<div dir="ltr">
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>Topic: Postdoc position on Deep
Learning and Computer Vision at KAIST, South Korea, on editing of actors’
facial performance videos.<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>Job description: </span><a href="http://cml.kaist.ac.kr/hiring/CML_postdoc_pdf_face_v01.pdf" style="color:blue;text-decoration:underline"><span>http://cml.kaist.ac.kr/hiring/CML_postdoc_pdf_face_v01.pdf</span></a><span>
<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>CML lab website: </span><a href="http://cml.kaist.ac.kr/" style="color:blue;text-decoration:underline"><span>http://cml.kaist.ac.kr/</span></a><span>
<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>Prof. Jean-Charles Bazin: </span><a href="http://cml.kaist.ac.kr/pres_jcbazin.html" style="color:blue;text-decoration:underline"><span>http://cml.kaist.ac.kr/pres_jcbazin.html</span></a><span>
<br>
<br>
</span><span><span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>The
Computational Media Lab (CML) led by Prof. Jean-Charles Bazin at KAIST has one
open postdoc position. The topic is </span><span>Computer Vision and
Deep Learning for automatic editing of actor’s facial performance videos and
face reenactment. This research project will be conducted in collaboration with
Korea’s leading visual effects (VFX) studio.<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>#############################################<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>DETAILED JOB DESCRIPTION AND BENEFITS<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>==> </span><a href="http://cml.kaist.ac.kr/hiring/CML_postdoc_pdf_face_v01.pdf" style="color:blue;text-decoration:underline"><span>http://cml.kaist.ac.kr/hiring/CML_postdoc_pdf_face_v01.pdf</span></a><span>
<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>#############################################<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>SALARY, TERMS AND BENEFITS<br>
------------------------------------------<br>
<br>
<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>Salary: 4.5 millions KRW per month
(around 4,000 US$).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>Contract: one year (renewable, under
conditions).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>Starting date: September 2018 (flexible
until December 2018).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>Vacation: 20 days per year.<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span style="font-size:10pt"><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>KAIST provides a wide range of benefits
including sports facilities (gyms, swimming pool, tennis courts, sauna, etc),
accommodation, restaurants with various choices, on-campus clinic, and many
more.<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span style="font-size:10pt"><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>Workplace: Computational Media Lab
(CML) at KAIST, Daejeon, South Korea. Daejeon is the fifth largest city of
South Korea with a population of over 1.5 million. Daejeon is known as the
Silicon Valley of Korea, and hosts several public and private R&D centers,
such as Samsung and LG. <span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span style="font-size:10pt"><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>Accommodation ranges from 200$
(on-campus dorm) to around 1000$ (large family-apartment with 3 bedrooms
outside the campus) per month.<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span>Income tax is relatively low in Korea
(especially compared to US and Europe), and Korea has an excellent healthcare
system (KAIST even has an on-campus clinic).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><br>
JOB DESCRIPTION<br>
-------------------------<span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>1.
You will conduct research on leveraging computer vision and deep learning
techniques for automatic editing of actor</span><span style="font-family:"Times New Roman"">’</span><span>s
facial performance videos and face reenactement. Possible research topics
include:<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Automatic synchronization of facial
performance videos captured at the same time (linear sync) and at different
times (non-linear sync, see [FaceDirector] and [ActionSnapping]).<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Automatic video stabilization dedicated
to facial performance videos.<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Face reenactement in 2D and 3D (see
[HeadOn] and [Face2Face]).<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Investigation of deep learning for
multi-modal data (audio+video).<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Investigate visual editing (e.g. face
manipulation) but also sound/voice manipulation.<span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>2.
This research project will be conducted in collaboration with Korea’s leading
visual effects (VFX) studio, with state-of-the-art equipment and cutting-edge
technology.<span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>3.
You will be encouraged to publish in major venues of computer vision (CVPR,
ICCV, ECCV, TPAMI, IJCV), graphics (SIGGRAPH, TOG, TVCG) and machine learning
(ICML, NIPS).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt 14.2pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>4.
You will have the opportunity to co-supervise interns, BS students, MS students
and PhD students.<span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span style="font-size:14pt"><span> </span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><i><span>References</span></i><span>:<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>"FaceDirector: Continuous Control
of Facial Performance in Video", ICCV, 2015.<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span style="font-family:"Times New Roman"">“</span><span>HeadOn:
Real-time Reenactment of Human Portrait Videos</span><span style="font-family:"Times New Roman"">”</span><span>,
TOG, 2018.<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span style="font-family:"Times New Roman"">“</span><span>Face2Face:
Real-time Face Capture and Reenactment of RGB Videos</span><span style="font-family:"Times New Roman"">”</span><span>, CVPR, 2016.<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>"ActionSnapping: Motion-based
Video Synchronization", <span>ECCV</span>,
2016<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><br>
<br>
<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>POSITION REQUIREMENTS<span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>-----------------------------------<br>
The candidate should have:<b><u><span></span></u></b></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.3pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>A PhD in computer science, engineering,
mathematics, or other relevant discipline (if thesis submission is pending,
state expected submission date).<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.3pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>A solid background in deep learning (especially
CNN, RNN, LSTM and GAN) and/or computer vision (especially 3D reconstruction
from multiple images and multi-view geometry). <span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.3pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Experience with OpenCV.<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.3pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Experience in computer graphics is a
plus (for example face manipulation, blendshapes, and animation).<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.3pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>A solid publication record in top-tier
venues of computer vision (CVPR, ICCV, ECCV, TPAMI, IJCV), graphics (SIGGRAPH,
TOG, TVCG,) and/or machine learning (ICML, NIPS).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>ABOUT KAIST<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>-------------------<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>KAIST is a world-leading public
research university located in Daejeon, South Korea. KAIST is recognized as a
world-class research university. For example, KAIST is ranked 14th in the world
and 5th within Asia in Engineering and Technology (QS World University
Rankings). KAIST is also ranked 6th in the world and 1st within Asia in the
World's Most Innovative Universities (Reuters). It is also ranked 5th of the
world among the universities that are aged 50 years or under (The Times Higher
Education Rankings).<span> </span>KAIST is also a
global university: more than 80% of major courses are conducted in English, and
international students from more than 70 different countries come to study at
KAIST.<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><br>
<br>
<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>ABOUT CML<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>----------------<span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>Website:
</span><a href="http://cml.kaist.ac.kr/" style="color:blue;text-decoration:underline"><span>http://cml.kaist.ac.kr/</span></a><span>
</span><span><span></span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>The
Computational Media Lab (CML) at KAIST is an interdisciplinary research group
dedicated to the analysis, processing and generation of media contents with
computer algorithms. Examples of our research topics include video editing, AI
(deep learning) for visual data, 3D telepresence, augmented/virtual reality, and
audiovisual media processing. We conduct research in the fields of computer
vision, computer graphics, robotics, machine learning (deep learning) and
multimedia. We invent novel algorithms and create exciting new applications. We
have collaborations and connections with several universities (MIT, ETH Zurich,
NTU Singapore) and companies (Disney Research, Adobe Research, Samsung), as
well as startups. We publish papers in the premier venues of computer vision
(TPAMI, CVPR, ECCV and ICCV), graphics (TOG, SIGGRAPH, and SIGGRAPH Asia) as
well as robotics (IJRR).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>The director of CML is Prof.
Jean-Charles Bazin (</span><a href="http://cml.kaist.ac.kr/pres_jcbazin.html" style="color:blue;text-decoration:underline"><span>http://cml.kaist.ac.kr/pres_jcbazin.html</span></a><span>).
Before joining KAIST, he was an Associate Research Scientist at Disney Research
Zurich, and at the same time an adjunct lecturer at ETH Zurich (2014-2016).
Before joining Disney Research, he was a Postdoc and a Senior Researcher at the
Computer Graphics Laboratory (Prof. Markus Gross) and at Computer Vision and
Geometry Group (Prof. Marc Pollefeys) at ETH Zurich (2011-2014). During this
time, he was a member of the Being There Center and was working in
collaboration with Disney Research Zurich. Before working at ETH, he was a
Postdoctoral Fellow at Computer Vision Lab of Prof. Katsushi Ikeuchi, Tokyo,
Japan (2010/2011). He received an MS in Computer Science at Universite de
Technologie de Compiegne, France (2006) and a PhD in Electrical Engineering at
Robotics and Computer Vision Laboratory, KAIST, South Korea (2011).<span></span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span><br>
<br>
APPLICATION<br>
------------------<br>
If you want to apply or have any queries about the position, please contact
Prof. Jean-Charles (Director of CML) at </span><a href="mailto:bazinjc@kaist.ac.kr" style="color:blue;text-decoration:underline"><span>bazinjc@kaist.ac.kr</span></a><span>.
Please provide:<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>CV with the list of publications.<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>A brief research statement (experience
and interests).<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 21.25pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span>-<span style="font:7pt "Times New Roman"">
</span></span></span><span>Letter of recommendation (not
mandatory, but appreciated).<span></span></span></p>
<p class="gmail-MsoListParagraph" style="margin:0cm 0cm 0.0001pt 18pt;text-align:justify;font-size:12pt;font-family:Cambria"><span><span> </span></span></p>
<p class="MsoNormal" style="text-align:justify;margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span>The
applications will start being reviewed on 25 August 2018 and will continue
until a successful candidate is selected.</span><span></span></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:12pt;font-family:Cambria"><span> </span></p>
</div>