yes	-	-	-
17	CMSA	34.8	Yes	Cross-Modal Self-Attention Network for Referring...	2019-04-09	Code