D15-1224 |
real-world uncertainty , such
|
object recognition
|
errors or cluttered scenes .
|
C92-4200 |
Torino . 3.1 OBJECT RECOGNITION The
|
object recognition
|
step processes the text from
|
J86-1012 |
approach to three-dimensional
|
object recognition
|
from a single view . The system
|
C92-4200 |
pragmatical reasons . When the
|
object recognition
|
analysis reported some problems
|
C92-4200 |
failures were reported during the
|
object recognition
|
. It integrates Bottom-Up ( BUS
|
D14-1005 |
well , but apply them to a visual
|
object recognition
|
task instead of concept meaning
|
C92-4200 |
the University of Torino . 3.1
|
OBJECT RECOGNITION
|
The object recognition step processes
|
C92-4200 |
order to pertbrm two main steps :
|
object recognition
|
and object linking . This separation
|
A97-1002 |
hard/software to allow visual
|
object recognition
|
for lexical acquisition . <title>
|
D14-1005 |
CNN ) trained on a large labeled
|
object recognition
|
dataset . This transfer learning
|
C92-4200 |
syntax and semantics brings to the
|
object recognition
|
from a structural and semantic
|
D13-1038 |
right ) . In addition , we use
|
object recognition
|
models ( Zhang and Lu , 2002
|
H05-1064 |
describe a hidden-variable model for
|
object recognition
|
in computer vision . The approaches
|
D12-1019 |
recognition ( Rabiner , 1989 ) and
|
object recognition
|
( Quattoni et al. , 2004 ) .
|
D15-1015 |
the network has been trained for
|
object recognition
|
. If , however , we are interested
|
D15-1015 |
computer vision tasks such as
|
object recognition
|
( Razavian et al. , 2014 ) .
|
C92-4200 |
sentence are identified by the
|
object recognition
|
step , a connection among them
|
C92-4200 |
. is guarantied because at the
|
object recognition
|
level each syntactic connection
|
D13-1115 |
have been immensely successful in
|
object recognition
|
( Farhadi et al. , 2009 ) , act
|
C92-4200 |
to the reliability rate of the
|
object recognition
|
. Note that even the TDS+BUS
|