2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML),
Journal Year:
2023,
Volume and Issue:
unknown, P. 1181 - 1184
Published: Nov. 3, 2023
In
recent
years,
military
science
and
technology
has
been
developed
rapidly,
new
equipments
equipped
in
the
army.
Augmented
Reality
(AR)
provides
possibility
to
solve
problem
of
operation
training.
But
training
process,
One
essential
technologies
is
how
location
identify
keys.
Obviously,
sample
set
keys
basis
key
recognition,
a
certain
scale
an
indispensable
element
ensure
performance
recognition
model.
On
manually
establishing
small
set,
this
paper
puts
forward
mechanism
based
on
interactive
automatic
labeling
expanding,
target
model
was
updated
by
incremental
learning
method
at
same
time.
Information Fusion,
Journal Year:
2024,
Volume and Issue:
113, P. 102616 - 102616
Published: Aug. 5, 2024
As
a
core
branch
of
financial
forecasting,
stock
forecasting
plays
crucial
role
for
analysts,
investors,
and
policymakers
in
managing
risks
optimizing
investment
strategies,
significantly
enhancing
the
efficiency
effectiveness
economic
decision-making.
With
rapid
development
information
technology
computer
science,
data-driven
neural
network
technologies
have
increasingly
become
mainstream
method
forecasting.
Although
recent
review
studies
provided
basic
introduction
to
deep
learning
methods,
they
still
lack
detailed
discussion
on
architecture
design
innovative
details.
Additionally,
latest
research
emerging
large
language
models
structures
has
yet
be
included
existing
literature.
In
light
this,
this
paper
comprehensively
reviews
literature
networks
field
from
2015
2023,
discussing
various
classic
structures,
including
Recurrent
Neural
Networks
(RNNs),
Convolutional
(CNNs),
Transformers,
Graph
(GNNs),
Generative
Adversarial
(GANs),
Large
Language
Models
(LLMs).
It
analyzes
application
achievements
these
market
Moreover,
article
also
outlines
commonly
used
datasets
evaluation
metrics
further
exploring
unresolved
issues
potential
future
directions,
aiming
provide
clear
guidance
reference
researchers
Robotics and Autonomous Systems,
Journal Year:
2024,
Volume and Issue:
174, P. 104615 - 104615
Published: Jan. 21, 2024
Service
robots
are
increasingly
integrating
into
our
daily
lives
to
help
us
with
various
tasks.
In
such
environments,
frequently
face
new
objects
while
working
in
the
environment
and
need
learn
them
an
open-ended
fashion.
Furthermore,
must
be
able
recognize
a
wide
range
of
object
categories.
this
paper,
we
present
lifelong
ensemble
learning
approach
based
on
multiple
representations
address
few-shot
recognition
problem.
particular,
form
methods
deep
handcrafted
3D
shape
descriptors.
To
facilitate
learning,
each
is
equipped
memory
unit
for
storing
retrieving
information
instantly.
The
proposed
model
suitable
scenarios
where
number
categories
not
fixed
can
grow
over
time.
We
have
performed
extensive
sets
experiments
assess
performance
offline,
scenarios.
For
evaluation
purposes,
addition
real
datasets,
generate
large
synthetic
household
dataset
consisting
27000
views
90
objects.
Experimental
results
demonstrate
effectiveness
method
online
tasks,
as
well
its
superior
state-of-the-art
approaches.
show
that
modestly
beneficial
offline
settings,
it
significantly
situations.
Additionally,
demonstrated
both
simulated
real-robot
robot
rapidly
learned
from
limited
examples.
A
video
available
at:
https://youtu.be/nxVrQCuYGdI.
