Instance Segmentation on Refer-YouTube-VOS (2021 public validation)

Metric: J&F (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

#	Model↕	J&F▼	Extra Data	Paper	Date↕	Code
1	MPG-SAM 2	73.9	No	MPG-SAM 2: Adapting SAM 2 with Mask Priors and G...	2025-01-23	Code
2	VRS-HQ (Chat-UniVi-13B)	71	No	The Devil is in Temporal Token: High Quality Vid...	2025-01-15	Code
3	GLEE-Pro	70.6	Yes	General Object Foundation Model for Images and V...	2023-12-14	Code
4	UNINEXT-H	70.1	No	Universal Instance Perception as Object Discover...	2023-03-12	Code
5	ReferDINO (Swin-B)	69.3	No	ReferDINO: Referring Video Object Segmentation w...	2025-01-24	-
6	MUTR	68.4	No	Referred by Multi-Modality: A Unified Temporal T...	2023-05-25	Code
7	VLP (VLMo-L)	67.6	No	Harnessing Vision-Language Pretrained Models wit...	2024-05-17	-
8	UniRef-L (Swin-L)	67.4	No	-	-	-
9	HTR (Pre-training)	67.1	No	Temporally Consistent Referring Video Object Seg...	2024-03-28	Code
10	DsHmp (Video-Swin-Base)	67.1	No	Decoupling Static and Hierarchical Motion Percep...	2024-04-04	Code
11	UniRef++-L	66.9	No	UniRef++: Segment Every Reference Object in Spat...	2023-12-25	Code
12	ViLLa	66.5	No	ViLLa: Video Reasoning Segmentation with Large L...	2024-07-18	Code
13	DEVA (ReferFormer)	66	Yes	Tracking Anything with Decoupled Video Segmentat...	2023-09-07	Code
14	SgMg (Pre-training)	65.7	No	Spectrum-guided Multi-granularity Referring Vide...	2023-07-25	Code
15	GroPrompt	65.5	No	GroPrompt: Efficient Grounded Prompting and Adap...	2024-06-18	-
16	EPCFormer (ViT-H)	65	No	Expression Prompt Collaboration Transformer for ...	2023-08-08	-
17	UniLSeg-100	64.9	No	Universal Segmentation at Arbitrary Granularity ...	2023-12-04	Code
18	LoSh-R	64.2	Yes	LoSh: Long-Short Text Joint Prediction Network f...	2023-06-14	Code
19	VLT	63.8	No	VLT: Vision-Language Transformer and Query Gener...	2022-10-28	Code
20	OnlineRefer (Swin-L, online)	63.5	No	OnlineRefer: A Simple Online Baseline for Referr...	2023-07-18	Code
21	R2VOS (Video-Swin-T)	61.3	Yes	Towards Robust Referring Video Object Segmentati...	2022-07-04	Code
22	SOC (Video-Swin-T)	59.2	No	SOC: Semantic-Assisted Object Cluster for Referr...	2023-05-26	Code
23	UniVS(Swin-L)	58	Yes	UniVS: Unified and Universal Video Segmentation ...	2024-02-28	Code
24	ReferFormer (ResNet-101)	57.3	Yes	Language as Queries for Referring Video Object S...	2022-01-03	Code
25	MANET	55.63	No	Multi-Attention Network for Compressed Video Ref...	2022-07-26	Code
26	ReferFormer (ResNet-50)	55.6	Yes	Language as Queries for Referring Video Object S...	2022-01-03	Code
27	MTTR (w=12)	55.32	No	End-to-End Referring Video Object Segmentation w...	2021-11-29	Code
28	Locater	50	No	Local-Global Context Aware Transformer for Langu...	2022-03-18	Code
29	MLRLSA	49.7	No	-	-	-
30	VLIDE	49.56	No	Deeply Interleaved Two-Stream Encoder for Referr...	2022-03-30	-
31	URVOS	48.9	No	-	-	Code
32	InternVideo2.5	34.2	No	InternVideo2.5: Empowering Video MLLMs with Long...	2025-01-21	Code