<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="fr">
	<id>https://datafranca.org/wiki/index.php?action=history&amp;feed=atom&amp;title=R%C3%A9cup%C3%A9ration_multimodale</id>
	<title>Récupération multimodale - Historique des versions</title>
	<link rel="self" type="application/atom+xml" href="https://datafranca.org/wiki/index.php?action=history&amp;feed=atom&amp;title=R%C3%A9cup%C3%A9ration_multimodale"/>
	<link rel="alternate" type="text/html" href="https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;action=history"/>
	<updated>2026-04-15T18:36:50Z</updated>
	<subtitle>Historique des versions pour cette page sur le wiki</subtitle>
	<generator>MediaWiki 1.39.5</generator>
	<entry>
		<id>https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110084&amp;oldid=prev</id>
		<title>Pitpitt le 9 novembre 2024 à 03:00</title>
		<link rel="alternate" type="text/html" href="https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110084&amp;oldid=prev"/>
		<updated>2024-11-09T03:00:20Z</updated>

		<summary type="html">&lt;p&gt;&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;fr&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Version précédente&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Version du 8 novembre 2024 à 23:00&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l21&quot;&gt;Ligne 21 :&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Ligne 21 :&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[https://arxiv.org/abs/2308.14263   Source : arxiv]&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[https://arxiv.org/abs/2308.14263   Source : arxiv]&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[[Catégorie:&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;publication&lt;/del&gt;]]&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[[Catégorie:&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;GRAND LEXIQUE FRANÇAIS&lt;/ins&gt;]]&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Pitpitt</name></author>
	</entry>
	<entry>
		<id>https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110076&amp;oldid=prev</id>
		<title>Arianne : Arianne a déplacé la page Cross-Modal Retrieval vers Récupération multimodale</title>
		<link rel="alternate" type="text/html" href="https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110076&amp;oldid=prev"/>
		<updated>2024-11-08T22:42:54Z</updated>

		<summary type="html">&lt;p&gt;Arianne a déplacé la page &lt;a href=&quot;/wiki/Cross-Modal_Retrieval&quot; class=&quot;mw-redirect&quot; title=&quot;Cross-Modal Retrieval&quot;&gt;Cross-Modal Retrieval&lt;/a&gt; vers &lt;a href=&quot;/wiki/R%C3%A9cup%C3%A9ration_multimodale&quot; title=&quot;Récupération multimodale&quot;&gt;Récupération multimodale&lt;/a&gt;&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;fr&quot;&gt;
				&lt;td colspan=&quot;1&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Version précédente&lt;/td&gt;
				&lt;td colspan=&quot;1&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Version du 8 novembre 2024 à 18:42&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-notice&quot; lang=&quot;fr&quot;&gt;&lt;div class=&quot;mw-diff-empty&quot;&gt;(Aucune différence)&lt;/div&gt;
&lt;/td&gt;&lt;/tr&gt;&lt;/table&gt;</summary>
		<author><name>Arianne</name></author>
	</entry>
	<entry>
		<id>https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110075&amp;oldid=prev</id>
		<title>Arianne le 8 novembre 2024 à 22:42</title>
		<link rel="alternate" type="text/html" href="https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110075&amp;oldid=prev"/>
		<updated>2024-11-08T22:42:25Z</updated>

		<summary type="html">&lt;p&gt;&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;fr&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Version précédente&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Version du 8 novembre 2024 à 18:42&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l1&quot;&gt;Ligne 1 :&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Ligne 1 :&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;== en construction ==&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-side-added&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-side-added&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Définition ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Définition ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Basée sur l&amp;#039;&amp;#039;&amp;#039;&amp;#039;[[apprentissage de représentations]]&amp;#039;&amp;#039;&amp;#039;, cette tâche récupère des items &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;provenant &lt;/del&gt;de différentes modalités &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;(&lt;/del&gt;image, texte, vidéo et audio&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;) &lt;/del&gt;à l&amp;#039;aide d&amp;#039;une requête de n&amp;#039;importe quelle modalité &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;et elle &lt;/del&gt;exploite également la complémentarité et la cohérence entre ces données hétérogènes. &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Elle &lt;/del&gt;facilite &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;ainsi &lt;/del&gt;la correspondance sémantique, elle aide les modèles de langue à combiner habilement les informations textuelles et visuelles ainsi qu&amp;#039;à générer du contenu enrichi par des images.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Basée sur l&amp;#039;&amp;#039;&amp;#039;&amp;#039;[[apprentissage de représentations]]&amp;#039;&amp;#039;&amp;#039;, cette tâche récupère des items de différentes modalités&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;, telles que l&amp;#039;&lt;/ins&gt;image, &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;le &lt;/ins&gt;texte, &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;la &lt;/ins&gt;vidéo et &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;l&amp;#039;&lt;/ins&gt;audio à l&amp;#039;aide d&amp;#039;une requête de n&amp;#039;importe quelle modalité&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;. Elle &lt;/ins&gt;exploite également la complémentarité et la cohérence entre ces données hétérogènes. &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Cette tâche &lt;/ins&gt;facilite &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;donc &lt;/ins&gt;la correspondance sémantique, elle aide les modèles de langue à combiner habilement les informations textuelles et visuelles ainsi qu&amp;#039;à générer du contenu enrichi par des images.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Voir aussi &amp;#039;&amp;#039;&amp;#039;[[génération texte-à-image]]&amp;#039;&amp;#039;&amp;#039;, &amp;#039;&amp;#039;&amp;#039;[[modèle de langue]]&amp;#039;&amp;#039;&amp;#039; et &amp;#039;&amp;#039;&amp;#039;[[grand modèle de langues]]&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Voir aussi &amp;#039;&amp;#039;&amp;#039;[[génération texte-à-image]]&amp;#039;&amp;#039;&amp;#039;, &amp;#039;&amp;#039;&amp;#039;[[modèle de langue]]&amp;#039;&amp;#039;&amp;#039; et &amp;#039;&amp;#039;&amp;#039;[[grand modèle de langues]]&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Français ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Français ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;XXXXXX&lt;/del&gt;&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;récupération multimodale&lt;/ins&gt;&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Anglais ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Anglais ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Cross&lt;/del&gt;-&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Modal Retrieval&lt;/del&gt;&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;cross&lt;/ins&gt;-&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;modal retrieval&lt;/ins&gt;&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; CMR&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; CMR&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l23&quot;&gt;Ligne 23 :&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Ligne 21 :&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[https://arxiv.org/abs/2308.14263   Source : arxiv]&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[https://arxiv.org/abs/2308.14263   Source : arxiv]&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[[Catégorie:&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;vocabulary&lt;/del&gt;]]&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;[[Catégorie:&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;publication&lt;/ins&gt;]]&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Arianne</name></author>
	</entry>
	<entry>
		<id>https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110074&amp;oldid=prev</id>
		<title>Arianne le 8 novembre 2024 à 22:38</title>
		<link rel="alternate" type="text/html" href="https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110074&amp;oldid=prev"/>
		<updated>2024-11-08T22:38:00Z</updated>

		<summary type="html">&lt;p&gt;&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;fr&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Version précédente&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Version du 8 novembre 2024 à 18:38&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l2&quot;&gt;Ligne 2 :&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Ligne 2 :&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Définition ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Définition ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;XXXXX&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Basée sur l&amp;#039;&amp;#039;&amp;#039;&amp;#039;[[apprentissage de représentations]]&amp;#039;&amp;#039;&amp;#039;, cette tâche récupère des items provenant de différentes modalités (image, texte, vidéo et audio) à l&amp;#039;aide d&amp;#039;une requête de n&amp;#039;importe quelle modalité et elle exploite également la complémentarité et la cohérence entre ces données hétérogènes. Elle facilite ainsi la correspondance sémantique, elle aide les modèles de langue à combiner habilement les informations textuelles et visuelles ainsi qu&amp;#039;à générer du contenu enrichi par des images.&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Voir aussi &amp;#039;&amp;#039;&amp;#039;[[génération texte-à-image]]&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Voir aussi &amp;#039;&amp;#039;&amp;#039;[[génération texte-à-image&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;]]&amp;#039;&amp;#039;&amp;#039;, &amp;#039;&amp;#039;&amp;#039;[[modèle de langue]]&amp;#039;&amp;#039;&amp;#039; et &amp;#039;&amp;#039;&amp;#039;[[grand modèle de langues&lt;/ins&gt;]]&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Français ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Français ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l14&quot;&gt;Ligne 14 :&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Ligne 14 :&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; CMR&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&amp;#039; CMR&amp;#039;&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Cross-Modal Retrieval (CMR) is a &lt;/del&gt;task &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;of retrieving &lt;/del&gt;items across different modalities&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;, such as &lt;/del&gt;image, text, video&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;, &lt;/del&gt;and audio&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;. The core challenge of CMR is the heterogeneity gap&lt;/del&gt;, &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;which arises because &lt;/del&gt;data &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;from different modalities have distinct representations, making direct comparison difficult&lt;/del&gt;. &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;To address this, most CMR methods focus on learning a shared latent embedding space. In this space, concepts from different modalities are projected, allowing their similarity &lt;/del&gt;to &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;be measured using a distance metric&lt;/del&gt;.&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Based on representation learning, this &lt;/ins&gt;task &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;retrieves &lt;/ins&gt;items across different modalities &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;(&lt;/ins&gt;image, text, video and audio&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;) using a query from any one modality&lt;/ins&gt;, &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;and it also leverages complementary and consistency between heterogenous &lt;/ins&gt;data. &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;It facilitates semantic matching and helps language models &lt;/ins&gt;to &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;combine adeptly textual and visual information&lt;/ins&gt;.&amp;#039;&amp;#039;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br/&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Source ==&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;== Source ==&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Arianne</name></author>
	</entry>
	<entry>
		<id>https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110047&amp;oldid=prev</id>
		<title>Arianne : Page créée avec « == en construction ==  == Définition == XXXXX  Voir aussi &#039;&#039;&#039;génération texte-à-image&#039;&#039;&#039;  == Français == &#039;&#039;&#039; XXXXXX&#039;&#039;&#039;  == Anglais == &#039;&#039;&#039; Cross-Modal Retrieval&#039;&#039;&#039;  &#039;&#039;&#039; CMR&#039;&#039;&#039;  &#039;&#039;Cross-Modal Retrieval (CMR) is a task of retrieving items across different modalities, such as image, text, video, and audio. The core challenge of CMR is the heterogeneity gap, which arises because data from different modalities have distinct representations, making direct compa... »</title>
		<link rel="alternate" type="text/html" href="https://datafranca.org/wiki/index.php?title=R%C3%A9cup%C3%A9ration_multimodale&amp;diff=110047&amp;oldid=prev"/>
		<updated>2024-11-06T16:08:29Z</updated>

		<summary type="html">&lt;p&gt;Page créée avec « == en construction ==  == Définition == XXXXX  Voir aussi &amp;#039;&amp;#039;&amp;#039;&lt;a href=&quot;/wiki/G%C3%A9n%C3%A9ration_texte-%C3%A0-image&quot; title=&quot;Génération texte-à-image&quot;&gt;génération texte-à-image&lt;/a&gt;&amp;#039;&amp;#039;&amp;#039;  == Français == &amp;#039;&amp;#039;&amp;#039; XXXXXX&amp;#039;&amp;#039;&amp;#039;  == Anglais == &amp;#039;&amp;#039;&amp;#039; Cross-Modal Retrieval&amp;#039;&amp;#039;&amp;#039;  &amp;#039;&amp;#039;&amp;#039; CMR&amp;#039;&amp;#039;&amp;#039;  &amp;#039;&amp;#039;Cross-Modal Retrieval (CMR) is a task of retrieving items across different modalities, such as image, text, video, and audio. The core challenge of CMR is the heterogeneity gap, which arises because data from different modalities have distinct representations, making direct compa... »&lt;/p&gt;
&lt;p&gt;&lt;b&gt;Nouvelle page&lt;/b&gt;&lt;/p&gt;&lt;div&gt;== en construction ==&lt;br /&gt;
&lt;br /&gt;
== Définition ==&lt;br /&gt;
XXXXX&lt;br /&gt;
&lt;br /&gt;
Voir aussi &amp;#039;&amp;#039;&amp;#039;[[génération texte-à-image]]&amp;#039;&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
== Français ==&lt;br /&gt;
&amp;#039;&amp;#039;&amp;#039; XXXXXX&amp;#039;&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
== Anglais ==&lt;br /&gt;
&amp;#039;&amp;#039;&amp;#039; Cross-Modal Retrieval&amp;#039;&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
&amp;#039;&amp;#039;&amp;#039; CMR&amp;#039;&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
&amp;#039;&amp;#039;Cross-Modal Retrieval (CMR) is a task of retrieving items across different modalities, such as image, text, video, and audio. The core challenge of CMR is the heterogeneity gap, which arises because data from different modalities have distinct representations, making direct comparison difficult. To address this, most CMR methods focus on learning a shared latent embedding space. In this space, concepts from different modalities are projected, allowing their similarity to be measured using a distance metric.&amp;#039;&amp;#039;&lt;br /&gt;
&lt;br /&gt;
== Source ==&lt;br /&gt;
[https://paperswithcode.com/task/cross-modal-retrieval   Source : Paper with code]&lt;br /&gt;
&lt;br /&gt;
[https://medium.com/@thube09/cross-modal-retrieval-in-advanced-language-models-bridging-text-and-visual-information-7158f4fface3   Source : Medium]&lt;br /&gt;
&lt;br /&gt;
[https://arxiv.org/abs/2308.14263   Source : arxiv]&lt;br /&gt;
&lt;br /&gt;
[[Catégorie:vocabulary]]&lt;/div&gt;</summary>
		<author><name>Arianne</name></author>
	</entry>
</feed>