PDF Report: Unknown Bigrams

From 4145a02558e33699ca754c143c547cbe68fafa23 Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Fri, 16 Nov 2018 00:49:28 +0100 Subject: bigram, trigram report --- reports/pdf_unknown_bigrams.html | 1 + reports/pdf_unknown_terms.html | 1 + reports/pdf_unknown_trigram.html | 1 + s2-pdf-report.py | 30 +++++++++++++++++++++++++++++- 4 files changed, 32 insertions(+), 1 deletion(-) create mode 100644 reports/pdf_unknown_bigrams.html create mode 100644 reports/pdf_unknown_terms.html create mode 100644 reports/pdf_unknown_trigram.html diff --git a/reports/pdf_unknown_bigrams.html b/reports/pdf_unknown_bigrams.html new file mode 100644 index 00000000..3defaa01 --- /dev/null +++ b/reports/pdf_unknown_bigrams.html @@ -0,0 +1 @@ +PDF Report: Unknown Bigrams

PDF Report: Unknown Bigrams

of the	1433
computer science	1230
of computer	1126
face recognition	970
in the	830
science and	671
facial expression	541
member ieee	538
of technology	501
for the	391
of electrical	384
to the	377
on the	353
for face	344
and technology	323
and computer	317
expression recognition	303
computer engineering	299
beijing china	298
computer vision	291
classi cation	288
of information	277
and engineering	268
facial expressions	259
of engineering	257
by the	249
in this	248
center for	242
carnegie mellon	237
and the	237
mellon university	236
international journal	231
from the	230
hong kong	229
electrical engineering	228
of science	225
electrical and	223
of sciences	222
engineering and	215
has been	210
chinese academy	208
of facial	205
of california	204
of computing	182
is the	178
this paper	176
with the	173
neural networks	167
state university	165
institute for	164
recognition using	162
action recognition	160
open access	158
for facial	156
http www	156
the university	154
pattern recognition	154
and information	153
of this	153
the face	153
face detection	152
national university	147
of face	145
the degree	144
information engineering	139
that the	136
real time	135
information technology	135
senior member	134
ieee and	132
of hong	130
have been	128
the wild	125
this work	124
fellow ieee	124
college london	121
deep learning	118
the chinese	117
the same	116
veri cation	114
face images	114
chinese university	114
convolutional neural	113
doi org	111
neural network	109
in partial	109
student member	108
of maryland	106
identi cation	105
the requirements	104
vision and	104
information science	103
emotion recognition	103
of advanced	102
recognition with	102
science university	101
this article	101
learning for	101
feature extraction	101
large scale	100
the netherlands	99
key laboratory	99
of automation	99
as the	99
of philosophy	97
signal processing	96
at the	94
in computer	94
face alignment	94
engineering university	93
san diego	92
of psychology	92
of chinese	92
college park	91
machine learning	91
imperial college	90
the art	88
research article	88
for action	88
the proposed	86
united kingdom	86
stanford university	85
the most	85
pa usa	84
detection and	84
of human	84
national laboratory	84
we propose	82
recognition and	81
engineering the	81
of electronics	81
ca usa	80
university china	80
age estimation	80
international conference	80
arti cial	80
requirements for	79
dx doi	78
based face	75
science department	75
the original	75
of informatics	74
tsinghua university	74
of pattern	74
centre for	74
new york	74
volume issue	73
partial ful	73
in video	72
expression analysis	72
of electronic	72
the facial	71
face and	71
research center	71
recognition system	71
facial landmark	70
facial action	70
ful llment	70
computer and	69
analysis and	69
key lab	69
face veri	69
for video	68
sciences beijing	68
electronic engineering	68
of our	67
face image	67
microsoft research	67
the image	67
electronics and	67
image processing	67
maryland college	66
networks for	66
model for	66
of texas	65
robust face	65
graduate school	65
method for	64
of intelligent	64
facial feature	64
cial intelligence	64
under the	64
spatio temporal	64
human computer	64
robotics institute	63
information processing	63
the problem	62
as well	62
network for	61
rama chellappa	61
in videos	61
using the	61
university beijing	61
image and	61
that are	61
of these	61
for research	61
in face	60
california san	60
technology and	60
in order	60
technology cas	60
real world	60
for example	60
xiaoou tang	60
stefanos zafeiriou	59
pose estimation	59
for human	59
be addressed	59
there are	59
be used	59
research institute	59
is not	59
of emotion	59
information and	58
of china	58
of singapore	58
ma usa	57
of oxford	57
component analysis	57
of illinois	57
the author	57
and communication	57
ny usa	56
used for	56
they are	56
creative commons	56
the main	55
recognition based	55
advanced technology	55
and recognition	55
of amsterdam	55
low rank	55
semi supervised	54
show that	54
recognition from	54
discriminant analysis	54
an open	54
in any	54
michigan state	54
local binary	54
science engineering	53
to face	53
intelligent systems	53
the data	53
head pose	53
features for	53
ef cient	52
and applications	52
we present	52
massachusetts institute	52
approach for	52
the number	52
support vector	52
peking university	52
the performance	51
object detection	51
assistant professor	51
invariant face	51
engineering department	51
dictionary learning	51
eth zurich	51
shiguang shan	51
for each	50
correspondence should	50
psychology university	50
machine vision	50
the other	50
facial images	49
columbia university	49
facial features	49
urbana champaign	49
action unit	49
of mathematics	49
volume article	49
automation chinese	49
computing and	49
the rst	49
metric learning	49
max planck	48
shenzhen institutes	48
commons attribution	48
of each	48
computer interaction	48
technical university	48
of washington	48
feature selection	47
sparse representation	47
models for	47
and face	47
action units	47
of images	47
of surrey	47
framework for	46
it has	46
for image	46
ieee transactions	46
barcelona spain	46
in which	46
published online	46
human face	46
the training	46
tel aviv	46
available online	45
university pittsburgh	45
technical report	45
dimensionality reduction	45
mathematics and	45
the human	45
laboratory for	45
wang and	45
automatic facial	45
the system	45
that can	45
to this	45
and its	44
of faces	44
maja pantic	44
learning and	44
planck institute	44
for informatics	44
deep neural	44
and video	44
artificial intelligence	44
which are	44
vol issue	44
institute carnegie	44
national institute	44
high dimensional	44
between the	44
to improve	44
cas beijing	44
human action	44
technological university	44
computer applications	44
in addition	43
and research	43
be inserted	43
received date	43
accepted date	43
zhang and	43
images and	43
in real	43
automatic face	43
corresponding author	43
over the	43
and machine	43
the state	42
are not	42
intelligent information	42
accepted for	42
the editor	42
date accepted	42
shuicheng yan	42
is used	42
of pittsburgh	42
for visual	42
nanyang technological	42
visual recognition	42
engineering science	41
fine grained	41
at urbana	41
representation for	41
on image	41
weakly supervised	41
the recognition	41
image analysis	41
tokyo japan	41
and facial	41
and security	41
speech and	41
and signal	41
low resolution	41
andrew zisserman	40
jeffrey cohn	40
the following	40
of southern	40
southern california	40
this material	40
issn online	40
anil jain	40
recognition systems	40
the creative	40
do not	40
our method	40
features and	40
associated with	40
computing technology	40
singapore singapore	40
indian institute	39
rights reserved	39
an image	39
of london	39
de ned	39
university college	39
nanjing university	38
of new	38
and computing	38
eurasip journal	38
active appearance	38
rutgers university	38
to cite	38
provided the	38
pose and	38
the visual	38
to recognize	38
in many	38
system for	38
data and	38
super resolution	38
engineering national	38
of central	38
activity recognition	38
electrical computer	37
multi task	37
the first	37
shanghai china	37
image retrieval	37
van gool	37
cite this	37
experimental results	37
of image	37
analysis for	37
information sciences	37
all rights	37
xilin chen	37
recognition under	37
the authors	37
north carolina	37
video based	37
and electronic	37
we are	37
cornell university	36
australian national	36
of thessaloniki	36
is that	36
luc van	36
deep convolutional	36
object recognition	36
binary pattern	36
to extract	36
united states	36
domain adaptation	36
to learn	36
university usa	36
from video	36
software engineering	35
supervised learning	35
and pattern	35
cation using	35
by using	35
facial emotion	35
or not	35
is one	35
the use	35
unconstrained face	35
the user	35
is also	35
all the	35
based methods	35
from face	35
when the	35
for robust	35
processing and	35
improve the	35
of cse	35
is available	35
queen mary	35
li and	35
of applied	35
systems and	35
central florida	35
state key	35
we use	35
to make	34
the model	34
published version	34
landmark localization	34
access article	34
distributed under	34
distribution and	34
original work	34
kristen grauman	34
for this	34
of data	34
the last	34
of social	34
we also	34
on computer	34
on facial	34
thesis submitted	34
of all	33
polytechnic institute	33
using deep	33
the work	33
pose invariant	33
and systems	33
algorithm for	33
md usa	33
model based	33
to achieve	33
to solve	33
affective computing	33
training data	33
and image	33
research and	33
on face	33
at austin	33
stony brook	33
california berkeley	33
where the	33
of tokyo	33
communication engineering	33
taipei taiwan	33
linear discriminant	33
tehran iran	33
aviv university	33
cation and	33
subspace clustering	32
for automation	32
principal component	32
la torre	32
at http	32
the department	32
https doi	32
to facial	32
appearance models	32
the video	32
the best	32
permits unrestricted	32
is properly	32
of features	32
the feature	32
the results	32
polytechnic university	32
and then	32
technische universit	32
facial image	32
an important	32
liu and	32
technology sydney	32
at unchen	32
of north	32
gesture recognition	32
th international	32
video classi	31
automation research	31
people with	31
the shape	31
the paper	31
aristotle university	31
thessaloniki greece	31
this version	31
deep face	31
detection using	31
of michigan	31
the images	31
and intelligent	31
the accuracy	31
dr ing	31
for vision	31
mary university	31
in our	31
fraser university	31
in figure	31
in social	31
machine intelligence	31
of posts	31
posts and	31
been accepted	31
we will	31
facial landmarks	31
of toronto	30
computer sciences	30
vision lab	30
in facial	30
zhen lei	30
not the	30
nanjing china	30
article distributed	30
unrestricted use	30
any medium	30
medium provided	30
jiaotong university	30
engineering research	30
illumination and	30
of oulu	30
into the	30
of research	30
during the	30
vector machine	30
simon fraser	30
the development	30
chen and	30
as follows	30
google research	30
learning based	30
signi cant	30
at www	29
information systems	29
in unconstrained	29
from facial	29
images with	29
come from	29
which permits	29
use distribution	29
and reproduction	29
classi ers	29
recent years	29
the computer	29
and their	29
biometrics and	29
academic editor	29
learning with	29
proposed method	29
in human	29
amsterdam the	29
methods for	29
the scene	29
human robot	29
national taiwan	29
shanghai jiao	29
jiao tong	29
of nottingham	28
information about	28
we show	28
of twente	28
thomas huang	28
landmark detection	28
zero shot	28
vision center	28
representations for	28
of massachusetts	28
for learning	28
to detect	28
shenzhen key	28
of visual	28
attribution license	28
transfer learning	28
robust facial	28
xiaogang wang	28
technology chinese	28
engineering college	28
electronic and	28
ku leuven	28
for large	28
cordelia schmid	28
use the	28
taiwan university	28
east lansing	28
tong university	28
and telecommunications	28
dissertation submitted	28
and peter	28
tx usa	27
please contact	27
material for	27
downloaded from	27
noname manuscript	27
georgia institute	27
images for	27
more information	27
learning from	27
and david	27
face analysis	27
id pages	27
of software	27
properly cited	27
of different	27
been proposed	27
ef icient	27
of pennsylvania	27
gender classi	27
and pose	27
in particular	27
west virginia	27
seoul korea	27
of deep	27
this chapter	27
on intelligent	27
of ece	27
normal university	27
for all	27
generative adversarial	27
intelligence and	27
we can	27
and software	26
yu qiao	26
to identify	26
the open	26
in other	26
nd the	26
signi cantly	26
and expression	26
whether they	26
teaching and	26
limin wang	26
of doctor	26
features are	26
research group	26
in image	26
we have	26
recognition has	26
the local	26
face representation	26
to end	26
which can	26
multi view	26
xiaoming liu	26
this study	26
human faces	26
issn print	26
expression and	26
of cambridge	26
shape and	26
however the	26
sun yat	26
yat sen	26
zurich switzerland	26
does not	26
optical flow	26
china university	26
pattern analysis	26
the past	26
massachusetts amherst	26
istanbul turkey	26
robotics and	26
the object	26
if the	26
this problem	25
rensselaer polytechnic	25
appearance based	25
of emotional	25
peer reviewed	25
personal use	25
no august	25
de lausanne	25
video processing	25
for more	25
is multi	25
ann arbor	25
are the	25
nicu sebe	25
our approach	25
to build	25
to obtain	25
oulu finland	25
for biometrics	25
latex class	25
class files	25
extracted from	25
it can	25
than the	25
la jolla	25
recognition via	25
local features	25
of objects	25
engineering technology	25
images are	25
chen change	25
change loy	25
research portal	25
lei zhang	25
the hong	25
kong polytechnic	25
university singapore	25
lior wolf	25
zhejiang university	25
algorithms for	24
science the	24
of people	24
the full	24
and rama	24
video and	24
and tracking	24
to publication	24
this document	24
from public	24
dataset for	24
ecole polytechnique	24
and dissemination	24
the documents	24
may come	24
or from	24
of interest	24
system and	24
the robotics	24
hindawi publishing	24
publishing corporation	24
the two	24
conference paper	24
visual attributes	24
security research	24
face reconstruction	24
applied sciences	24
of automatic	24
of training	24
the journal	24
on automatic	24
sen university	24
recognition for	24
of video	24
correspondence tel	24
the task	24
the identity	24
the input	24
of any	24
in section	24
michigan ann	24
of computational	24
of latex	24
to have	24
of statistics	24
and cognitive	24
this journal	24
for computer	24
and low	23
and are	23
open university	23
and gender	23
images using	23
based facial	23
and ioannis	23
the published	23
if you	23
dimitris metaxas	23
ieee international	23
multi disciplinary	23
disciplinary open	23
rchive for	23
the deposit	23
deposit and	23
of sci	23
research documents	23
documents whether	23
are pub	23
documents may	23
research institutions	23
in france	23
or private	23
private research	23
research centers	23
archive ouverte	23
ouverte pluridisciplinaire	23
pluridisciplinaire hal	23
hal est	23
la diffusion	23
de documents	23
de niveau	23
niveau recherche	23
recherche publi	23
ou non	23
recherche fran	23
des laboratoires	23
ou priv	23
recognition algorithms	23
in terms	23
tel fax	23
through the	23
al this	23
the high	23
for age	23
delhi india	23
is more	23
single image	23
key words	23
files vol	23
unsupervised learning	23
the current	23
the ability	23
sciences cas	23
of them	23
vision speech	23
feature based	23
large number	23
ground truth	23
beijing university	23
each other	23
virginia university	23
adobe research	23
of machine	23
machine perception	23
face hallucination	23
not been	23
these methods	23
differences between	23
and robotics	23
decision making	23
josef kittler	23
speci cally	23
arizona state	23
for publication	23
for object	22
vishal patel	22
tal hassner	22
research online	22
for pose	22
was submitted	22
action localization	22
electronics engineering	22
on artificial	22
extraction and	22
research asia	22
as conference	22
at iclr	22
illumination invariant	22
under varying	22
for real	22
vision group	22
research national	22
regression for	22
ai research	22
article was	22
www frontiersin	22
frontiersin org	22
the research	22
and illumination	22
expressions and	22
for recognition	22
is very	22
of two	22
international joint	22
guangzhou china	22
and social	22
for information	22
brook university	22
received march	22
for machine	22
tracking and	22
methods have	22
devi parikh	22
detection with	22
south china	22
cation with	22
and electronics	22
on machine	22
los angeles	22
notre dame	22
still images	22
california institute	22
natural language	22
such that	22
brain science	22
in recent	22
and vision	22
to determine	22
for instance	21
matrix factorization	21
of defense	21
works for	21
adversarial networks	21
harbin institute	21
learned miller	21
the second	21
cas china	21
kong china	21
institute university	21
ibm watson	21
recognition rate	21
binary patterns	21
and local	21
while the	21
and analysis	21
original research	21
of emotions	21
data for	21
idiap research	21
expressions are	21
studies have	21
and other	21
an efficient	21
low dimensional	21
for intelligent	21
dacheng tao	21
about the	21
technology beijing	21
and electrical	21
and anil	21
reduce the	21
is still	21
georgios tzimiropoulos	21
using local	21
with deep	21
of trento	21
on pattern	21
the dataset	21
paris france	21
computational intelligence	21
and human	21
perception and	21
visual geometry	21
geometry group	21
event detection	21
data points	21
article has	21
northeastern university	21
the method	21
university nanjing	20
new jersey	20
to address	20

\ No newline at end of file diff --git a/reports/pdf_unknown_terms.html b/reports/pdf_unknown_terms.html new file mode 100644 index 00000000..da701f81 --- /dev/null +++ b/reports/pdf_unknown_terms.html @@ -0,0 +1 @@ +PDF Report: Unknown Terms

PDF Report: Unknown Terms

the	10321
and	9825
university	5067
for	4495
face	2875
recognition	2650
computer	2272
science	1886
facial	1876
department	1846
engineering	1688
with	1589
this	1382
research	1355
technology	1351
from	1280
that	1229
are	1164
institute	1133
based	1112
learning	1085
information	1063
using	1054
image	1039
china	966
ieee	925
expression	826
usa	773
images	733
video	722
school	711
human	676
analysis	647
feature	622
detection	612
data	611
which	558
member	552
vision	549
deep	547
features	545
cation	538
journal	536
college	529
electrical	523
can	520
model	501
action	490
systems	484
sciences	482
wang	481
has	477
system	462
have	457
visual	444
such	444
center	439
expressions	424
international	415
national	415
http	412
zhang	411
our	406
faces	405
processing	394
beijing	393
these	389
not	388
neural	383
been	383
computing	380
article	379
doi	375
classi	374
laboratory	374
chen	367
method	364
www	362
paper	361
state	358
one	356
may	355
networks	354
india	353
object	343
applications	343
local	343
emotion	342
new	340
pose	340
methods	335
more	333
chinese	329
liu	327
used	327
accepted	327
work	324
pattern	321
machine	318
california	317
published	317
social	316
representation	315
use	305
two	302
approach	301
multi	297
lab	294
robust	294
received	293
different	292
yang	291
each	290
network	288
problem	288
under	286
high	286
time	285
hong	284
other	284
models	282
illumination	280
videos	274
training	270
performance	270
estimation	263
dept	262
real	262
large	258
group	257
automatic	254
all	254
key	254
org	251
age	251
low	247
issn	246
results	246
person	244
set	243
london	243
online	242
dataset	242
vol	239
carnegie	238
mellon	238
email	238
kong	238
open	236
academy	232
their	231
algorithm	231
introduction	230
access	228
proposed	228
via	226
faculty	226
temporal	225
shape	223
intelligent	217
part	215
between	213
its	212
submitted	212
intelligence	212
also	212
conference	211
most	208
when	206
was	205
mail	205
sparse	202
number	202
com	201
supervised	199
will	199
matrix	199
author	198
database	198
many	198
france	197
convolutional	195
however	195
volume	194
available	193
pittsburgh	191
appearance	191
germany	191
universit	190
people	190
issue	189
into	189
where	189
linear	189
singapore	188
advanced	187
task	187
algorithms	184
non	184
scale	184
clustering	183
informatics	183
motion	178
interaction	178
space	175
alignment	174
class	174
huang	173
but	172
japan	172
classification	172
tracking	171
psychology	171
study	170
level	169
degree	169
they	168
student	168
emotional	168
subspace	167
version	167
techniques	167
professor	166
attribute	165
how	165
some	165
than	163
extraction	162
attributes	160
regression	160
any	158
there	158
park	157
vector	155
robotics	153
electronics	153
copyright	153
figure	152
security	152
only	151
signal	151
automation	150
identity	150
june	149
multiple	149
single	148
tel	147
correspondence	147
then	147
emotions	147
well	147
communication	146
accuracy	146
senior	145
date	145
over	145
framework	144
localization	143
partial	143
biometric	143
wei	143
were	143
novel	142
sun	142
yan	142
objects	141
both	141
given	141
while	141
same	140
thesis	140
requirements	140
applied	140
australia	139
dynamic	139
approaches	138
datasets	137
recent	136
lin	136
understanding	136
david	135
electronic	135
computational	135
resolution	134
content	133
perception	133
publication	133
fellow	133
important	133
wild	132
section	132
matching	131
prof	130
view	130
san	130
activity	130
united	129
dimensional	129
application	128
active	128
cas	128
edu	127
august	127
keywords	127
hal	127
identi	127
zhao	126
domain	126
joint	125
veri	125
centre	125
technical	124
like	124
review	124
shenzhen	124
biometrics	124
eye	123
media	122
through	122
unsupervised	122
netherlands	122
discriminant	122
canada	121
september	121
landmark	120
about	120
first	120
natural	120
brain	120
texture	119
should	119
april	119
cambridge	118
head	118
representations	118
problems	118
unconstrained	117
selection	117
inc	117
gender	117
des	117
zhou	116
example	116
modeling	116
original	116
maryland	115
scene	115
italy	114
general	114
korea	114
you	114
invariant	114
order	114
technologies	113
search	113
michael	113
studies	113
ing	113
very	113
user	112
distribution	111
cross	111
input	111
component	111
show	111
rank	111
december	111
conditions	111
variations	111
still	111
july	110
zhu	110
cognitive	110
march	110
graduate	109
lee	108
mathematics	108
spain	108
label	108
world	108
art	107
multimedia	107
context	107
because	107
points	107
binary	107
due	107
several	107
software	106
propose	106
shown	106
works	106
dictionary	106
present	106
discriminative	106
tech	105
york	105
dissertation	105
switzerland	104
retrieval	104
https	104
kim	104
cnn	103
optimization	103
philosophy	103
attention	103
report	102
prediction	102
proceedings	102
january	101
control	101
process	100
including	100
doctor	100
berkeley	99
speci	99
stanford	99
amsterdam	99
surveillance	98
oxford	98
semantic	98
authors	98
affective	98
editor	97
digital	97
der	97
peter	97
three	97
see	97
distance	97
corresponding	96
during	96
diego	96
language	96
ali	96
behavior	96
hand	96
taiwan	96
sample	95
kernel	95
tang	95
andrew	94
van	94
imaging	94
actions	94
related	94
thomas	94
rights	94
evaluation	94
color	94
box	94
form	94
revised	94
lighting	93
cial	93
microsoft	93
imperial	92
terms	92
february	92
shanghai	91
reconstruction	91
similarity	91
global	91
embedding	91
various	91
provided	90
cheng	90
michigan	90
graph	90
rst	90
october	90
fast	89
role	89
manuscript	89
barcelona	89
even	89
changes	89
automated	89
november	88
feng	88
project	88
massachusetts	88
tsinghua	88
occlusion	88
univ	88
region	88
coding	88
google	87
without	87
experimental	87
kumar	87
what	87
kingdom	87
personal	86
structure	86
camera	86
gao	86
material	86
current	86
presented	86
design	86
humans	86
frame	86
function	86
make	85
tion	85
please	85
public	85
towards	85
those	85
pca	85
tokyo	85
jun	85
survey	84
wen	84
made	84
provide	84
web	84
development	84
them	84
metric	83
citation	82
gabor	82
unit	82
event	82
peng	82
main	82
ful	82
arti	82
washington	82
texas	81
dong	81
lei	81
patterns	81
interactions	81
known	80
central	80
robot	80
speech	80
long	80
cient	79
transactions	79
end	79
parts	79
test	79
fusion	79
descriptors	78
obtained	78
recognizing	78
dimensionality	78
learned	78
subject	78
support	77
components	77
israel	77
limited	77
rate	77
years	77
learn	77
shan	77
semi	76
identification	76
across	76
whether	75
way	75
further	75
challenge	75
florida	75
song	75
statistics	75
manifold	75
segmentation	75
chang	74
zafeiriou	74
spatial	74
improved	74
static	74
samples	74
databases	74
states	74
nanjing	73
polytechnic	73
adversarial	73
knowledge	73
documents	73
zheng	73
often	73
mobile	72
medical	72
point	72
tasks	72
improve	72
areas	72
per	71
self	71
thessaloniki	71
out	71
commons	71
compared	71
higher	71
quality	71
landmarks	71
xiang	70
challenging	70
result	70
stefanos	70
gaze	70
singh	70
llment	70
similar	70
svm	70
eecs	69
chellappa	69
address	69
found	69
simon	69
max	69
generative	69
zhen	69
shen	69
machines	69
alexander	69
since	69
basis	69
future	69
better	68
multimodal	68
cohn	68
final	68
transfer	68
labeling	68
improving	68
grenoble	68
relative	68
technique	68
independent	68
loss	68
change	68
iran	68
recognize	68
shi	68
objective	68
jda	68
fig	67
ming	67
hua	67
jia	67
interest	67
best	67
creative	67
accurate	67
spatio	67
could	67
must	66
illinois	66
urbana	66
reduction	66
jain	66
hierarchical	66
guo	66
experiments	66
decision	66
potential	66
south	66
differences	66
complex	65
rama	65
photo	65
distributed	65
additional	65
signi	65
addressed	65
technological	65
prior	65
con	65
disgust	65
small	65
within	65
sequence	65
annotation	64
participants	64
assistant	64
contact	64
mit	64
han	64
zurich	64
possible	64
neutral	64
cost	64
tao	64
full	63
regions	63
jiang	63
thus	63
etc	63
therefore	63
virginia	63
inria	62
reference	62
effective	62
daniel	62
solution	62
examples	62
eth	62
liang	62
mohammad	62
classes	62
cse	62
target	62
queen	62
comparison	61
correlation	61
previous	61
negative	61
link	61
austin	61
sydney	61
performed	61
geometric	61
road	61
random	61
recently	61
columbia	60
fine	60
grained	60
pantic	60
impact	60
existing	60
xiaoou	60
units	60
jean	60
labeled	60
categories	60
layer	60
surrey	60
eld	60
pages	59
top	59
preserving	59
few	59
recherche	59
among	59
academic	59
license	59
light	59
feedback	59
aware	59
simple	59
basic	59
detecting	59
individual	59
extract	59
parameters	59
labels	59
here	59
turkey	59
making	59
street	58
projection	58
need	58
james	58
luc	58
springer	58
artificial	58
lda	58
efficient	58
geometry	58
authentication	57
details	57
greece	57
document	57
net	57
frames	57
fei	57
much	57
campus	57
neuroscience	57
subjects	57
adaptation	57
following	56
fully	56
master	56
variation	56
eyes	56
fisher	56
area	56
martin	56
malaysia	56
individuals	56
tan	56
detector	56
others	55
labs	55
second	55
cvpr	55
extracted	55
generation	55
last	55
pre	55
specific	55
nanyang	55
north	55
synthesis	55
principal	54
jeffrey	54
program	54
environment	54
include	54
computation	54
anil	54
memory	54
adaptive	54
useful	54
pairs	54
structured	54
super	54
cues	54
cornell	53
photos	53
common	53
sets	53
step	53
management	53
institutes	53
sequences	53
karlsruhe	53
ability	53
factors	53
luo	53
range	53
size	53
west	53
phase	53
weakly	52
statistical	52
cnrs	52
description	52
instance	52
users	52
reviewed	52
stage	52
inference	52
xin	52
detect	52
words	52
east	52
encoding	52
developed	52
education	52
being	52
stimuli	52
associated	52
life	52
optimal	52
peking	52
term	52
zisserman	51
text	51
pennsylvania	51
boston	51
australian	51
ioannis	51
peer	51
normalization	51
signals	51
amherst	51
attribution	51
response	51
output	51
less	51
according	51
edited	51
shiguang	51
responses	51
sensetime	51
positive	51
pro	51
sensors	51
effect	50
facebook	50
error	50
frontal	50
champaign	50
cite	50
fax	50
brazil	50
constraints	50
intensity	50
vectors	50
particular	50
publications	50
colorado	50
trained	49
rutgers	49
fernando	49
hybrid	49
challenges	49
template	49
shot	49
dense	49
descriptor	49
lausanne	49
cao	49
qiang	49
tong	49
finland	49
does	49
william	49
ekman	49
latent	49
committee	49
istanbul	49
patients	49
exploiting	48
jie	48
service	48
shows	48
benchmark	48
planck	48
gang	48
free	48
indian	48
norm	48
deng	48
sci	48
source	48
publishing	48
medicine	48
researchers	48
category	48
demonstrate	48
noise	48
ased	48
mark	48
uses	48
seoul	48
gesture	48
ned	48
weighted	48
und	48
ibm	47
city	47
cmu	47
constrained	47
would	47
business	47
describe	47
yuan	47
ranking	47
theory	47
wide	47
optical	47
ltd	47
paris	47
aviv	47
addition	46
good	46
publisher	46
paul	46
jian	46
affect	46
varying	46
aging	46
who	46
behavioral	46
automatically	46
case	46
map	46
theses	46
facs	46
toronto	45
skin	45
generated	45
perceptual	45
evidence	45
bristol	45
above	45
interactive	45
george	45
scienti	45
focus	45
means	45
bayesian	45
tian	45
probabilistic	45
stan	45
condition	45
perform	45
leuven	45
especially	45
body	45
lower	45
ping	45
major	45
print	45
scenarios	45
short	45
ece	45
after	45
avenue	45

\ No newline at end of file diff --git a/reports/pdf_unknown_trigram.html b/reports/pdf_unknown_trigram.html new file mode 100644 index 00000000..7dd4ed03 --- /dev/null +++ b/reports/pdf_unknown_trigram.html @@ -0,0 +1 @@ +PDF Report: Unknown Trigrams

PDF Report: Unknown Trigrams

of computer science	856
department of computer	631
computer science and	396
institute of technology	278
department of electrical	243
science and engineering	243
science and technology	240
carnegie mellon university	235
facial expression recognition	225
academy of sciences	212
university of california	202
school of computer	196
university of technology	191
of electrical and	178
for face recognition	166
and computer engineering	160
of electrical engineering	157
electrical and computer	155
of science and	137
for the degree	135
senior member ieee	133
of hong kong	130
university of hong	129
member ieee and	123
in the wild	123
the chinese university	112
student member ieee	108
university of maryland	104
and computer science	103
in this paper	102
department of information	96
of the requirements	94
doctor of philosophy	94
university of science	91
of chinese academy	91
journal of computer	89
state of the	88
imperial college london	84
of the art	83
of computer engineering	78
dx doi org	78
engineering and computer	76
requirements for the	76
http dx doi	75
of engineering and	74
of information engineering	74
one of the	73
in partial ful	73
electrical engineering and	72
department of psychology	71
college of engineering	71
computer science university	70
computer science department	70
proceedings of the	70
face veri cation	69
partial ful llment	69
dept of computer	68
of sciences beijing	67
of information science	67
of maryland college	66
maryland college park	66
sciences beijing china	65
institute of automation	64
engineering the chinese	64
face recognition using	64
pittsburgh pa usa	63
university of texas	63
laboratory of pattern	63
arti cial intelligence	63
computer vision and	63
department of computing	62
of pattern recognition	62
for action recognition	62
the requirements for	61
of information technology	61
submitted in partial	61
university of chinese	61
of california san	60
california san diego	60
for facial expression	60
school of information	60
facial expression analysis	59
university of singapore	58
should be addressed	57
university of oxford	56
university of illinois	56
convolutional neural networks	56
university beijing china	55
and information engineering	54
information engineering the	54
school of electrical	53
university of amsterdam	53
llment of the	52
michigan state university	52
of facial expressions	52
based on the	51
of advanced technology	49
of automation chinese	49
automation chinese academy	49
expression recognition using	48
institutes of advanced	48
of electronics and	48
information science and	48
school of computing	47
university of washington	47
college of computer	46
human computer interaction	46
university of surrey	46
mellon university pittsburgh	45
creative commons attribution	45
center for research	45
max planck institute	44
computer science engineering	44
institute carnegie mellon	44
cas beijing china	44
in computer vision	44
planck institute for	43
department of informatics	43
institute of computing	43
convolutional neural network	43
will be inserted	42
inserted by the	42
by the editor	42
received date accepted	42
date accepted date	42
university of pittsburgh	42
department of engineering	42
engineering and technology	41
of computer and	41
faculty of electrical	41
of face recognition	41
of psychology university	41
of the face	41
faculty of engineering	41
of computer applications	41
illinois at urbana	40
at urbana champaign	40
of intelligent information	40
university of southern	40
of southern california	40
robotics institute carnegie	40
institute for informatics	39
invariant face recognition	39
face recognition with	39
based face recognition	39
of engineering science	38
of this work	38
submitted to the	38
department of electronics	38
institute of science	38
of computing technology	38
university of london	38
nanyang technological university	38
lab of intelligent	37
institute of information	37
is an open	37
an open access	37
the creative commons	37
all rights reserved	37
university of central	37
australian national university	36
intelligent information processing	36
university of thessaloniki	36
robust face recognition	36
luc van gool	36
of the most	36
technology of china	35
science and information	35
of information and	35
department of electronic	35
department of mathematics	35
cambridge ma usa	34
face recognition system	34
open access article	34
the original work	34
and signal processing	34
automatic facial expression	34
of central florida	34
face detection and	33
and pattern recognition	33
facial action unit	33
to cite this	33
provided the original	33
and information technology	33
journal of engineering	33
computing technology cas	33
texas at austin	33
university of tokyo	33
university college london	33
tel aviv university	33
journal of advanced	32
de la torre	32
https doi org	32
master of science	32
work is properly	32
due to the	32
technology cas beijing	32
speech and signal	32
of electronic engineering	32
deep neural networks	32
university of north	32
video classi cation	31
center for automation	31
for automation research	31
in face recognition	31
university of michigan	31
under the creative	31
reproduction in any	31
queen mary university	31
of technology sydney	31
of california berkeley	31
universit at unchen	31
university of posts	31
of posts and	31
has been accepted	31
been accepted for	31
university of toronto	30
tsinghua university beijing	30
access article distributed	30
article distributed under	30
distributed under the	30
permits unrestricted use	30
in any medium	30
any medium provided	30
medium provided the	30
university of oulu	30
simon fraser university	30
and electronic engineering	30
of north carolina	30
of electrical computer	29
electrical computer engineering	29
school of engineering	29
which permits unrestricted	29
unrestricted use distribution	29
use distribution and	29
distribution and reproduction	29
dept of electrical	29
recognition in the	29
it has been	29
shanghai jiao tong	29
computer and information	29
th international conference	29
university of nottingham	28
computer vision center	28
image and video	28
processing of chinese	28
support vector machine	28
technology chinese academy	28
amsterdam the netherlands	28
head pose estimation	28
national taiwan university	28
jiao tong university	28
recognition of facial	28
online at www	27
university of twente	27
in computer science	27
university of massachusetts	27
article id pages	27
commons attribution license	27
is properly cited	27
can be used	27
part of the	27
face recognition under	27
electrical and electronic	27
computer vision lab	26
mathematics and computer	26
faces in the	26
of facial expression	26
image processing and	26
gender classi cation	26
university of cambridge	26
sun yat sen	26
of singapore singapore	26
and communication engineering	26
of massachusetts amherst	26
posts and telecommunications	26
principal component analysis	25
pose invariant face	25
journal on image	25
end to end	25
biometrics and security	25
latex class files	25
research in computer	25
chen change loy	25
state key laboratory	25
rensselaer polytechnic institute	24
and rama chellappa	24
active appearance models	24
whether they are	24
may come from	24
shenzhen key lab	24
of computer vision	24
in this work	24
center for biometrics	24
for biometrics and	24
and security research	24
yat sen university	24
the hong kong	24
hong kong polytechnic	24
of michigan ann	24
journal of latex	24
of latex class	24
computer science the	23
of mathematics and	23
cite this version	23
hal is multi	23
is multi disciplinary	23
multi disciplinary open	23
disciplinary open access	23
rchive for the	23
for the deposit	23
the deposit and	23
deposit and dissemination	23
dissemination of sci	23
research documents whether	23
documents whether they	23
they are pub	23
lished or not	23
or not the	23
not the documents	23
the documents may	23
documents may come	23
teaching and research	23
and research institutions	23
institutions in france	23
broad or from	23
or from public	23
public or private	23
or private research	23
private research centers	23
archive ouverte pluridisciplinaire	23
ouverte pluridisciplinaire hal	23
pluridisciplinaire hal est	23
et la diffusion	23
diffusion de documents	23
de niveau recherche	23
niveau recherche publi	23
publics ou priv	23
the robotics institute	23
and intelligent systems	23
hindawi publishing corporation	23
et al this	23
have been proposed	23
of oulu finland	23
class files vol	23
university of pennsylvania	23
for vision speech	23
vision speech and	23
advanced technology chinese	23
of electronic and	23
west virginia university	23
such as the	23
for face detection	23
michigan ann arbor	23
science and software	22
and software engineering	22
university of new	22
neural networks for	22
facial landmark detection	22
microsoft research asia	22
as conference paper	22
paper at iclr	22
paper we propose	22
face recognition based	22
security research national	22
research national laboratory	22
facial emotion recognition	22
to improve the	22
this article was	22
www frontiersin org	22
of sciences cas	22
human action recognition	22
the proposed method	22
school of electronic	22
stony brook university	22
facial landmark localization	22
kong polytechnic university	22
department of statistics	22
link to publication	21
institute of engineering	21
deep convolutional neural	21
hong kong china	21
local binary pattern	21
idiap research institute	21
centre for vision	21
on artificial intelligence	21
engineering national university	21
and engineering university	21
technological university singapore	21
university of trento	21
pattern analysis and	21
and machine intelligence	21
degree of doctor	21
visual geometry group	21
linear discriminant analysis	21
this article has	21
article has been	21
accepted for publication	21
research center for	20
some of the	20
conference on artificial	20
springer science business	20
science business media	20
of sciences china	20
from face images	20
in real time	20
of the twenty	20
international joint conference	20
center for machine	20
and anil jain	20
for large scale	20
neural network for	20
on automatic face	20
in recent years	20
arizona state university	20
in future issue	20
issue of this	20
of this journal	20
the open university	19
university of bristol	19
ming hsuan yang	19
use of this	19
of this material	19
material is permitted	19
servers or lists	19
in partial fulfillment	19
vol no august	19
erik learned miller	19
advanced technology cas	19
vision and pattern	19
local binary patterns	19
xi an china	19
facebook ai research	19
prof dr ing	19
face identi cation	19
show that the	19
face recognition via	19
eth zurich switzerland	19
and electrical engineering	19
classi cation using	19
ieee international conference	19
and computer vision	19
on pattern analysis	19
analysis and machine	19
of the same	19
research on intelligent	19
on intelligent perception	19
intelligent perception and	19
perception and computing	19
journal of information	19
face recognition and	18
uc san diego	18
follow this and	18
this and additional	18
and additional works	18
accepted for inclusion	18
terms of use	18
this material for	18
material for advertising	18
redistribution to servers	18
johns hopkins university	18
laboratory of intelligent	18
for face veri	18
university nanjing china	18
face recognition systems	18
this is the	18
recognition in videos	18
image classi cation	18
and xiaoou tang	18
of pittsburgh pittsburgh	18
expression recognition with	18
analysis of facial	18
for face alignment	18
article was submitted	18
faculty of computer	18
face recognition from	18
computer engineering national	18
electrical engineering university	18
video based face	18
department of automation	18
on computer vision	18
action unit detection	18
university of wollongong	18
conference on automatic	18
university shanghai china	17
brought to you	17
to you for	17
you for free	17
for free and	17
free and open	17
and open access	17
ieee personal use	17
http hdl handle	17
hdl handle net	17
computer vision laboratory	17
fulfillment of the	17
li fei fei	17
information and communication	17
on image and	17
we propose novel	17
expression recognition based	17
technology cas china	17
and mobile computing	17
college of information	17
results show that	17
real time face	17
of computing and	17
haz kemal ekenel	17
universit degli studi	17
to this work	17
dept of cse	17
of the university	17
hong kong hong	17
conference on computer	17
electronics and communication	17
university of york	17
new collective works	17
collective works for	17
transactions on pattern	17
of engineering technology	17
to whom correspondence	17
section of the	17
center for excellence	17
excellence in brain	17
science and intelligence	17
and intelligence technology	17
and information sciences	17
ieee th international	17
frontiers in psychology	17
has not been	17
shih fu chang	16
semi supervised learning	16
and maja pantic	16
works at http	16
by an authorized	16
in accordance with	16
in other works	16
deep face recognition	16
computer engineering department	16
and video processing	16
for more information	16
novel software technology	16
for arti cial	16
most of the	16
science and mobile	16
real world applications	16
face recognition has	16
expression recognition and	16
zhang member ieee	16
university of rochester	16
of new york	16
is an important	16
kong hong kong	16
wang member ieee	16
for machine vision	16
of computing imperial	16
computing imperial college	16
electronic and information	16
classi cation with	16
university hong kong	16
state university east	16
university east lansing	16
whom correspondence should	16
university istanbul turkey	16
classi cation and	16
based on facial	16
in brain science	16
brain science and	16
facial action units	16
department of cse	16
university of colorado	16
institute of computer	16
south china university	16
louis philippe morency	16
publication in future	16
this journal but	16
journal but has	16
but has not	16
not been fully	16
been fully edited	16
fully edited content	16
edited content may	16
content may change	16
may change prior	16
prior to final	16
to final publication	16
and computer sciences	15
california at berkeley	15
http www eecs	15
texas at arlington	15
science the university	15
of the facial	15
access by the	15
an authorized administrator	15
creating new collective	15
application to face	15
university of defense	15
face recognition algorithms	15
www intechopen com	15
key laboratory for	15
laboratory for novel	15
for novel software	15
university of queensland	15
feature extraction and	15
of advanced computer	15
the fact that	15
for real time	15
and facial expression	15
of the data	15
of the journal	15
of the main	15
on the other	15
the other hand	15
this work was	15
computer engineering university	15
of california riverside	15
in this chapter	15
and machine learning	15
department of ece	15
expressions of emotion	15
conference on machine	15
dept of computing	15
university of notre	15
of notre dame	15
sensetime group limited	15
authors contributed equally	15
for zero shot	15
et al and	15
robotics and intelligent	15
re identi cation	15
on arti cial	15
rio de janeiro	15
politehnica of bucharest	15
tadas baltru saitis	15
automatic face gesture	15
face gesture recognition	15
houston tx usa	14
university of israel	14
performance of face	14
based facial expression	14
yu gang jiang	14
detection and tracking	14
advertising or promotional	14
work in other	14
must be obtained	14
to facial expression	14
university of barcelona	14
to face recognition	14
of defense technology	14
pattern recognition casia	14
anil jain fellow	14
jain fellow ieee	14
et al eurasip	14
al eurasip journal	14
engineering and information	14
advanced computer science	14
watson research center	14
detection and recognition	14
pattern recognition institute	14
int comput vis	14
electronics and information	14
university of edinburgh	14
support vector machines	14
issn volume issue	14
faculty of information	14
equally to this	14
of this paper	14
submitted for the	14
in this study	14
university of kentucky	14
video face recognition	14
of technology beijing	14
islamic azad university	14
university of houston	14
in the context	14
for visual recognition	14
computer vision group	14
polytechnic university hong	14
faculty of science	14
university of ljubljana	14
these authors contributed	14
to deal with	14
for classi cation	14
forbes ave pittsburgh	14
heterogeneous face recognition	14
of computing science	14
brain and cognitive	14
unconstrained face recognition	14
seoul national university	14
electrical and electronics	14
component of this	14
of arti cial	14
department of psychiatry	14
metric learning for	14
report no ucb	13
no ucb eecs	13
www eecs berkeley	13
eecs berkeley edu	13
berkeley edu pubs	13
edu pubs techrpts	13
pubs techrpts eecs	13
techrpts eecs html	13
nec laboratories america	13
recognition in video	13
engineering science university	13
we show that	13
for video classi	13
and ioannis pitas	13
of nebraska lincoln	13
peer reviewed version	13
of california merced	13
or promotional purposes	13
works for resale	13
resale or redistribution	13
journal of science	13
more information please	13
entific research documents	13
scientifiques de niveau	13
publi ou non	13
manant des tablissements	13
des tablissements enseignement	13
recherche fran ais	13
ais ou trangers	13
ou trangers des	13
trangers des laboratoires	13
the face recognition	13
for facial action	13
action unit recognition	13
and face recognition	13
institute of advanced	13
to solve the	13
illumination invariant face	13
and classi cation	13
published as conference	13
jean luc dugelay	13
engineering research and	13
shiguang shan xilin	13
shan xilin chen	13
according to the	13
school of electronics	13
beihang university beijing	13
supported by the	13
electronic engineering the	13
of the image	13
pattern recognition and	13
action recognition with	13
itet eth zurich	13
technology beijing china	13
methods have been	13
low rank representation	13
engineering michigan state	13
based on local	13
queen university belfast	13
taiwan university taipei	13
university taipei taiwan	13
jun cheng chen	13
detection in the	13
human robot interaction	13
information technology and	13
on facial expression	13
author to whom	13
be addressed mail	13
university of adelaide	13
institute for robotics	13
for robotics and	13
berkeley ca usa	13
hong kong university	13
of biomedical engineering	13
for all other	13
natural language processing	13
der technischen universit	13
zur erlangung des	13
of face images	13
of the proposed	13
university of groningen	13
human activity recognition	13
philadelphia pa usa	13
generative adversarial networks	13
af nity matrix	13
of advanced research	12
if you believe	12
version of the	12
learning for face	12
polytechnique ed erale	12
the author and	12
hal id hal	12
southeast university nanjing	12
is the author	12
because of the	12
and jeffrey cohn	12
ibm watson research	12
for age estimation	12
xi an jiaotong	12
in real world	12
refers to the	12
processing and analysis	12
facial expressions are	12
wen sheng chu	12
work was supported	12
expression recognition system	12
the australian national	12
school of data	12
recognition under varying	12
for object detection	12
ieee and anil	12
the facial expression	12
peking university beijing	12
and engineering michigan	12
of applied sciences	12
national laboratory for	12
received april accepted	12
university of sydney	12
facial expression classification	12
lab of comp	12
of comp vis	12
comp vis pat	12
vis pat rec	12
pat rec shenzhen	12
rec shenzhen institutes	12
carolina at chapel	12
at chapel hill	12
university belfast research	12
belfast research portal	12
fr ed eric	12
permission from ieee	12
reuse of any	12
lansing mi usa	12
shown in figure	12
artificial intelligence aaai	12
this paper presents	12
there are many	12
of washington seattle	12
in revised form	12
of facial images	12
science and applications	12
and computing casia	12
and technology tsinghua	12
technology tsinghua university	12
school of automation	12
and telecommunications beijing	12
telecommunications beijing china	12
university of wisconsin	12
of brain and	12
conference on arti	12
to the same	12
volume issue may	12
information please contact	12
deep learning for	12
school of eecs	12
we use the	12
of the human	12
university of bath	12
hand over face	12
final publication citation	12
this work for	11
troy ny usa	11
explore bristol research	11
obtained from the	11
to the department	11
for pose invariant	11
rwth aachen university	11
erale de lausanne	11
national key laboratory	11
the graduate school	11
received december accepted	11
of technology tehran	11
an jiaotong university	11
and its application	11
vision center uab	11
and kristen grauman	11
regression for face	11
for robust face	11
of engineering research	11
ability to recognize	11
on face recognition	11
terms of the	11
that has been	11
can be found	11
citation for published	11
it is not	11
for quantum computation	11
for information science	11
real time facial	11
center for cognitive	11
in the eld	11
have been developed	11
in the scene	11
automation tsinghua university	11
engineering south china	11
of twente the	11
using convolutional neural	11
academia sinica taipei	11
of computing the	11
computing the hong	11
research showcase cmu	11
ed eric jurie	11
in any current	11
machine learning techniques	11
to the faculty	11
that the proposed	11
www mdpi com	11
mdpi com journal	11
computational intelligence and	11
usc ca usa	11
ijacsa international journal	11
of bucharest romania	11
university chengdu china	11
box thessaloniki greece	11
in the face	11
university of florence	11
of wisconsin madison	11
cial intelligence ijcai	11
in partial satisfaction	11
in human computer	11
the th international	11
information about this	11
beijing jiaotong university	11
park md usa	11
seattle wa usa	11
erlangung des akademischen	11
des akademischen grades	11
face image retrieval	11
the main paper	11
for fine grained	11
computer graphics and	11
northeastern university boston	11
ur elektrotechnik und	11
elektrotechnik und informationstechnik	11
florida state university	11
publication citation information	11
citation information doi	11
rutgers the state	10
the state university	10
of new jersey	10
and information systems	10
university of canberra	10
to publication record	10
take down policy	10
you believe that	10
science and research	10
for video technology	10
and control engineering	10
university of the	10
ouvertes fr hal	10
technology nanjing university	10
arts and sciences	10
university of basel	10
in pattern recognition	10
beckman institute university	10
features for face	10
of advanced industrial	10
in the literature	10
saarland informatics campus	10
electrical and information	10
expression recognition from	10
representation of the	10
is licensed under	10
creativecommons org licenses	10
high dimensional data	10
received june accepted	10
have shown that	10
faculty of informatics	10
of the paper	10
computer interaction hci	10
is that the	10
tencent ai lab	10
dept of information	10
additional key words	10
key words and	10
words and phrases	10
of our method	10
facial expressions and	10
facial expression and	10
and physical sciences	10
because of its	10
such as face	10
sen university china	10
college of engg	10
for published version	10
of the author	10
university of southampton	10
institute for infocomm	10
for infocomm research	10
enti research documents	10
ques de niveau	10
es ou non	10
emanant des etablissements	10
des etablissements enseignement	10
recherche fran cais	10
cais ou etrangers	10
ou etrangers des	10
etrangers des laboratoires	10
de minas gerais	10
received march accepted	10
facial feature detection	10
temporal action localization	10
in facial expression	10
of machine perception	10
cooperative medianet innovation	10
medianet innovation center	10

\ No newline at end of file diff --git a/s2-pdf-report.py b/s2-pdf-report.py index c47579a6..d3e117f1 100644 --- a/s2-pdf-report.py +++ b/s2-pdf-report.py @@ -6,17 +6,23 @@ import json import click import math import string +# import nltk +from collections import Counter from util import * PDF_DIR = 'datasets/s2/pdf' +punctuation = re.compile(r'[-.?!,":;()|0-9]') @click.command() def s2_pdf_report(): rows = [] empty_papers = [] no_separator_papers = [] - geocoded_papers = [] + geocoded_papers = [] unknown_papers = [] + unknown_terms = Counter() + unknown_bigrams = Counter() + unknown_trigrams = Counter() found_count = 0 total_count = 0 addresses = AddressBook() @@ -40,6 +46,24 @@ def s2_pdf_report(): address = addresses.find(l) if address: found_addresses.append(address) + if not address: + for heading in headings: + l = heading.lower().strip() + l = re.sub('[^a-zA-Z]+', ' ', l) + l = re.sub('\s+', ' ', l) + terms = l.strip().split(' ') + last_term = None + penultimate_term = None + for term in terms: + if len(term) > 1 and term != 'cid': + if len(term) > 2: + unknown_terms[term] += 1 + if last_term: + unknown_bigrams[last_term + ' ' + term] += 1 + if penultimate_term: + unknown_trigrams[penultimate_term + ' ' + last_term + ' ' + term] += 1 + penultimate_term = last_term + last_term = term # MAYBE try checking the entire string against everything? # if not len(found_addresses): @@ -54,6 +78,10 @@ def s2_pdf_report(): geocoded_papers.append([paper.paper_id, paper.title] + address) else: unknown_papers.append([paper.paper_id, paper.title, heading_string]) + + write_report('reports/pdf_unknown_terms.html', title='PDF Report: Unknown Terms', keys=None, rows=unknown_terms.most_common(1000)) + write_report('reports/pdf_unknown_bigrams.html', title='PDF Report: Unknown Bigrams', keys=None, rows=unknown_bigrams.most_common(1000)) + write_report('reports/pdf_unknown_trigram.html', title='PDF Report: Unknown Trigrams', keys=None, rows=unknown_trigrams.most_common(1000)) write_csv('reports/stats/empty_papers.csv', keys=None, rows=empty_papers) write_csv('reports/stats/no_separator_papers.csv', keys=None, rows=no_separator_papers) write_csv('reports/stats/geocoded_papers.csv', keys=None, rows=geocoded_papers) -- cgit v1.2.3-70-g09d2