IJCB 2023 IJCB 2023

CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE.

000 054
001 055
002 056
003 LATEX Author Guidelines for IJCB 2023 Proceedings [Based on CVPR] 057
004 058
005 059
006 060
Anonymous IJCB 2023 submission
007 061
008 062
009 063
010 064
011 Abstract guide. Note that this LATEX guide already sets figure cap- 065
012 tions and references in a smaller font. The reason such pa- 066
013 The ABSTRACT is to be in fully-justified italicized text, pers will not be reviewed is that there is no provision for 067
014 at the top of the left-hand column, below the author and supervised revisions of manuscripts. The reviewing process 068
015 affiliation information. Use the word “Abstract” as the title, cannot determine the suitability of the paper for presenta- 069
016 in 12-point Times, boldface type, centered relative to the tion in eight pages if it is reviewed in eleven. If you submit 070
017 column, initially capitalized. The abstract is to be in 10- 8 for review expect to pay the added page charges for them. 071
018 point, single-spaced type. Leave two blank lines after the 072
019 Abstract, then begin the main text. Look at previous IJCB 073
020 abstracts to get a feel for style and length. 1.4. The ruler 074
021 075
022 The LATEX style defines a printed ruler which should be 076
023 1. Introduction present in the version submitted for review. The ruler is 077
024 provided in order that reviewers may comment on partic- 078
025 Please follow the steps outlined below when submitting ular lines in the paper without circumlocution. If you are 079
026 your manuscript. preparing a document using a non-LATEX document prepa- 080
027 1.1. Language ration system, please arrange for an equivalent ruler to 081
028 appear on the final output pages. The presence or ab- 082
029 All manuscripts must be in English. sence of the ruler should not change the appearance of 083
030 any other content on the page. The camera ready copy 084
1.2. Dual submission
031 should not contain a ruler. (LATEX users may uncomment 085
032 By submitting a manuscript to IJCB, the authors assert the \ijcbfinalcopy command in the document pream- 086
033 that it has not been previously published in substantially ble.) Reviewers: note that the ruler measurements do not 087
034 similar form. Furthermore, no paper which contains signif- align well with lines in the paper — this turns out to be very 088
035 icant overlap with the contributions of this paper either has difficult to do well when the paper contains many figures 089
036 been or will be submitted during the IJCB 2023 review pe- and equations, and, when done, looks ugly. Just use frac- 090
037 riod to either a journal or any conference (including IJCB tional references (e.g. this line is 095.5), although in most 091
038 2023) or any workshop. Papers violating this condition cases one would expect that the approximate location will 092
039 will be rejected and a list of violating authors may be be adequate. 093
040 included in the proceedings. 094
041 If there are papers that may appear to the reviewers to vi- 095
042 olate this condition, then it is your responsibility to: (1) cite 1.5. Mathematics 096
043 these papers (preserving anonymity as described in Section 097
044 1.6 below), (2) argue in the body of your paper why your Please number all of your sections and displayed equa- 098
045 IJCB paper is non-trivially different from these concurrent tions. It is important for readers to be able to refer to any 099
046 submissions, and (3) include anonymized versions of those particular equation. Just because you didn’t refer to it in the 100
047 papers in the supplemental material. text doesn’t mean some future reader might not need to re- 101
048 fer to it. It is cumbersome to have to use circumlocutions 102
1.3. Paper length
049 like “the equation second from the top of page 3 column 1”. 103
050 Consult the call for papers for page-length limits. Over (Note that the ruler will not be present in the final copy, so 104
051 length papers will simply not be reviewed. This includes pa- is not an alternative to equation numbers). All authors will 105
052 pers where the margins and formatting are deemed to have benefit from reading Mermin’s description of how to write 106
053 been significantly altered from those laid down by this style mathematics. 107
IJCB 2023 IJCB 2023
CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE.

108 162
1.6. Blind review to a techreport for further details. Thus, you may say in
109 163
the body of the paper “further details may be found in [4]”.
110 Many authors misunderstand the concept of anonymiz- 164
Then submit the techreport as additional material. Again,
111 ing for blind review. Blind review does not mean that one 165
you may not assume the reviewers will read this material.
112 must remove citations to one’s own work—in fact it is often 166
Sometimes your paper is about a problem which you
113 impossible to review a paper unless the previous citations 167
tested using a tool which is widely known to be restricted
114 are known and available. 168
to a single institution. For example, let’s say it’s 1969, you
115 Blind review means that you do not use the words “my” 169
have solved a key problem on the Apollo lander, and you be-
116 or “our” when citing previous work. That is all. (But see 170
lieve that the IJCB 2023 audience would like to hear about
117 below for techreports) 171
your solution. The work is a development of your cele-
118 Saying “this builds on the work of Lucy Smith [1]” does 172
brated 1968 paper entitled “Zero-g frobnication: How be-
119 not say that you are Lucy Smith, it says that you are building 173
ing the only people in the world with access to the Apollo
120 on her work. If you are Smith and Jones, do not say “as we 174
lander source code makes us a wow at parties”, by Zeus et
121 show in [7]”, say “as Smith and Jones show in [7]” and at 175
al.
122 the end of the paper, include reference 7 as you would any 176
You can handle this paper like any other. Don’t write
123 other cited work. 177
“We show how to improve our previous work [Anonymous,
124 An example of a bad paper just asking to be rejected: 178
1968]. This time we tested the algorithm on a lunar lander
125 179
An analysis of the frobnicatable foo filter. [name of lander removed for blind review]”. That would be
126 180
silly, and would immediately identify the authors. Instead
127 In this paper we present a performance analysis write the following: 181
128 of our previous paper [1], and show it to be in- 182
129 ferior to all previously known methods. Why the We describe a system for zero-g frobnication. 183
130 previous paper was accepted without this analysis This system is new because it handles the fol- 184
131 is beyond me. lowing cases: A, B. Previous systems [Zeus et al. 185
132 1968] didn’t handle case B properly. Ours han- 186
[1] Removed for blind review
133 dles it by including a foo term in the bar integral. 187
134 An example of an acceptable paper: ... 188
135 The proposed system was integrated with the 189
136 An analysis of the frobnicatable foo filter. Apollo lunar lander, and went all the way to the 190
137 moon, don’t you know. It displayed the following 191
In this paper we present a performance analysis of
138 behaviours which show how well we solved cases 192
the paper of Smith et al. [1], and show it to be in-
139 A and B: ... 193
ferior to all previously known methods. Why the
140 194
previous paper was accepted without this analysis
141 As you can see, the above text follows standard scientific 195
is beyond me.
142 convention, reads better than the first version, and does not 196
143 [1] Smith, L and Jones, C. “The frobnicatable explicitly name you as the authors. A reviewer might think 197
144 foo filter, a fundamental contribution to human it likely that the new paper was written by Zeus et al., but 198
145 knowledge”. Nature 381(12), 1-213. cannot make any decision based on that guess. He or she 199
146 would have to be sure that no other authors could have been 200
147
If you are making a submission to another conference at contracted to solve problem B. 201
148
the same time, which covers similar or overlapping mate- FAQ: Are acknowledgements OK? No. Leave them for 202
149
rial, you may need to refer to that submission in order to the final copy. 203
150
explain the differences, just as you would if you had pre- 204
151
viously published related work. In such cases, include the 1.7. Miscellaneous 205
anonymized parallel submission [5] as additional material
152 Compare the following: 206
and cite it as
153 $conf_a$ confa 207
154 [1] Authors. “The frobnicatable foo filter”, F&G $\mathit{conf}_a$ conf a 208
155 2011 Submission ID 324, Supplied as additional See The TEXbook, p165. 209
156 material [Link]. The space after e.g., meaning “for example”, should not 210
157 be a sentence-ending space. So e.g. is correct, e.g. is not. 211
158 Finally, you may feel you need to tell the reader that The provided \eg macro takes care of this. 212
159 more details can be found elsewhere, and refer them to a When citing a multi-author paper, you may save space 213
160 technical report. For conference submissions, the paper by using “et alia”, shortened to “et al.” (not “et. al.” as 214
161 must stand on its own, and not require the reviewer to go “et” is a complete word.) However, use it only when there 215

2
IJCB 2023 IJCB 2023
CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE.

216 270
MAIN TITLE. Center the title 1-3/8 inches (3.49 cm)
217 271
from the top edge of the first page. The title should be
218 272
in Times 14-point, boldface type. Capitalize the first let-
219 273
ter of nouns, pronouns, verbs, adjectives, and adverbs; do
220 274
not capitalize articles, coordinate conjunctions, or preposi-
221 275
tions (unless the title begins with such a word). Leave two
222 276
blank lines after the title.
223 277
AUTHOR NAME(s) and AFFILIATION(s) are to be
224 278
centered beneath the title and printed in Times 12-point,
225 279
non-boldface type. This information is to be followed by
226 280
two blank lines.
227 281
228
The ABSTRACT and MAIN TEXT are to be in a two- 282
229
column format. 283
230
Figure 1. Example of caption. It is set in Roman so that mathemat- MAIN TEXT. Type main text in 10-point Times, single- 284
ics (always set in Roman: B sin A = A sin B) may be included spaced. Do NOT use double-spacing. All paragraphs
231 285
without an ugly clash. should be indented 1 pica (approx. 1/6 inch or 0.422 cm).
232 286
233 Make sure your text is fully justified—that is, flush left and 287
234 are three or more authors. Thus, the following is correct: flush right. Please do not place any additional blank lines 288
235 “ Frobnication has been trendy lately. It was introduced between paragraphs. 289
236 by Alpher [1], and subsequently developed by Alpher and Figure and table captions should be 9-point Roman type 290
237 Fotheringham-Smythe [2], and Alpher et al. [3].” as in Figures 1 and 2. Short captions should be centred. 291
238 This is incorrect: “... subsequently developed by Alpher Callouts should be 9-point Helvetica, non-boldface type. 292
239 et al. [2] ...” because reference [2] has just two authors. Initially capitalize only the first word of section titles and 293
240 If you use the \etal macro provided, then you need not first-, second-, and third-order headings. 294
241 worry about double periods when used at the end of a sen- FIRST-ORDER HEADINGS. (For example, 1. Intro- 295
242 tence as in Alpher et al. duction) should be Times 12-point boldface, initially cap- 296
243 For this citation style, keep multiple citations in numeri- italized, flush left, with one blank line before. 297
244 cal (not chronological) order, so prefer [2, 1, 3] to [1, 2, 3]. SECOND-ORDER HEADINGS. (For example, 1.1. 298
245 Database elements) should be Times 11-point boldface, 299
246 2. Formatting your paper initially capitalized, flush left, with one blank line before, 300
247 and one after. If you require a third-order heading (we dis- 301
248 All text must be in a two-column format. The total allow- 302
courage it), use 10-point Times, boldface, initially capital-
249 able width of the text area is 6 78 inches (17.5 cm) wide by 303
ized, flush left, preceded by one blank line, followed by a
250 8 87 inches (22.54 cm) high. Columns are to be 3 14 inches 304
5 period and your text on the same line.
251 (8.25 cm) wide, with a 16 inch (0.8 cm) space between 305
them. The main title (on the first page) should begin 1.0
252 2.3. Footnotes 306
253 inch (2.54 cm) from the top edge of the page. The second 307
254 and following pages should begin 1.0 inch (2.54 cm) from Please use footnotes1 sparingly. Indeed, try to avoid 308
255 the top edge. On all pages, the bottom margin should be footnotes altogether and include necessary peripheral ob- 309
256 1-1/8 inches (2.86 cm) from the bottom edge of the page servations in the text (within parentheses, if you prefer, as 310
257 for 8.5 × 11-inch paper; for A4 paper, approximately 1-5/8 in this sentence). If you wish to use a footnote, place it at the 311
258 inches (4.13 cm) from the bottom edge of the page. bottom of the column on the page on which it is referenced. 312
259 Use Times 8-point type, single-spaced. 313
2.1. Margins and page numbering
260 314
261 All printed material, including text, illustrations, and 2.4. References 315
262 charts, must be kept within a print area 6-7/8 inches (17.5 316
List and number all bibliographical references in 9-point
263 cm) wide by 8-7/8 inches (22.54 cm) high. 317
Times, single-spaced, at the end of your paper. When ref-
264 erenced in the text, enclose the citation number in square 318
2.2. Type-style and fonts
265 brackets, for example [3]. Where appropriate, include the 319
266 Wherever Times is specified, Times Roman may also be name(s) of editors of referenced books. 320
267 used. If neither is available on your word processor, please 321
268 use the font closest in appearance to Times to which you 1 This is what a footnote looks like. It often distracts the reader from 322
269 have access. the main flow of the argument. 323

3
IJCB 2023 IJCB 2023
CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE.

324 378
325 379
326 380
327 381
328 382
329 383
330 384
331 385
332 386
333 387
334 388
335 389
336 390
337 391
338 Figure 2. Example of a short caption, which should be centered. 392
339 393
340 394
Method Frobnability References
341 395
Theirs Frumpy [1] A. Alpher. Frobnication. Journal of Foo, 12(1):234–778,
342 396
Yours Frobbly 2002.
343 397
Ours Makes one’s heart Frob [2] A. Alpher and J. P. N. Fotheringham-Smythe. Frobnication
344 398
345 revisited. Journal of Foo, 13(1):234–778, 2003. 399
Table 1. Results. Ours is better.
346 [3] A. Alpher, J. P. N. Fotheringham-Smythe, and G. Gamow. Can 400
347
a machine frobnicate? Journal of Foo, 14(1):234–778, 2004. 401
348 2.5. Illustrations, graphs, and photographs [4] Authors. Frobnication tutorial, 2006. Supplied as additional 402
material [Link].
349 403
All graphics should be centered. Please ensure that any [5] Authors. The frobnicatable foo filter, 2011. Face and
350 404
point you wish to make is resolvable in a printed copy of Gesture submission ID 324. Supplied as additional material
351 405
the paper. Resize fonts in figures to match the font in the [Link].
352 406
body text, and choose line widths which render effectively
353 407
in print. Many readers (and reviewers), even of an electronic
354 408
copy, will choose to print your paper in order to read it.
355 409
You cannot insist that they do otherwise, and therefore must
356 410
not assume that they can zoom in to see tiny details on a
357 411
graphic.
358 412
When placing figures in LATEX, it’s almost always best to
359 use \includegraphics, and to specify the figure width 413
360 as a multiple of the line width as in the example below 414
361 415
362 \usepackage[dvips]{graphicx} ... 416
363 \includegraphics[width=0.8\linewidth] 417
364 {[Link]} 418
365 419
366
2.6. Color 420
367 Color is valuable, and will be visible to readers of the 421
368 electronic copy. However ensure that, when printed on a 422
369 monochrome printer, no important information is lost by the 423
370 conversion to grayscale. 424
371 425
372 426
3. Only for Final copy
373 427
374 You must include your signed IEEE copyright release 428
375 form when you submit your finished paper. We MUST have 429
376 this form before your paper can be published in the proceed- 430
377 ings. 431