List your company

Referring Expression Comprehension on ReferItGame (test)

79.3Top-1 AccSimVG-TB
27.029640.599854.1767.7402Jun 6, 2021Dec 24, 2021Jul 13, 2022Jan 31, 2023Aug 20, 2023Mar 8, 2024Sep 26, 2024

Evaluation results

MethodLinks
SimVG-TBVisual Encoder=ViT-L/32, Time (ms)=1012024.0979.3
SimVG-DBVisual Encoder=ViT-L/32, Time (ms)=1162024.0978.75
Referring TransformerBackbone=RN101, Stage=One-stage, Inference time (ms)=40(15), Pre-trained=true2021.0676.18
Referring TransformerBackbone=RN50, Stage=One-stage, Inference time (ms)=37(14), Pre-trained=true2021.0675.49
SimVG-DBVisual Encoder=ViT-B/32, Time (ms)=522024.0974.83
QRNetBackbone=Swin-S/BERT2024.0674.61
SimVG-TBVisual Encoder=ViT-B/32, Time (ms)=442024.0974.59
TransCPVisual Encoder=RN50, Time (ms)=74*2024.0972.05
VLTVGZero-Shot=false2024.0371.98
PLV-FPNBackbone=ResNet-101/BERT2024.0671.77
VLTVGVisual Encoder=RN50, Time (ms)=79*2024.0971.6
Referring TransformerBackbone=RN101, Stage=One-stage, Inference time (ms)=40(15), Pre-trained=false2021.0671.42
RefTRBackbone=ResNet-101/BERT2024.0671.42
LADSBackbone=ResNet-50/BERT2024.0671.08
CLIP-VGZero-Shot=false2024.0370.89
Referring TransformerBackbone=RN50, Stage=One-stage, Inference time (ms)=37(14), Pre-trained=false2021.0670.81
TransVGBackbone=ResNet-101/BERT2024.0670.73
TransVGVisual Encoder=RN101, Time (ms)=622024.0970.73
Dyn.MDETRVisual Encoder=ViT-B/162024.0970.37
SeqTRZero-Shot=false2024.0369.66
SeqTRBackbone=DarkNet-53/GRU2024.0669.66
SeqTRVisual Encoder=DN53, Time (ms)=502024.0969.66
Qwen-VL + SC-TuneZero-Shot=true2024.0369.28
ScanFormerBackbone=Unified Transformer2024.0668.85
PFOSBackbone=ResNet-101/BERT2024.0667.9
LBYLVisual Encoder=DN53, Time (ms)=302024.0967.47
NMTreeVisual Encoder=RN1012024.0966.44
ReSC-LargeBackbone=DN53, Stage=One-stage, Inference time (ms)=362021.0664.6
ReSC-LargeBackbone=DarkNet-53/BERT2024.0664.6
ReSCLVisual Encoder=DN53, Time (ms)=362024.0964.6
RCCFBackbone=DLA34, Stage=One-stage, Inference time (ms)=252021.0663.79
VGTRVisual Encoder=RN502024.0963.63
DDPNBackbone=RN101, Stage=Two-stage2021.0663
Qwen-VLZero-Shot=true2024.0361.48
FAOABackbone=DN53, Stage=One-stage, Inference time (ms)=232021.0660.67
FAOABackbone=DarkNet-53/BERT2024.0660.67
FAOAVisual Encoder=DN53, Time (ms)=392024.0960.67
ZSGNetBackbone=RN50, Stage=One-stage2021.0658.63
SSGBackbone=DN53, Stage=One-stage, Inference time (ms)=252021.0654.24
DGAVisual Encoder=VGG16, Time (ms)=3412024.0951.99
MiniGPT-v2 + SC-TuneZero-Shot=true2024.0343.68
MiniGPT-v2Zero-Shot=true2024.0336.05
CITEBackbone=RN101, Stage=Two-stage, Inference time (ms)=1962021.0635.07
Similarity NetBackbone=RN101, Stage=Two-stage, Inference time (ms)=1842021.0634.54
MAttNetBackbone=RN101, Stage=Two-stage, Inference time (ms)=3202021.0629.04
MAttNetBackbone=ResNet-101/LSTM2024.0629.04
MAttNetVisual Encoder=RN101, Time (ms)=3202024.0929.04