List your company

Referring Video Object Segmentation on JHMDB-Sentences (with P@X metrics)

74.4Overall IoUVD-IT
53.28858.76964.2569.731Jan 3, 2022May 18, 2022Oct 1, 2022Feb 14, 2023Jun 30, 2023Nov 13, 2023Mar 28, 2024

Evaluation results

MethodLinks
VD-ITBackbone=Video Diffusion2024.0374.4—————73.446.5
HTRBackbone=VideoSwin-B2024.0373.997.19272.12,3700.372.644.9
SgMgBackbone=Video-Swin-B2024.0373.7—————72.545
SOCBackbone=Video-Swin-B, Image Pretrain=true2023.0573.696.991.471.12,1300.172.344.6
OnlineReferBackbone=Video-Swin-B, Online/Offline=semi-online, Window size (w)=52023.0773.596.190.4712,1900.271.9—
OnlineReferBackbone=VideoSwin-B2024.0373.596.190.4712,1900.271.9—
ReferFormerBackbone=Video-Swin-B, Window size (w)=52022.017396.290.270.22,1000.371.843.7
ReferFormerBackbone=Video-Swin-B, Image Pretrain=true2023.057396.290.270.22,1000.371.843.7
ReferFormerBackbone=Video-Swin-B, Online/Offline=offline, Window size (w)=52023.077396.290.270.22,1000.371.8—
ReferFormerBackbone=Video-Swin-B2024.0373—————71.843.7
ReferFormerBackbone=VideoSwin-B2024.037396.290.270.22,1000.371.843.7
ReferFormerBackbone=Video-Swin-S, Window size (w)=52022.0172.895.890.168.72,0300.271.542.4
SgMgBackbone=Video-Swin-T2024.0372.8—————71.744.4
SOCBackbone=Video-Swin-T, Image Pretrain=true2023.0572.796.388.767.21,9600.171.642.7
ReferFormerBackbone=Video-Swin-T, Window size (w)=52022.0171.995.889.366.81,8900.27142.2
ReferFormerBackbone=Video-Swin-T, Image Pretrain=true2023.0571.995.889.366.81,8900.27142.2
ReferFormerBackbone=Video-Swin-T, Online/Offline=offline, Window size (w)=52023.0771.995.889.366.81,8900.271—
ReferFormerBackbone=Video-Swin-T2024.0371.9—————7142.2
SOCBackbone=Video-Swin-T, Image Pretrain=false2023.0570.794.786.462.71,7900.170.139.7
MTTRBackbone=Video-Swin-T, Window size (w)=102022.0170.193.985.261.61,6600.169.839.2
MTTRBackbone=Video-Swin-T, Image Pretrain=false2023.0570.193.985.261.61,6600.169.839.2
MTTRBackbone=Video-Swin-T, Online/Offline=offline, Window size (w)=102023.0770.193.985.261.61,6600.169.8—
MTTRBackbone=Video-Swin-T2024.0370.1—————69.839.2
MTTRBackbone=VideoSwin-T2024.0370.193.985.261.61,6600.169.839.2
ReferFormerBackbone=Video-Swin-T, Window size (w)=6, Training protocol=trained from scratch2022.017093.384.261.41,6400.369.339.1
ReferFormerBackbone=Video-Swin-T, Image Pretrain=false2023.057093.384.261.41,6400.369.339.1
MTTRBackbone=Video-Swin-T, Window size (w)=82022.0167.49181.5571,4400.167.936.6
ClawCraneNetBackbone=ResNet-50/1012022.0164.48879.656.61,4700.265.6—
ClawCraneNetBackbone=ResNet-50/101, Image Pretrain=false2023.0564.48879.656.61,4700.265.6—
ClawCraneNetBackbone=ResNet-50/101, Online/Offline=offline2023.0764.48879.656.61,4700.265.6—
ClawCraneNetBackbone=ResNet-50/1012024.0364.4—————65.6—
ClawCraneNetBackbone=ResNet-50/1012024.0364.48879.656.61,4700.265.6—
CMSA + CFSABackbone=ResNet-1012022.0162.876.462.538.99000.158.1—
CMSA + CFSABackbone=ResNet-101, Image Pretrain=false2023.0562.876.462.538.99000.158.1—
CMSA + CFSABackbone=ResNet-101, Online/Offline=offline2023.0762.876.462.538.99000.158.1—
CMSA + CFSABackbone=ResNet-1012024.0362.876.462.538.99000.158.1—
CMPC-VBackbone=I3D2022.0161.681.365.737.1700061.734.2
CMPC-VBackbone=I3D, Image Pretrain=false2023.0561.681.365.737.1700061.734.2
CMPC-VBackbone=I3D, Online/Offline=offline2023.0761.681.365.737.1700061.7—
CMPC-VBackbone=I3D2024.0361.6—————61.731.2
CMPC-VBackbone=I3D2024.0361.681.365.737.1700061.734.2
ACANBackbone=I3D2022.0157.675.656.428.7340058.428.9
ACANBackbone=I3D, Image Pretrain=false2023.0557.675.656.428.7340058.428.9
ACANBackbone=I3D, Online/Offline=offline2023.0757.675.656.428.7340058.4—
ACANBackbone=I3D2024.0357.6—————58.428.9
ACANBackbone=I3D2024.0357.675.656.428.7340058.428.9
Hu et al.Backbone=VGG-162022.0154.663.3358.520052.817.8
Hu et al.Backbone=VGG-16, Image Pretrain=false2023.0554.663.3358.520052.817.8
Hu et al.Backbone=VGG-16, Online/Offline=offline2023.0754.663.3358.520052.8—
Hu et al.Backbone=VGG-162024.0354.6—————52.817.8
Hu et al.Backbone=VGG-162024.0354.663.3358.520052.817.8
Gavrilyuk et al.Backbone=I3D2022.0154.169.94617.3140054.223.3
Gavrilyuk et al.Backbone=I3D, Image Pretrain=false2023.0554.169.94617.3140054.223.3
Gavrilyuk et al.Backbone=I3D, Online/Offline=offline2023.0754.169.94617.3140054.2—
Gavrilyuk et al.Backbone=I3D2024.0354.1—————54.223.3
Gavrilyuk et al.Backbone=I3D2024.0354.169.94617.3140054.223.3