List your company

Visual Grounding on ReferitGame (test) using Pr@0.5

0.7142Pr@0.5RefTR
0.2660640.3824070.498750.615093Apr 9, 2021Jun 7, 2021Aug 5, 2021Oct 3, 2021Dec 1, 2021Jan 29, 2022Mar 30, 2022

Evaluation results

MethodLinks
RefTRStage=One-stage, Visual Encoder=RN101, Time (ms)=402022.030.7142
TransVGStage=One-stage, Visual Encoder=RN101, Time (ms)=622022.030.7073
SeqTRStage=One-stage, Visual Encoder=DN53, Time (ms)=502022.030.6966
LBYL-NetVisual Encoder=DarkNet-53, Language Encoder=BERT, Processing Stage=One-stage, Time=30 ms2021.040.6747
LBYL-NetVisual Encoder=DarkNet-53, Language Encoder=LSTM, Processing Stage=One-stage, Time=28 ms2021.040.6548
SQC-LargeVisual Encoder=DarkNet-53, Language Encoder=BERT, Processing Stage=One-stage, Time=36 ms2021.040.646
ReSCLStage=One-stage, Visual Encoder=DN53, Time (ms)=362022.030.646
SQC-BaseVisual Encoder=DarkNet-53, Language Encoder=BERT, Processing Stage=One-stage, Time=26 ms2021.040.6433
RCCFVisual Encoder=DLA-34, Language Encoder=LSTM, Processing Stage=One-stage, Time=25 ms2021.040.6379
RCCFStage=One-stage, Visual Encoder=DLA34, Time (ms)=252022.030.6379
DDPN+Visual Encoder=ResNet-101, Language Encoder=LSTM, Processing Stage=Two-stage2021.040.63
DDPNStage=Two-stage, Visual Encoder=RN1012022.030.63
LBYL-Net w/o LFCVisual Encoder=DarkNet-53, Language Encoder=LSTM, Processing Stage=One-stage, Time=25 ms2021.040.6259
FAOAStage=One-stage, Visual Encoder=DN53, Time (ms)=232022.030.6067
YOLO-VGVisual Encoder=DarkNet-53, Language Encoder=BERT, Processing Stage=One-stage, Time=38 ms2021.040.593
BaselineVisual Encoder=DarkNet-53, Language Encoder=LSTM, Processing Stage=One-stage, Time=24 ms2021.040.5928
YOLO-VGVisual Encoder=DarkNet-53, Language Encoder=LSTM, Processing Stage=One-stage, Time=21 ms2021.040.5876
ZSGNetVisual Encoder=ResNet-50, Language Encoder=LSTM, Processing Stage=One-stage, Time=25 ms2021.040.5863
ZSGNetStage=One-stage, Visual Encoder=RN502022.030.5863
CITEVisual Encoder=ResNet-101, Processing Stage=Two-stage, Time=196 ms2021.040.3507
Similarity NetVisual Encoder=ResNet-101, Processing Stage=Two-stage, Time=184 ms2021.040.3454
SimilarityNetStage=Two-stage, Visual Encoder=RN101, Time (ms)=1842022.030.3454
VCVisual Encoder=VGG-16, Language Encoder=LSTM, Processing Stage=Two-stage2021.040.3113
MAttNetVisual Encoder=ResNet-101, Language Encoder=LSTM, Processing Stage=Two-stage, Time=320 ms2021.040.2904
MAttNetStage=Two-stage, Visual Encoder=RN101, Time (ms)=3202022.030.2904
CMNVisual Encoder=VGG-16, Language Encoder=LSTM, Processing Stage=Two-stage2021.040.2833