BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Towards generating Deep Art
DTSTART:20210824T103000
DTEND:20210824T123000
DTSTAMP:20260407T004040Z
UID:1ab224752c9c73d1b79bbce4ce1cb615770f64b32d67aaa544ebc5ef
CATEGORIES:Conferences - Seminars
DESCRIPTION:Ehsan Pajouheshgar\nEDIC candidacy exam\nexam president: Prof.
  Wenzel Jakob\nthesis advisor: Prof. Sabine Süsstrunk\nco-examiner: Prof.
  Pascal Fua\n\nAbstract\nWe investigate recent deep generative models like
  StyleGAN2 and how they can be controlled by a textual description using t
 he OpenAI Clip network.\n\nBackground papers\n1 -  A Style-Based Generat
 or Architecture for Generative Adversarial Networks 1' - Analyzing and Im
 proving the Image Quality of StyleGAN\n2 - GAN DISSECTION: VISUALIZING AN
 D UNDERSTANDING GENERATIVE ADVERSARIAL NETWORKS\n3 - Editing in Style: Un
 covering the Local Semantics of GANs\n 
LOCATION:
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR