Video on Refer-YouTube-VOS

Metric: J&F (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

#	Model↕	J&F▼	Extra Data	Paper	Date↕	Code
1	FindTrack	73.7	Yes	Find First, Track Next: Decoupling Identificatio...	2025-03-05	Code
2	GLEE-Pro	70.6	Yes	General Object Foundation Model for Images and V...	2023-12-14	Code
3	HyperSeg	68.5	Yes	HyperSeg: Towards Universal Visual Segmentation ...	2024-11-26	Code
4	GLEE-Plus	67.7	Yes	General Object Foundation Model for Images and V...	2023-12-14	Code
5	HTR	67.1	Yes	Temporally Consistent Referring Video Object Seg...	2024-03-28	Code
6	SOC	66	Yes	SOC: Semantic-Assisted Object Cluster for Referr...	2023-05-26	Code
7	SgMg	65.7	Yes	Spectrum-guided Multi-granularity Referring Vide...	2023-07-25	Code
8	VATEX	65.4	No	Vision-Aware Text Features in Referring Image Se...	2024-04-12	Code
9	VLT	63.8	Yes	VLT: Vision-Language Transformer and Query Gener...	2022-10-28	Code
10	HTML-SwinL	63.4	Yes	-	-	-
11	HTML-Video-SwinB	63.4	Yes	-	-	-
12	ReferFormer (Large)	62.9	Yes	Language as Queries for Referring Video Object S...	2022-01-03	Code
13	HTML-Video-SwinS	61.4	Yes	-	-	-
14	HTML-Video-SwinT	61.2	Yes	-	-	-
15	R2VOS (Swin-T)	60.2	No	Towards Robust Referring Video Object Segmentati...	2022-07-04	Code
16	HTML-ResNet101	58.5	Yes	-	-	-
17	HTML-ResNet50	57.8	Yes	-	-	-
18	CMSA	36.4	Yes	Cross-Modal Self-Attention Network for Referring...	2019-04-09	Code