-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathindex.html
More file actions
541 lines (506 loc) · 26.9 KB
/
Copy pathindex.html
File metadata and controls
541 lines (506 loc) · 26.9 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<!-- Primary Meta Tags -->
<meta name="title" content="VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text - Everaert et al. - BMVC 2023">
<meta name="description" content="VETIM expands the vocabulary of text-to-image models using only textual descriptions, without sample images. By supervising only the text encoder output, it enables faster single-token concept learning from text alone.">
<meta name="keywords" content="text-to-image, vocabulary expansion, textual inversion, stable diffusion, CLIP, text encoder, concept learning, BMVC 2023, machine learning, computer vision, AI">
<meta name="author" content="Martin Nicolas Everaert, Marco Bocchio, Sami Arpa, Sabine Süsstrunk, Radhakrishna Achanta">
<meta name="robots" content="index, follow">
<meta name="language" content="English">
<!-- Open Graph / Facebook -->
<meta property="og:type" content="article">
<meta property="og:site_name" content="IVRL - EPFL">
<meta property="og:title" content="VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text - Everaert et al. - BMVC 2023">
<meta property="og:description" content="VETIM expands the vocabulary of text-to-image models using only textual descriptions, without sample images. By supervising only the text encoder output, it enables faster single-token concept learning from text alone.">
<meta property="og:url" content="https://ivrl.github.io/vetim/">
<meta property="og:image" content="https://ivrl.github.io/vetim/static/diagram.png">
<meta property="og:image:width" content="1200">
<meta property="og:image:height" content="630">
<meta property="og:image:alt" content="VETIM architecture">
<meta property="article:published_time" content="2023-11-20T00:00:00.000Z">
<meta property="article:author" content="Martin Nicolas Everaert">
<meta property="article:section" content="Research">
<meta property="article:tag" content="text-to-image">
<meta property="article:tag" content="vocabulary expansion">
<meta property="article:tag" content="textual inversion">
<meta property="article:tag" content="stable diffusion">
<meta property="article:tag" content="CLIP">
<meta property="article:tag" content="text encoder">
<meta property="article:tag" content="concept learning">
<meta property="article:tag" content="BMVC 2023">
<meta property="article:tag" content="machine learning">
<meta property="article:tag" content="computer vision">
<meta property="article:tag" content="AI">
<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image">
<!-- TODO: Replace with your lab/institution Twitter handle
<meta name="twitter:site" content="@YOUR_TWITTER_HANDLE"> -->
<meta name="twitter:creator" content="@EveraertMartin">
<meta name="twitter:title" content="VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text - Everaert et al. - BMVC 2023">
<meta name="twitter:description" content="VETIM expands the vocabulary of text-to-image models using only textual descriptions, without sample images. By supervising only the text encoder output, it enables faster single-token concept learning from text alone.">
<meta name="twitter:image" content="https://ivrl.github.io/vetim/static/diagram.png">
<meta name="twitter:image:alt" content="VETIM architecture">
<!-- Academic/Research Specific -->
<meta name="citation_title" content="VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text">
<meta name="citation_author" content="Everaert, Martin Nicolas">
<meta name="citation_author" content="Bocchio, Marco">
<meta name="citation_author" content="Arpa, Sami">
<meta name="citation_author" content="Süsstrunk, Sabine">
<meta name="citation_author" content="Achanta, Radhakrishna">
<meta name="citation_publication_date" content="2023">
<meta name="citation_conference_title" content="34th British Machine Vision Conference (BMVC 2023)">
<meta name="citation_pdf_url" content="https://papers.bmvc2023.org/0016.pdf">
<!-- Additional SEO -->
<meta name="theme-color" content="#2563eb">
<meta name="msapplication-TileColor" content="#2563eb">
<meta name="apple-mobile-web-app-capable" content="yes">
<meta name="apple-mobile-web-app-status-bar-style" content="default">
<!-- Preconnect for performance -->
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="preconnect" href="https://ajax.googleapis.com">
<link rel="preconnect" href="https://documentcloud.adobe.com">
<link rel="preconnect" href="https://cdn.jsdelivr.net">
<title>VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text</title>
<!-- Favicon and App Icons -->
<link rel="icon" type="image/png" href="static/images/favicon.png">
<link rel="apple-touch-icon" href="static/images/favicon.png">
<!-- Critical CSS - Load synchronously -->
<link rel="stylesheet" href="static/css/bulma.min.css">
<link rel="stylesheet" href="static/css/index.css">
<!-- Non-critical CSS - Load asynchronously -->
<link rel="preload" href="static/css/bulma-carousel.min.css" as="style" onload="this.onload=null;this.rel='stylesheet'">
<link rel="preload" href="static/css/bulma-slider.min.css" as="style" onload="this.onload=null;this.rel='stylesheet'">
<link rel="preload" href="static/css/fontawesome.all.min.css" as="style" onload="this.onload=null;this.rel='stylesheet'">
<link rel="preload" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css" as="style" onload="this.onload=null;this.rel='stylesheet'">
<!-- Fallback for browsers that don't support preload -->
<noscript>
<link rel="stylesheet" href="static/css/bulma-carousel.min.css">
<link rel="stylesheet" href="static/css/bulma-slider.min.css">
<link rel="stylesheet" href="static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
</noscript>
<!-- Fonts - Optimized loading -->
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&display=swap" rel="stylesheet">
<!-- Defer non-critical JavaScript -->
<script defer src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script defer src="https://documentcloud.adobe.com/view-sdk/main.js"></script>
<script defer src="static/js/fontawesome.all.min.js"></script>
<script defer src="static/js/bulma-carousel.min.js"></script>
<script defer src="static/js/bulma-slider.min.js"></script>
<script defer src="static/js/index.js"></script>
<!-- Structured Data for Academic Papers -->
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "ScholarlyArticle",
"headline": "VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text",
"description": "VETIM expands the vocabulary of text-to-image models using only textual descriptions, without sample images. By supervising only the text encoder output, it enables faster single-token concept learning from text alone.",
"author": [
{
"@type": "Person",
"name": "Martin Nicolas Everaert",
"affiliation": {
"@type": "Organization",
"name": "EPFL"
}
},
{
"@type": "Person",
"name": "Marco Bocchio",
"affiliation": {
"@type": "Organization",
"name": "Largo.ai"
}
},
{
"@type": "Person",
"name": "Sami Arpa",
"affiliation": {
"@type": "Organization",
"name": "Largo.ai"
}
},
{
"@type": "Person",
"name": "Sabine Süsstrunk",
"affiliation": {
"@type": "Organization",
"name": "EPFL"
}
},
{
"@type": "Person",
"name": "Radhakrishna Achanta",
"affiliation": {
"@type": "Organization",
"name": "EPFL"
}
}
],
"datePublished": "2023-11-20",
"publisher": {
"@type": "Organization",
"name": "BMVA"
},
"url": "https://ivrl.github.io/vetim/",
"image": "https://ivrl.github.io/vetim/static/diagram.png",
"keywords": ["text-to-image", "vocabulary expansion", "textual inversion", "stable diffusion", "CLIP", "text encoder", "concept learning", "machine learning", "computer vision"],
"abstract": "Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabulary embedding of new tokens. These methods have two limitations: slowness of optimisation and dependence on sample images. Slowness mainly stems from the use of the original text-to-image training loss, without considering potential auxiliary supervision terms. Relying on sample images enables learning new visual features but restricts the vocabulary expansion to concepts with pre-existing images. In response, we introduce a novel approach, named VETIM, which takes only a textual description of the concept as input. It expands the vocabulary through supervision only at the text encoder output, without accessing the image-generation part, making it faster at optimisation time. It also does not copy visual features from sample images. Our method can be used directly for applications that require a concept as a single token but do not require learning new visual features. Our approach shows that a mere textual description suffices to obtain a single token referring to a specific concept. To show the effectiveness of our method, we evaluate its performance subjectively and through objective measures. The results show that our approach is effective in expanding the vocabulary of text-to-image models without requiring images.",
"isAccessibleForFree": true
}
</script>
<!-- Website/Organization Structured Data -->
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "Organization",
"name": "IVRL - EPFL",
"url": "https://www.epfl.ch/labs/ivrl/"
}
</script>
<meta name="google-site-verification" content="ohByZQJx9EYQ7Po92WxVz1fvVDkQqgI6U5wQZ_7mKBY" />
</head>
<body>
<!-- Scroll to Top Button -->
<button class="scroll-to-top" onclick="scrollToTop()" title="Scroll to top" aria-label="Scroll to top">
<i class="fas fa-chevron-up"></i>
</button>
<!-- More Works Dropdown -->
<div class="more-works-container">
<button class="more-works-btn" onclick="toggleMoreWorks()" title="View More Works">
<i class="fas fa-flask"></i>
More Works
<i class="fas fa-chevron-down dropdown-arrow"></i>
</button>
<div class="more-works-dropdown" id="moreWorksDropdown">
<div class="dropdown-header">
<h4>More Works</h4>
<button class="close-btn" onclick="toggleMoreWorks()">
<i class="fas fa-times"></i>
</button>
</div>
<div class="works-list">
<a href="https://martin-ev.github.io/vgoq" class="work-item" target="_blank">
<div class="work-info">
<h5>Visual Grounding for Object Questions</h5>
<p>Introduces Visual Grounding for Object Questions (VGOQ), a new task for grounding visual evidence or context that supports answering general questions about objects, beyond directly visible elements.</p>
<span class="work-venue">CVPR 2026</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://ivrl.github.io/covariance-mismatch/" class="work-item" target="_blank">
<div class="work-info">
<h5>Covariance Mismatch in Diffusion Models</h5>
<p>Investigates the covariance mismatch between noise and data in diffusion models and its impact on image generation.</p>
<span class="work-venue">Preprint 2024</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://ivrl.github.io/signal-leak-bias/" class="work-item" target="_blank">
<div class="work-info">
<h5>Exploiting the Signal-Leak Bias in Diffusion Models</h5>
<p>Examines and leverages the signal-leak bias in diffusion models for improved image generation.</p>
<span class="work-venue">WACV 2024</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://ivrl.github.io/diffusion-in-style/" class="work-item" target="_blank">
<div class="work-info">
<h5>Diffusion in Style</h5>
<p>Customizes Stable Diffusion's output style by adapting the initial noise distribution, making style adaptation more sample-efficient and faster.</p>
<span class="work-venue">ICCV 2023</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://ivrl.github.io/vetim/" class="work-item" target="_blank">
<div class="work-info">
<h5>VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text</h5>
<p>Expands text-to-image models' vocabulary by learning new token embeddings from textual descriptions alone, without requiring sample images.</p>
<span class="work-venue">BMVC 2023</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://ivrl.github.io/ComicsDepth/" class="work-item" target="_blank">
<div class="work-info">
<h5>Estimating Image Depth in the Comics Domain</h5>
<p>Estimates depth in comic book images by converting them to natural images and filtering out text to improve accuracy.</p>
<span class="work-venue">WACV 2022</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://arxiv.org/abs/2006.02333" class="work-item" target="_blank">
<div class="work-info">
<h5>Scene Relighting with Illumination Estimation in the Latent Space</h5>
<p>Transfers lighting conditions between images by estimating and manipulating illumination in the latent space of an encoder-decoder network.</p>
<span class="work-venue">arXiv 2020</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
<a href="https://www.epfl.ch/labs/ivrl" class="work-item" target="_blank">
<div class="work-info">
<h5>More works from Image and Visual Representation Lab (IVRL)</h5>
<p>Also check more works from our labmates at the Image and Visual Representation Lab (IVRL) at EPFL.</p>
<span class="work-venue">IVRL - EPFL</span>
</div>
<i class="fas fa-external-link-alt"></i>
</a>
</div>
</div>
</div>
<main id="main-content">
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://martin-ev.github.io/" target="_blank">Martin Nicolas Everaert</a> <sup>1</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=KDiTxBQAAAAJ" target="_blank">Marco Bocchio</a> <sup>2</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=84FopNgAAAAJ" target="_blank">Sami Arpa</a> <sup>2</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=EX3OYP4AAAAJ" target="_blank">Sabine Süsstrunk</a> <sup>1</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=lc2HaZwAAAAJ" target="_blank">Radhakrishna Achanta</a> <sup>1</sup>
</span>
</div>
<div class="is-size-5 publication-authors">
<span class="author-block">
<sup>1</sup> EPFL, Switzerland, <br><sup>2</sup> Largo.ai, Lausanne, Switzerland
</span>
</div>
<div class="is-size-5 publication-authors">
<span class="author-block"><a href="https://bmvc2023.org/" target="_blank">BMVC 2023</a></span>
</div>
<div class="column has-text-centered">
<div class="publication-links">
<span class="link-block">
<a href="https://proceedings.bmvc2023.org/16/" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-external-link-alt"></i>
</span>
<span>BMVC 2023 proceedings</span>
</a>
</span>
<span class="link-block">
<a href="https://papers.bmvc2023.org/0016.pdf" target="_blank" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper (pdf)</span>
</a>
</span>
<span class="link-block">
<a href="https://bmvc2022.mpi-inf.mpg.de/BMVC2023/0016_supp.zip" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-archive"></i>
</span>
<span>Supplementary material (zip)</span>
</a>
</span>
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- Paper abstract -->
<section class="section hero is-light">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual
prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models
with additional concepts, by learning the vocabulary embedding of new tokens.
These methods have two limitations: slowness of optimisation and dependence on sample images. Slowness
mainly stems from the use of the original text-to-image training loss, without considering potential
auxiliary supervision terms. Relying on sample images enables learning new visual features but restricts
the vocabulary expansion to concepts with pre-existing images.
In response, we introduce a novel approach, named VETIM, which takes only a textual description of the
concept as input.
It expands the vocabulary through supervision only at the text encoder output, without accessing the
image-generation part, making it faster at optimisation time.
It also does not copy visual features from sample images.
Our method can be used directly for applications that require a concept as a single token but do not
require learning new visual features.
Our approach shows that a mere textual description suffices to obtain a single token referring to a
specific concept.
To show the effectiveness of our method, we evaluate its performance subjectively and through objective
measures.
The results show that our approach is effective in expanding the vocabulary of text-to-image models
without requiring images.
</p>
</div>
</div>
</div>
</div>
</section>
<!-- End paper abstract -->
<!-- Image carousel
<section class="hero is-small">
<div class="hero-body">
<div class="container">
<div id="results-carousel" class="carousel results-carousel">
<div class="item">
<img src="static/images/carousel1.jpg" alt="First research result visualization" loading="lazy"/>
<h2 class="subtitle has-text-centered">
First image description.
</h2>
</div>
<div class="item">
<img src="static/images/carousel2.jpg" alt="Second research result visualization" loading="lazy"/>
<h2 class="subtitle has-text-centered">
Second image description.
</h2>
</div>
<div class="item">
<img src="static/images/carousel3.jpg" alt="Third research result visualization" loading="lazy"/>
<h2 class="subtitle has-text-centered">
Third image description.
</h2>
</div>
<div class="item">
<img src="static/images/carousel4.jpg" alt="Fourth research result visualization" loading="lazy"/>
<h2 class="subtitle has-text-centered">
Fourth image description.
</h2>
</div>
</div>
</div>
</div>
</section>
End image carousel -->
<!-- Youtube video -->
<section class="hero is-small">
<div class="hero-body">
<div class="container">
<!-- Paper video. -->
<h2 class="title is-3 has-text-centered">Video Presentation</h2>
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<div class="publication-video">
<iframe src="https://www.youtube.com/embed/FBnUVXgvBac?si=0vxmiJll_JFm_LNk" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- End youtube video -->
<!-- Video carousel
<section class="hero is-small">
<div class="hero-body">
<div class="container">
<h2 class="title is-3">Another Carousel</h2>
<div id="results-carousel" class="carousel results-carousel">
<div class="item item-video1">
<video poster="" id="video1" controls muted loop height="100%">
<!-- Your video file here
<source src="static/videos/carousel1.mp4" type="video/mp4">
</video>
</div>
<div class="item item-video2">
<video poster="" id="video2" controls muted loop height="100%">
<!-- Your video file here
<source src="static/videos/carousel2.mp4" type="video/mp4">
</video>
</div>
<div class="item item-video3">
<video poster="" id="video3" controls muted loop height="100%">\
<!-- Your video file here
<source src="static/videos/carousel3.mp4" type="video/mp4">
</video>
</div>
</div>
</div>
</div>
</section>
End video carousel -->
<!--Poster -->
<section class="hero is-small is-light">
<div class="hero-body">
<div class="container">
<h2 class="title is-3 has-text-centered">Poster</h2>
<div class="columns is-centered">
<div class="column is-four-fifths">
<div class="poster-container" style="position: relative; width: fit-content; max-width: 100%; margin: 0 auto;">
<a href="static/BMVC poster.pdf" target="_blank" class="download-poster-btn" style="position: absolute; top: 0.5rem; right: 0.5rem; text-decoration: none; opacity: 0; transition: opacity 0.3s ease; z-index: 1;" title="Download Poster as PDF">
<i class="fas fa-download"></i>
<span class="copy-text">PDF</span>
</a>
<a href="static/BMVC poster.pdf" target="_blank">
<img src="static/images/poster.png" alt="VETIM - BMVC 2023 Poster" style="max-height: 900px; width: auto; max-width: 100%; display: block; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.15); border-radius: 8px; border: 1px solid rgba(0, 0, 0, 0.08);">
</a>
</div>
</div>
</div>
</div>
</div>
</section>
<!--End Poster -->
<!--BibTex citation -->
<section class="hero is-small" id="BibTeX">
<div class="hero-body">
<div class="container is-max-desktop content">
<div class="columns is-centered">
<div class="column is-four-fifths">
<h2 class="title is-3 has-text-centered">Citation</h2>
<div class="content has-text-justified">
<p>Please use the following BibTeX entry to cite our paper:</p>
</div>
</div>
</div>
<div style="position: relative;">
<button class="copy-bibtex-btn" onclick="copyBibTeX()" title="Copy BibTeX to clipboard" style="position: absolute; top: 0; right: 0; z-index: 1;">
<i class="fas fa-copy"></i>
<span class="copy-text">Copy</span>
</button>
<pre id="bibtex-code"><code>@InProceedings{Everaert_2023_BMVC,
title = {{VETIM}: {E}xpanding the {V}ocabulary of {T}ext-to-{I}mage {M}odels only with {T}ext},
author = {Everaert, Martin Nicolas and Bocchio, Marco and Arpa, Sami and S\"usstrunk, Sabine and Achanta, Radhakrishna},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {{BMVA}},
month = {November},
year = {2023},
url = {https://papers.bmvc2023.org/0016.pdf}
}</code></pre>
</div>
</div>
</div>
</section>
<!--End BibTex citation -->
</main>
<footer class="footer">
<div class="container">
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<p>
This page was built using the <a href="https://github.com/eliahuhorwitz/Academic-project-page-template"
target="_blank">Academic Project Page Template</a> which was adopted from the <a
href="https://nerfies.github.io" target="_blank">Nerfies</a> project page.
</p>
</div>
</div>
</div>
</div>
</footer>
</body>
</html>