List your company

Video Instance Segmentation on OVIS (val)

57.1APCAVIS
32.03638.54345.0551.557Jul 22, 2022Mar 16, 2023Nov 9, 2023Jul 4, 2024Feb 27, 2025Oct 23, 2025Jun 18, 2026

Evaluation results

MethodLinks
CAVISBackbone=ViT-L, temporal refiner=true2024.0757.182.663.521.261.8———
DVIS-DAQBackbone=ViT-L, Pre-training=DINOv2, GFLOPs=1173, FPS=8, Input resolution=5442026.0254.3—60.2—59.8———
DVIS++Backbone=ViT-L, temporal refiner=true2024.0753.478.958.521.158.7———
CAVISBackbone=ViT-L, temporal refiner=false2024.0753.275.959.120.958.2———
CAVISBackbone=ViT-L, Pre-training=DINOv2, GFLOPs=863, FPS=15, Input resolution=default2026.0253.2—59.1—58.2———
VidEoMTBackbone=ViT-L, Pre-training=DINOv2, GFLOPs=934, FPS=115, Input resolution=5442026.0252.5—57.2—57.5———
GLEE-ProBackbone=EVA02-L, Evaluation Protocol=Fine-tuned2023.1250.471.455.5—————
DVISMode=Offline, Backbone=Swin-L, Resolution=720px2023.0649.975.95319.455.3———
DVISBackbone=Swin-L2023.1249.975.953—————
DVIS++Backbone=ViT-L, temporal refiner=false2024.0749.672.55520.854.6———
DVIS++Backbone=ViT-L, Pre-training=DINOv2, GFLOPs=868, FPS=17, Input resolution=default2026.0249.6—55—54.6———
DVIS-DAQBackbone=Swin-L, Pre-training=IN21K, GFLOPs=423, FPS=12, Input resolution=default2026.0249.5—51.7—54.9———
UNINEXTBackbone=ViT-H, Online=true2023.034972.552.2—————
UNINEXTBackbone=ViT-H2023.124972.552.2—————
CAVISBackbone=Swin-L, temporal refiner=false2024.0748.67452.519.553.3———
DVISMode=Offline, Backbone=Swin-L2023.0648.674.750.518.853.8———
DVISbackbone=Swin-L, processing_mode=offline2023.1148.674.750.518.853.8———
DVISMode=Online, Backbone=Swin-L, Resolution=720px2023.0647.171.949.219.452.5———
DVISbackbone=Swin-L, processing_mode=online/near-online2023.1147.171.949.219.452.5———
CTVISBackbone=Swin-L, temporal refiner=false2024.0746.971.547.519.152.1———
CTVISBackbone=Swin-L, Params.=216M2023.0746.971.547.519.152.1———
TCOVISBackbone=Swin-L, temporal refiner=false2024.0746.770.949.519.150.8———
RefineVISBackbone=Swin-L, Evaluation Protocol=online2023.0646.169.747.81950.8———
RefineVISBackbone=Swin-L, Evaluation Protocol=offline2023.064670.448.419.151.2———
DVISBackbone=Swin-L, temporal refiner=false2024.0745.971.148.318.551.5———
DVISMode=Online, Backbone=Swin-L2023.0645.971.148.318.551.5———
DVISBackbone=Swin-L, Pre-training=IN21K, GFLOPs=419, FPS=24, Input resolution=default2026.0245.9—48.3—51.5———
GenVISBackbone=Swin-L, Evaluation Mode=semi-online2022.1145.469.247.818.949———
GenVISMode=Offline, Backbone=Swin-L, Use COCO pseudo videos=true2023.0645.469.247.818.949———
GenVISBackbone=Swin-L2023.1245.469.247.8—————
GenVIS (near-online)backbone=Swin-L, processing_mode=near-online2023.1145.469.247.818.949———
GenVISBackbone=Swin-L, temporal refiner=false2024.0745.269.148.419.148.6———
GenVISBackbone=Swin-L, Evaluation Mode=online2022.1145.269.148.419.148.6———
GenVisMode=Online, Backbone=Swin-L, Use COCO pseudo videos=true2023.0645.269.148.419.148.6———
GenVIS (online)backbone=Swin-L, processing_mode=online2023.1145.269.148.419.148.6———
NOVISBackbone=Swin-L, T/S=4/2, MST=720, Note=Only evaluated but not trained on larger input resolution2023.0843.568.343.819.446.9———
NOVISBackbone=Swin-L2023.1243.568.343.8—————
TarVISbackbone=Swin-L, processing_mode=online/near-online2023.1143.267.844.61850.4———
NOVISBackbone=Swin-L, T/S=4/2, MST=3602023.084366.944.518.946.3———
MinVISBackbone=ViT-L, temporal refiner=false2024.0742.965.745.419.846.5———
IDOLBackbone=Swin-L2022.1142.665.745.217.949.6———
IDOLBackbone=Swin-L2023.0642.665.745.217.949.6———
IDOLSupervision=Pixel, Backbone=Swin Large (SwinL), Input Resolution=720p2023.0342.665.745.2—————
MDQESupervision=Pixel, Backbone=Swin Large (SwinL), Input Resolution=720p2023.0342.667.844.3——49.321.665.1
IDOLBackbone=Swin-L, Online=true2023.0342.665.745.2—————
IDOLMode=Online, Backbone=Swin-L, Resolution=720px2023.0642.665.745.217.949.6———
ROVISMode=Online, Backbone=Swin-L, Resolution=720px2023.0642.664.742.618.449.1———
MDQEMode=Offline, Backbone=Swin-L, Resolution=720px2023.0642.667.844.318.346.5———
IDOLBackbone=Swin-L, Params.=213M2023.0742.665.745.217.949.6———
IDOLBackbone=Swin-L, T/S=ON, MST=7202023.0842.665.745.217.949.6———
IDOLBackbone=Swin-L2023.1242.665.745.2—————
IDOLbackbone=Swin-L, processing_mode=online/near-online2023.1142.665.745.217.949.6———
MinVISSupervision=Pixel, Backbone=Swin Large (SwinL)2023.0341.665.443.4——48.520.565.5
MinVISMode=Online, Backbone=Swin-L, Resolution=720px2023.0641.665.242.819.345.1———
ROVISMode=Online, Backbone=Swin-L2023.0641.66542.918.746.9———
UNINEXTBackbone=ConvNeXt-L, Online=true2023.0341.165.842—————
UNINEXTBackbone=ConvNeXt-L2023.1241.165.842—————
BoxVISSupervision=Box, Backbone=Swin Large (SwinL), Tracker=clip-level tracker (MDQE)2023.0340.668.439.9——45.820.959.4
GLEE-PlusBackbone=Swin-L, Evaluation Protocol=Fine-tuned2023.1240.363.839.8—————
IDOLBackbone=Swin-L, temporal refiner=false2024.074063.140.517.646.4———
IDOLMode=Online, Backbone=Swin-L2023.064063.140.517.646.4———
Axial-VS w/ Tube-Linkbackbone=Swin-L, processing_mode=offline2023.1139.864.540.117.943.7———
MinVISBackbone=Swin-L, temporal refiner=false2024.0739.461.541.318.143.3———
MinVISBackbone=Swin-L2022.1139.461.541.318.143.3———
MinVISBackbone=Swin-L2023.0639.461.541.318.143.3———
MinVISMode=Online, Backbone=Swin-L2023.0639.461.541.318.143.3———
MinVISBackbone=Swin-L, Params.=216M2023.0739.461.541.318.143.3———
MinVISBackbone=Swin-L, T/S=ON, MST=3602023.0839.461.541.318.143.3———
MinVISbackbone=Swin-L, processing_mode=online/near-online2023.1139.461.541.318.143.3———
MinVISBackbone=Swin-L, Pre-training=IN21K, GFLOPs=408, FPS=30, Input resolution=default2026.0239.4—41.3—43.3———
Axial-VS w/ Tube-Linkbackbone=Swin-L, processing_mode=online/near-online2023.1139.162.339.818.542.3———
GLEE-ProBackbone=EVA02-L, Evaluation Protocol=Zero-shot2023.1238.759.439.7—————
CAROQBackbone=Swin-L, temporal refiner=false2024.0738.260.739.517.744.1———
CAVISBackbone=ResNet-50, temporal refiner=false2024.0737.663.438.216.543.5———
VISAGEBackbone=ResNet-50, temporal refiner=false2024.0736.260.335.316.140.3———
GRAtt-VISTraining Protocol=video train2026.0636.260.836.816.840———
GenVISBackbone=ResNet-50, temporal refiner=false2024.0735.860.836.216.339.6———
GenVISBackbone=ResNet-50, Evaluation Mode=online2022.1135.860.836.216.339.6———
GenVIS (online)backbone=ResNet50, processing_mode=online2023.1135.860.836.216.339.6———
GenVISTraining Protocol=video train2026.0635.860.836.216.339.6———
CTVISBackbone=ResNet-50, temporal refiner=false2024.0735.560.834.916.141.9———
CTVISBackbone=ResNet-50, Params.=44M2023.0735.560.834.916.141.9———
CTVISTraining Protocol=video train2026.0635.560.834.916.141.9———
TCOVISBackbone=ResNet-50, temporal refiner=false2024.0735.360.736.615.739.5———
DeVISBackbone=SwinL, Method Mode=Near-online, T=6, S=42022.0734.658.736.8—————
DeVISBackbone=Swin-L, T/S=6/4, MST=3602023.0834.658.736.8—————
GenVISBackbone=ResNet-50, Evaluation Mode=semi-online2022.1134.559.43516.638.3———
GenVISBackbone=ResNet-502023.1234.559.435—————
GenVIS (near-online)backbone=ResNet50, processing_mode=near-online2023.1134.559.43516.638.3———
BoxVISSupervision=Box, Backbone=Swin Large (SwinL)2023.0334.45933.8——39.514.656.8
DVISMode=Offline, Backbone=ResNet50, Resolution=720px2023.0634.159.832.315.941.1———
DVISBackbone=ResNet-502023.1234.159.832.3—————
UNINEXTBackbone=ResNet-50, Online=true2023.033455.535.6—————
UNINEXTBackbone=ResNet-502023.123455.535.6—————
DVISMode=Offline, Backbone=ResNet502023.0633.860.433.515.339.5———
DVISbackbone=ResNet50, processing_mode=offline2023.1133.860.433.515.339.5———
RefineVISBackbone=ResNet-50, Evaluation Protocol=offline2023.0633.756.234.815.639.8———
RefineVISBackbone=ResNet-50, Evaluation Protocol=online2023.0633.457.132.616.340.2———
Tube-Linkbackbone=Swin-L, processing_mode=online/near-online, reproduced=true2023.1133.354.632.816.837.7———
MDQEType=720p, Backbone=ResNet50, FPS=13.5, Params=51.4M2023.033357.432.215.438.4———