image description 0.002934536
same image 0.002882155
image descriptions 0.0028217200000000002
image representation 0.002776503
image regions 0.002763142
annotated image 0.002761986
automatic image 0.0027602480000000003
similar image 0.0027375240000000003
image parser 0.0027001100000000004
image structure 0.0026792770000000003
corresponding image 0.0026480930000000002
image retrieval 0.002638299
image descrip 0.002636457
good image 0.0026359570000000004
single image 0.0026181110000000002
structured image 0.002595729
image representa 0.0025883200000000003
image collections 0.002573835
image 0.00235531
model corpus 0.002104674
visual object 0.0020141729999999997
ing model 0.0018434800000000002
visual dependency 0.0017847919999999999
original model 0.0017059520000000002
model structure 0.001690287
model parallel 0.001662447
markov model 0.001609708
corpus information 0.001599175
model outputs 0.0015855840000000001
corpus models 0.0015601529999999999
object region 0.001508213
large data 0.00150774
language models 0.001506768
data set 0.001474351
new data 0.001466231
training data 0.0014548949999999999
annotated data 0.001443096
text corpus 0.001421063
test data 0.001407943
description models 0.001401025
first sentence 0.0013882780000000002
domain data 0.001384721
object regions 0.001372365
annotated object 0.001371209
automatic object 0.001369471
translation sentence 0.001366718
model 0.00136632
second sentence 0.001337956
different models 0.001334181
visual depen 0.0013286169999999998
visual attributes 0.0013139269999999999
sentence template 0.001311281
reference sentence 0.001302639
pascal visual 0.001298706
other models 0.001297472
object labels 0.001290826
our data 0.001289905
data our 0.001289905
data sets 0.0012898879999999999
object recognition 0.001289594
scene description 0.0012844879999999999
sentence fragments 0.001270658
development data 0.0012687129999999999
probable sentence 0.001262616
combined sentence 0.001261373
arate sentence 0.001257918
ond sentence 0.001257219
mulate sentence 0.001257219
sentence fragment 0.001257219
diverse data 0.0012552219999999998
object detection 0.001246383
art object 0.001243338
object classification 0.001226729
evaluation human 0.001219242
action scene 0.0012087769999999999
similar images 0.001208109
object detectors 0.001202369
object proxim 0.001183941
object subtrees 0.001183941
dependency representation 0.001156345
additional information 0.0011548980000000001
feature set 0.0011426510000000002
parallel models 0.001117926
corpus baseline 0.001115284
language generation 0.001114392
region annotation 0.001106409
background scene 0.001085409
structural information 0.00108438
caption generation 0.00106845
scene type 0.001063942
human measures 0.001061661
ation models 0.001052881
dependency representations 0.00105274
visual 0.00104964
sentence 0.00103789
dependency accuracy 0.00102903
dependency grammar 0.00102344
sual dependency 0.00101752
natural language 0.001016287
different action 0.001015897
