List your company

Image Annotation on Flickr30k (test)

55.5R@1semantic-enhanced image and sentence matching model
10.36422.08233.845.518Nov 17, 2014May 21, 2015Nov 23, 2015May 27, 2016Nov 29, 2016Jun 3, 2017Dec 6, 2017

Evaluation results

MethodLinks
semantic-enhanced image and sentence matching modelBackbone=ResNet-1522017.1255.589.369.782—
DANBackbone=ResNet-1522017.12558968.981.8—
VSE++Backbone=ResNet-1522017.1252.987.26879.1—
2WayNetBackbone=VGGNet-192017.1249.8——67.5—
RRFBackbone=ResNet-1522017.1247.687.16677.4—
semantic-enhanced image and sentence matching modelBackbone=VGGNet-192017.1244.283.662.374.1—
sm-LSTMensemble=true2016.1142.581.5271.9358.7
sm-LSTMBackbone=VGGNet-192017.1242.581.559.871.9—
sm-LSTM2016.1142.479.9267.5343.4
DANBackbone=VGGNet-192017.1241.482.560.673.5—
VSE++Backbone=VGGNet-192017.1241.377.958.469—
DSPE+FVuses external text corpora=true2016.1140.379.9—68.9351
DSPEBackbone=VGGNet-192017.1240.379.958.568.9—
RTP+FVensemble=true, uses external text corpora=true2016.1137.474.3—63.1326.1
RTPBackbone=VGGNet-192017.1237.474.354.363.1—
m-RNN2016.1135.473.7363.8309.5
m-RNNBackbone=VGGNet-192017.1235.473.751.663.8—
FVensemble=true, uses external text corpora=true2016.113573.8362314.5
FVBackbone=VGGNet-192017.123573.852.462—
RNN+FVuses external text corpora=true2016.1134.772.6362.7320.5
RNN+FVBackbone=VGGNet-192017.1234.772.653.462.7—
VQABackbone=VGGNet-192017.1233.974.552.262.5—
m-CNNensemble=true2016.1133.674.9364.1324.7
m-CNNBackbone=VGGNet-192017.1233.674.954.164.1—
sm-LSTM-ctx2016.1133.570.8360.6300.1
sm-LSTM-att2016.112765.6553.6271.1
sm-LSTM-mean2016.1125.965.4553.1261.5
MNLM2014.1123635——
MNLM2016.112362.9550.7251.9
MNLMBackbone=VGGNet-192017.122362.94250.7—
DVSA (BRNN)2016.1122.261.44.848.2235.2
DVSABackbone=VGGNet-192017.1222.261.439.248.2—
m-RNN2014.11185110——
NIC2014.1117567——
NIC2016.1117567——
DCCA2016.1116.752.9839.3195.5
DeFrag2014.1116558——
Deep Fragment2016.1114.251.31037.7188.4
RVP(T+I)2016.1112.147.81127.8178.4