List your company

Referring Video Object Segmentation on Ref-Youtube-VOS v1.0 (test)

61.3J&F ScoreR2-VOS
15.12427.11239.151.088Jul 4, 2022Nov 4, 2022Mar 8, 2023Jul 10, 2023Nov 11, 2023Mar 14, 2024Jul 16, 2024

Evaluation results

MethodLinks
R2-VOSBackbone=V-Swin-T, P (Pre-trained on ref-coco+)=true2022.0761.359.663.1
R2-VOSBackbone=Swin-T, P (Pre-trained on ref-coco+)=false2022.0760.258.961.5
ReferFormerBackbone=V-Swin-T, P (Pre-trained on ref-coco+)=true2022.0759.45860.9
ReferFormerBackbone=Swin-T, P (Pre-trained on ref-coco+)=false2022.0758.757.659.9
VISABackbone=LLaVA-13B, Instruction Tuning=true2024.0757.455.759
VISABackbone=Chat-UniVi-13B, Instruction Tuning=true2024.0757.455.659.1
R2-VOSBackbone=ResNet50, P (Pre-trained on ref-coco+)=false2022.0757.356.158.4
R2-VOSBackbone=V-Swin-T, P (Pre-trained on ref-coco+)=false2022.0757.155.958.2
CITDBackbone=ResNet101, P (Pre-trained on ref-coco+)=false2022.0756.454.858.1
ReferFormerBackbone=V-Swin-T, P (Pre-trained on ref-coco+)=false2022.075654.857.3
ReferFormerBackbone=ResNet50, P (Pre-trained on ref-coco+)=false2022.0755.654.856.5
Chen et al.Backbone=V-Swin-T, P (Pre-trained on ref-coco+)=false2022.0755.65455.6
MTTRBackbone=V-Swin-T, P (Pre-trained on ref-coco+)=false2022.0755.35456.6
YOFOBackbone=ResNet50, P (Pre-trained on ref-coco+)=false2022.0754.450.158.7
VISABackbone=Chat-UniVi-13B, Instruction Tuning=false2024.0754.152.355.8
PMINetBackbone=ResNet101, P (Pre-trained on ref-coco+)=false2022.075351.554.5
VISABackbone=Chat-UniVi-7B, Instruction Tuning=false2024.0752.951.154.7
VISABackbone=LLaVA-7B, Instruction Tuning=true2024.075149.452.6
VISABackbone=Chat-UniVi-7B, Instruction Tuning=true2024.0750.949.252.6
Wu et al.Backbone=ResNet50, P (Pre-trained on ref-coco+)=false2022.0749.748.451
TrackGPTBackbone=LLaVA-13B, Instruction Tuning=true, Reproduced=true2024.0749.548.350.6
LBDTBackbone=LBDT, P (Pre-trained on ref-coco+)=false2022.0749.448.250.6
TrackGPTBackbone=LLaVA-7B, Instruction Tuning=true, Reproduced=true2024.0748.246.749.7
URVOSBackbone=ResNet50, P (Pre-trained on ref-coco+)=false2022.0747.245.349.2
LISABackbone=LLaVA-13B, Instruction Tuning=false, Reproduced=true2024.0746.645.247.9
LISABackbone=LLaVA-7B, Instruction Tuning=false2024.0745.744.347.1
CMSA + RNNBackbone=ResNet50, P (Pre-trained on ref-coco+)=false2022.0736.434.838.1
CMSABackbone=ResNet50, P (Pre-trained on ref-coco+)=false2022.0734.933.336.5
LMPMBackbone=Swin-T, Instruction Tuning=false2024.0734.12939.1
LLaMA-VID+LMPMBackbone=Swin-T, Instruction Tuning=false2024.0734.12939.1
ReferFormerBackbone=Video-Swin-B, Instruction Tuning=false2024.0732.731.234.3
MTTRBackbone=Video-Swin-T, Instruction Tuning=false2024.073029.830.2
ReferFormerBackbone=ResNet-50, Instruction Tuning=false2024.0716.916.617.1