List your company

Referring Video Segmentation on Ref-YouTube-VOS

73.9J&F ScoreMPG-SAM 2
47.58854.41961.2568.081Jul 26, 2022Mar 5, 2023Oct 14, 2023May 24, 2024Jan 1, 2025Aug 12, 2025Mar 23, 2026

Evaluation results

MethodLinks
MPG-SAM 22025.0173.971.776.1
FindTrack++N=10, fine-tuning=true2025.0373.771.875.7
FindTrack++N=5, fine-tuning=true2025.0373.171.275
GLEE-ProBackbone=EVA02-L2023.1270.668.272.9
FindTrackN=52025.0370.368.672
FindTrackN=102025.0370.368.671.9
UNINEXTBackbone=ViT-H2023.0370.167.672.7
UNINEXTBackbone=ViT-H2023.1270.167.672.7
ReferDINOBackbone=Swin-B2025.0169.36771.5
ReferDINOBackbone=GroundingDINO-B2026.0369.36771.5
SAMWISEPublication=CVPR'252025.0369.267.870.6
MUTRPublication=AAAI'242025.0368.466.470.4
MUTRReference=AAAI'242025.0168.466.470.4
AL-Ref-SAM2Backbone=GPT-42026.0367.965.969.9
GLEE-PlusBackbone=Swin-L2023.1267.765.669.7
ReferDINOBackbone=Swin-T2025.0167.565.569.6
SOCPublication=NeurIPS'232025.0367.365.369.3
SOCBackbone=Video-Swin-B2023.1267.365.369.3
LoShBackbone=Swin-B2025.0167.265.469
LoShPublication=CVPR'242025.0367.265.469
LoShReference=CVPR'242025.0167.265.469
DsHmpBackbone=Swin-B2025.0167.16569.1
DsHmpPublication=CVPR'242025.0367.16569.1
DsHmpReference=CVPR'242025.0167.16569.1
DsHmpBackbone=Video-Swin-B2026.0367.16569.1
TrajSegBackbone=LLaVA-7B2026.036765.268.7
G-DINO-DHBackbone=Swin-B2025.0166.764.569
VD-ITPublication=ECCV'242025.0366.564.468.5
VD-ITReference=ECCV'242025.0166.564.468.5
VD-ITBackbone=Video Diffusion2026.0366.564.468.5
G-DINO-SHBackbone=Swin-B2025.0166.264.268.3
UNINEXTBackbone=ConvNext-L2023.0366.26468.4
UNINEXTBackbone=ConvNext-L2023.1266.26468.4
SOCBackbone=Swin-B2025.016664.167.9
SOCReference=NIPS'232025.016664.167.9
TempCDReference=ICCV'232025.0165.863.668
SgMgBackbone=Swin-B2025.0165.763.967.4
SgMgPublication=ICCV'232025.0365.763.967.4
SgMgReference=ICCV'232025.0165.763.967.4
SgMgBackbone=SwinB2024.0265.7——
ReferFormerBackbone=Video-Swin-T2023.0364.962.867
ReferFormerBackbone=Video-Swin-B2023.1264.962.867
DMVSPublication=CVPR'252025.0364.362.466.2
SSAPublication=CVPR'252025.0364.362.266.4
SSABackbone=CLIP-B2026.0364.362.266.4
G-DINO-DHBackbone=Swin-T2025.0164.262.466.1
VideoChat-TPOzero-shot=true2024.1263.952.375.4
G-DINO-SHBackbone=Swin-T2025.0163.96265.8
OnlineReferFine-tuning=true2025.0163.9——
VideoChat-TPOFine-tuning=true2025.0163.9——
VideoLISA2024.1263.761.763.7
LoShBackbone=Swin-T2025.0163.76265.4
VideoLISAFine-tuning=true2025.0163.7——
VideoLISA (p)Backbone=LLaVA-Phi-3.8B2026.0363.761.765.7
DsHmpBackbone=Swin-T2025.0163.661.865.4
OnlineReferBackbone=Swin-L2026.0363.561.665.5
HTMLBackbone=Swin-B2025.0163.461.565.2
HTMLPublication=ICCV'232025.0363.461.565.2
HTMLReference=ICCV'232025.0163.461.565.2
VISAReference=ECCV'242025.016361.464.7
OnlineReferBackbone=Swin-L2024.0263——
VISABackbone=Chat-UniVi-13B2026.036361.464.7
ReferFormer2024.1262.961.364.6
OnlineRefer2024.1262.96164.7
ReferFormerBackbone=Swin-B2025.0162.961.364.6
UniVTGFine-tuning=true2025.0162.9——
ReferFormerFine-tuning=true2025.0162.9——
ReferFormerPublication=CVPR'222025.0362.961.364.6
ReferFormerReference=CVPR'222025.0162.961.364.6
OnlineReferReference=ICCV'232025.0162.96164.7
ReferFormerBackbone=Video-Swin-B2026.0362.961.364.6
VLT+TCPublication=TPAMI'232025.0362.7——
SOCBackbone=Swin-T2025.0162.461.163.7
SgMgBackbone=Swin-T2025.016260.463.5
SgMgBackbone=SwinT2024.0262——
VideoLISABackbone=LLaVA-Phi-3.8B2026.0361.760.263.3
VISABackbone=Chat-UniVi-7B2026.0361.559.863.2
CITDBackbone=Ensemble2023.0361.46062.7
CITDBackbone=Ensemble2023.1261.46062.7
HTMLBackbone=Swin-T2025.0161.259.563
UNINEXTBackbone=ResNet-502023.0361.259.363
UNINEXTBackbone=ResNet-502023.1261.259.363
TrackGPTBackbone=LLaVA-13B2026.0359.558.160.8
ReferFormerBackbone=Swin-T2025.0159.45860.9
ReferFormerBackbone=ResNet-502023.0358.757.460.1
ReferFormerBackbone=ResNet-502023.1258.757.460.1
OnlineReferBackbone=R502024.0257.3——
TrackGPTBackbone=LLaVA-7B2026.0356.455.357.4
MANet2022.0755.6354.7556.51
ReferFormerBackbone=R502024.0255.6——
MTTRVenue=CVPR222022.0755.325456.64
MTTRBackbone=Video-Swin-T2023.0355.35456.6
MTTRBackbone=Video-Swin-T2026.0355.35456.6
VISABackbone=LLaVA-13B2026.0354.45454.8
PMINet + CFBIBackbone=Ensemble2023.0354.25355.5
PMINet + CFBIBackbone=Ensemble2023.1254.25355.5
VISABackbone=LLaVA-7B2026.0353.953.454.3
LISA2024.1252.652.153
LISAFine-tuning=true2025.0152.6——
YOFOBackbone=ResNet-502023.0348.647.549.7