Journal article Closed Access

Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes

Hao Tang; Nicu Sebe

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="">
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-06-26</subfield>
  <controlfield tag="005">20210627194908.0</controlfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-ai4media</subfield>
  <controlfield tag="001">5034672</controlfield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">user-ai4media</subfield>
    <subfield code="o"></subfield>
  <datafield tag="909" ind1="C" ind2="4">
    <subfield code="p">IEEE TRANSACTIONS ON MULTIMEDIA</subfield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;We propose a novel and unified Cycle in Cycle Generative Adversarial Network (C2GAN) for generating human faces, hands, bodies, and natural scenes. Our proposed C2GAN is a cross-modal model exploring the joint exploitation of the input image data and guidance data in an interactive manner. C2GAN contains two different generators, i.e., an image-generation generator and a guidance-generation generator. Both generators are mutually connected and trained in an end-to-end fashion and explicitly form three cycled subnets, i.e., one image generation cycle and two guidance generation cycles. Each cycle aims at reconstructing the input domain and simultaneously produces a useful output involved in the generation of another cycle. In this way, the cycles constrain each other implicitly providing complementary information from both image and guidance modalities and bringing an extra supervision gradient across the cycles, facilitating a more robust optimization of the whole model. Extensive results on four guided image-to-image translation subtasks demonstrate that the proposed C2GAN is effective in generating more realistic images compared with state-of-the-art models.&lt;/p&gt;</subfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento, Italy</subfield>
    <subfield code="a">Nicu Sebe</subfield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">closed</subfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">article</subfield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Trento, Italy</subfield>
    <subfield code="a">Hao Tang</subfield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1109/TMM.2021.3091847</subfield>
    <subfield code="2">doi</subfield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes</subfield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">951911</subfield>
    <subfield code="a">A European Excellence Centre for Media, Society and Democracy</subfield>
Views 13
Downloads 1
Data volume 7.9 MB
Unique views 12
Unique downloads 1


Cite as