https://datafranca.org/wiki/index.php?action=history&feed=atom&title=Paper2Video 2026-04-16T19:34:57Z Historique des versions pour cette page sur le wiki MediaWiki 1.39.5 https://datafranca.org/wiki/index.php?title=Paper2Video&diff=117633&oldid=prev 2025-10-28T01:02:48Z

<p>Page créée avec « == EN CONSTRUCTION == == Définition == xxxxx == Français == &#039;&#039;&#039;xxxxx &#039;&#039;&#039; == Anglais == &#039;&#039;&#039;Paper2Video&#039;&#039;&#039; Automatic Video Generation from Scientific Papers A system that automatically generates academic presentation videos from research papers. The work addresses the time-consuming process of creating presentation videos, which typically requires hours of slide design, recording, and editing for just a few minutes of content. The paper presents both a be... »</p> <p><b>Nouvelle page</b></p><div>== EN CONSTRUCTION ==<br /> <br /> == Définition ==<br /> xxxxx<br /> <br /> == Français ==<br /> &#039;&#039;&#039;xxxxx &#039;&#039;&#039;<br /> <br /> == Anglais ==<br /> &#039;&#039;&#039;Paper2Video&#039;&#039;&#039;<br /> <br /> Automatic Video Generation from Scientific Papers<br /> <br /> A system that automatically generates academic presentation videos from research papers. The work addresses the time-consuming process of creating presentation videos, which typically requires hours of slide design, recording, and editing for just a few minutes of content. The paper presents both a benchmark for evaluating such systems and a multi-agent framework called PaperTalker that can produce complete presentation videos with slides, speech, subtitles, and a talking presenter.<br /> PaperTalker is a multi-agent framework that automates academic presentation video generation by integrating slide generation, layout refinement, subtitling, speech synthesis, and talking-head rendering, outperforming existing methods.<br /> <br /> ==Sources==<br /> [https://huggingface.co/papers/2510.05096 Sources : huggingface]<br /> <br /> <br /> [[Catégorie:vocabulary]]</div>

Pitpitt