[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Gzz-commits] manuscripts/Paper IV03.cls paper.tex
From: |
Janne V. Kujala |
Subject: |
[Gzz-commits] manuscripts/Paper IV03.cls paper.tex |
Date: |
Fri, 25 Apr 2003 04:15:31 -0400 |
CVSROOT: /cvsroot/gzz
Module name: manuscripts
Changes by: Janne V. Kujala <address@hidden> 03/04/25 04:15:31
Modified files:
Paper : IV03.cls paper.tex
Log message:
unify citation format
CVSWeb URLs:
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/manuscripts/Paper/IV03.cls.diff?tr1=1.1&tr2=1.2&r1=text&r2=text
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/manuscripts/Paper/paper.tex.diff?tr1=1.129&tr2=1.130&r1=text&r2=text
Patches:
Index: manuscripts/Paper/IV03.cls
diff -u manuscripts/Paper/IV03.cls:1.1 manuscripts/Paper/IV03.cls:1.2
--- manuscripts/Paper/IV03.cls:1.1 Tue Mar 18 04:23:34 2003
+++ manuscripts/Paper/IV03.cls Fri Apr 25 04:15:31 2003
@@ -503,8 +503,10 @@
%
%% separate citations with "], ["
address@hidden@address@hidden
address@hidden@address@hidden@citeb:=#2\do address@hidden@citea{],
address@hidden address@hidden@citeb}{{\bf address@hidden {Citation
address@hidden' on
address@hidden@address@hidden@citeb:=#2\do address@hidden@citea{%
+%], [%
+, % --Jvk: don't add extra brackets
address@hidden address@hidden@citeb}{{\bf address@hidden {Citation
address@hidden' on
page \thepage \space undefined}}%
{\csname address@hidden@citeb\endcsname}}}{#1}}
Index: manuscripts/Paper/paper.tex
diff -u manuscripts/Paper/paper.tex:1.129 manuscripts/Paper/paper.tex:1.130
--- manuscripts/Paper/paper.tex:1.129 Thu Apr 24 08:11:09 2003
+++ manuscripts/Paper/paper.tex Fri Apr 25 04:15:31 2003
@@ -67,10 +67,6 @@
%FIXME: Fig 1, a): Mark the link clearer. Try to avoid line crossing.
-%FIXME: The citation might be better if only a unified format is used.
-%E.g., "point (see, e.g., Heeger[16])" -> "point[16]" . (Optional)
-%XXX: is there a reason for inserting "], [" between citations?
-
%FIXME: The fonts should be uniform in the topics of figure 1 and table 1.
%FIXME: Revise the spelling and grammar errors, esp. grammar of long sentences.
@@ -276,9 +272,9 @@
Textures have been synthesized in several ways:
procedurally\cite{perlin-noise-intro},
using
other textures as a starting point\cite{heeger95pyramid},
-perceptually, for visualizing surface
orientation\cite{schweitzer83texturing,interrante97illustrating} and scalar or
vector fields\cite{ware95texture},
-and statistically, as samples from a probability distribution on a random field
-\cite{cross83markov,geman84stochastic}.
+perceptually, for visualizing surface
orientation\cite{interrante97illustrating,schweitzer83texturing} and scalar or
vector fields\cite{ware95texture},
+and statistically, as samples from a probability distribution on a
+random field\cite{cross83markov,geman84stochastic}.
% FIXME: grammar
% XXX: there's overlap between the enumerated cases
@@ -293,7 +289,7 @@
Psychophysical studies on texture perception have mostly concentrated
on pre-attentive
-\emph{visual texture
discrimination}\cite{julesz62visualpattern,bergen91theories},
+\emph{visual texture
discrimination}\cite{bergen91theories,julesz62visualpattern},
the ability of human observers to effortlessly discriminate
pairs of certain textures.
%Discrimination models can provide insight on the pre-attentive
@@ -304,27 +300,26 @@
However, the textons are hard to define formally.
Simpler, filtering-based models can explain texture discrimination
-equally well \cite{bergen88earlyvision}.
+equally well\cite{bergen88earlyvision}.
In these models, a bank of linear filters is applied to the texture followed
by a nonlinearity and then another set of filters to extract features
-(see, e.g., Heeger\cite{heeger95pyramid}).
+(see, e.g., %Heeger
+\cite{heeger95pyramid}).
%FIXME: grammar and citation
There is also physiological evidence of the filtering processes:
%The first stages
%of visual perception
%are fairly well known
in the visual cortex, there are cells sensitive to different
-frequencies, orientations, and locations in the visual field
-%(see, e.g.,~Bruce et al
+frequencies, orientations, and locations in the visual field%(see, e.g.,~Bruce
et al
\cite{bruce96visualperception}.
On a higher level, the correlations between local features are combined
by forming contours and possibly
-other higher-level constructions %(see, e.g.,
+other higher-level constructions%(see, e.g.,
\cite{saarinen97integration}.
These higher levels are not yet thoroughly understood;
-some theories
-%(see, e.g., Biederman%
+some theories%(see, e.g., Biederman%
\cite{biederman87}
assume certain primitive shapes whose
structure facilitates recognition.
@@ -340,7 +335,7 @@
(no color, lack of frequency-band interaction, etc.).
For some natural texture sets,
three dimensions have also been
-sufficient \cite{rao96texturenaming}, but often semantic connections cause the
+sufficient\cite{rao96texturenaming}, but often semantic connections cause the
similarity to be context-dependant, making it hard to assess the
dimensionality.
%% XXX: this is something we should experiment with our textures
@@ -729,7 +724,7 @@
Features that are orthogonal for human perception
(e.g.,~color and direction of fastest luminance change)
should be independently random, and features not orthogonal
-(e.g. colors of neighbouring pixels)
+(e.g., colors of neighbouring pixels)
should be correlated so as to maximize the entropy.
%For example, pixels on a small area should correlate enough to
%facilitate perception of contours.
@@ -1078,8 +1073,7 @@
any mapping of the texture is fine, as long as it repeats
with the selected repeating unit. For example, a texture can
repeat multiple times inside the repeating unit, or can be skewed
-w.r.t.~the repeating unit.
-%FIXME: spell out w.r.t?(Optional)
+with respect to the repeating unit.
Again, a heuristic distribution is used which does not skew or scale
the basis texture too much too often.
@@ -1399,7 +1393,7 @@
Another question is how many textures would the user have to remember
for it to be useful.
-Studies of web cache statistics (see, e.g. \cite{breslau99web})
+Studies of web cache statistics (see, e.g., \cite{breslau99web})
have shown that file popularity approximately follows Zipf's law
so that a small number of documents accounts
for most of the use,
[Prev in Thread] |
Current Thread |
[Next in Thread] |
- [Gzz-commits] manuscripts/Paper IV03.cls paper.tex,
Janne V. Kujala <=